Geocarto International

ISSN: (Print) (Online) Journal homepage: www.tandfonline.com/journals/tgei20

Landslide dynamic hazard prediction based on

precipitation variation trend and backpropagation
neural network

Ruixuan Huang, Bin Zeng, Dong Ai, Jingjing Yuan & Huiyuan Xu

To cite this article: Ruixuan Huang, Bin Zeng, Dong Ai, Jingjing Yuan & Huiyuan Xu
(2024) Landslide dynamic hazard prediction based on precipitation variation trend
and backpropagation neural network, Geocarto International, 39:1, 2322058, DOI:
10.1080/10106049.2024.2322058

To link to this article: https://doi.org/10.1080/10106049.2024.2322058

© 2024 The Author(s). Published by Informa

UK Limited, trading as Taylor & Francis
Group

Published online: 27 Feb 2024.

Submit your article to this journal

Article views: 631

View related articles

View Crossmark data

Full Terms & Conditions of access and use can be found at

https://www.tandfonline.com/action/journalInformation?journalCode=tgei20
GEOCARTO INTERNATIONAL
2024, VOL. 39, NO. 1, 2322058
https://doi.org/10.1080/10106049.2024.2322058

Landslide dynamic hazard prediction based on

precipitation variation trend and backpropagation
neural network
Ruixuan Huanga, Bin Zenga, Dong Aib, Jingjing Yuanb and Huiyuan Xub
a
School of Environmental Studies, China University of Geosciences, Wuhan, China; bThe Seventh
Geological Brigade of Hubei Geological Bureau, Yichang, China

ABSTRACT ARTICLE HISTORY

The assessment of landslide hazards is crucial for disaster preven­ Received 12 November 2023
tion and mitigation, but it has not considered the dynamic influ­ Accepted 16 February 2024
encing factors that trigger landslides. The timeliness and practical
KEYWORDS
value of the assessment results still need to be further improved.
Landslides; dynamic hazard
This study constructed a dynamic landslide hazard assessment assessment; precipitation
system using information value model, dynamic precipitation variation trend; BPNN;
data, and Backpropagation Neural Network (BPNN) model. Taking remote sensing
the Qingjiang Reservoir landslide in Changyang County, Hubei
Province, China as an example, based on dynamic precipitation
data and the BPNN model were used to develop a dynamic land­
slide hazard prediction model, and the temporal assessment and
spatial distribution results of slope unit hazards in the study area
from the 1980s to the 2010s, 2025, and 2030 were evaluated and
predicted. It is predicted that the percentage of very high and
high areas in 2025 and 2030 will be 50.5% and 57.5%
respectively.

1. Introduction
With the continuous expansion of urban scale and the impact of extreme weather, land­
slides have become exceedingly common and extremely harmful natural disasters world­
wide (Petley 2012), significantly impacting people’s production and livelihood (Froude
and Petley 2018). Determining the range of landslide-prone areas holds significant mean­
ing in reducing economic losses and casualties brought upon by such disasters
(Arabameri et al. 2019; Pardeshi et al. 2013; Peruccacci et al. 2023). From 1940 to 2020, it
is estimated that 14,394 people died of landslides in China (Zhang et al. 2023). According
to the statistical data of China’s Ministry of Natural Resources (https://www.mnr.gov.cn/),
there were 5659 geological disasters such as landslides, collapses, and debris flows in 2022,
resulting in a total of 90 deaths, 16 missing people, 34 injured people, and direct eco­
nomic losses of 1.5 billion yuan. Among them, 3919 landslides occurred. Under these

CONTACT Bin Zeng [email protected]

� 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/
licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by
the author(s) or with their consent.
2 R. HUANG ET AL.

circumstances, conducting a landslide catastrophe investigation and assessment system as

well as enhancing and promoting research in disaster prevention and mitigation remains
a topic of keen interest for various countries.
Carrara, A. (Carrara et al. 1995) analyzed the landslide susceptibility of slope units in
small watersheds in Italy and defined the landslide susceptibility assessment. Landslide
susceptibility assessment is the basis of landslide hazard assessment and landslide risk
assessment, which reflects the spatial probability of the slope evolving into a landslide
under the action of its basic environmental factors (Griffiths et al. 2002; Guzzetti et al.
2005; Huang et al. 2020; Huang et al. 2021; Jun et al. 2016; Li et al. 2020; Wang et al.
2024). The research system of landslide susceptibility assessment is widely used to solve
the threat of landslides to people’s lives, property safety and social and economic develop­
ment (Baeza and Corominas 2001; Gokceoglu 2002). Landslide hazard assessment is based
on the assessment of landslide susceptibility, considering the dynamic influence of land­
slide induced factors on landslide, and predicting the possibility of landslide hazard (Fell
et al. 2008; Tyagi et al. 2022). In recent years, with the gradual improvement of the land­
slide assessment system, the research on landslide hazard assessment has also increased
year by year. As a key step in predicting landslides and formulating disaster prevention
and mitigation policies, landslide hazard assessment has become a subject of in-depth
study by scholars (Singh and Kumar 2018; Tan et al. 2021; Versain et al. 2019).
Moreover, it serves as a significant component of international disaster risk reduction
strategies, playing a vital role in disaster management. Through this approach, decision-
makers can assess potential hazards, thereby reducing human and property losses (Hader
et al. 2022; Shahzad et al. 2022; Skrzypczak et al. 2021). In the subtropical monsoon cli­
mate area, a short period of heavy precipitation is easy to cause landslides (Zeng et al.
2023). However, from the content of landslide hazard assessment, over the years, the
existing research mainly focuses on the selection of relatively stable geological environ­
ment factors and triggering factors for landslide hazard assessment (Basharat et al. 2023;
Wang et al. 2014; Yang 2017). At present, landslide hazard assessment based on precipita­
tion factors is mainly based on landslide susceptibility assessment, and the calculated pre­
cipitation thresholds (Huang et al. 2022) or extreme precipitation in different
precipitation return periods (Kawagoe et al. 2010) is the disaster-causing factor, and the
result is a static assessment under specific precipitation conditions. Because the factors
that trigger landslide disasters such as climate and precipitation have dynamic trends, the
hazard of landslide disasters will also change dynamically (Sui et al. 2022; Tang et al.
2017). It is necessary to add the evolution process of precipitation dynamic changes to
the prediction of landslide hazard.
Significant progress has been achieved in the field of landslide hazard assessment due
to the continual advancements in Geographic Information System (GIS), Remote Sensing
(RS), and Global Positioning System (GPS) (Pan et al. 2021; Wang et al. 2022). With the
deepening of research, various statistical models based on GIS technology are becoming
more and more diversified, which can be summarized as heuristic models, mathematical
statistical models and machine learning models. The heuristic models and mathematical
statistical models that have been widely used are the expert scoring method, analytic hier­
archy process, information value method, frequency ratio method, etc. Yang used the
expert scoring method (Yang et al. 2023), Panchal & Shrivastava (2022) and Zangmene
(Zangmene et al. 2023) used the analytic hierarchy process to assign weights to different
disaster-causing factors and draw landslide hazard maps. Afungang (Afungang et al. 2017)
used the information value model to link the geological environment factors with previ­
ous landslides and assessed the hazard of landslides that may occur in the future in
 GEOCARTO INTERNATIONAL 3

Bamenda highlands. Wubalem and Meten (Wubalem and Meten 2020) used the informa­
tion value model to provide a more accurate prediction of landslide hazard in an area of
northwest Ethiopia. Khan (Khan et al. 2019) studied the impact of disaster-causing factors
on the spatial distribution of landslides and used the frequency ratio method to draw a
landslide susceptibility zoning map in northern Pakistan. With the advancement of com­
puter technology, machine learning models have gradually been used to study landslide
hazard assessment. Lee selected 17 factors that have a greater impact on the occurrence of
landslides and used two methods of support vector machine and artificial neural network
to predict the susceptibility of landslides in the study area (Lee & Lee et al. 2017). Based
on the support vector machine method, Lee analyzed the landslide susceptibility of two
different regions in South Korea (Huang and Zhao 2018; Lee, Hong, et al. 2017). Niu
used BPNN to construct an intelligent safety early warning system (Niu 2020), and
Mehrabi used a multilayer perceptron neural network to predict landslide susceptibility in
a certain area of Italy (Mehrabi 2022). Kim used random forest and boosted tree models
to analyze and verify the susceptibility of landslides in the Pyeong-Chang area (Kim et al.
2018). Through these machine learning approaches, researchers can conduct decision ana­
lysis on the probability of landslide occurrences and effectively enhance the reliability of
landslide hazard assessment (Karakas et al. 2023; Yu and Chen 2020; Zhao et al. 2022).
The traditional mathematical statistical model mainly analyzes the historical landslide,
determines influencing factors, and calculates the probability of landslide occurrence
based on these influencing factors; the machine learning model learns complex rules from
data without clarifying the correlation between various influencing factors, and predicts
landslides based on training samples (Zou et al. 2023). On this basis, the mathematical
statistical model and machine learning model are used to assessment the hazard of land­
slides, which can not only predict the relationship between the occurrence of landslides
and various influencing factors but also accurately predict the hazard of landslides.
However, the method of combining mathematical statistics with machine learning for
landslide hazard assessment is not widely used in current research and application.
Based on the above analysis, to identify potentially hazardous areas for landslide disas­
ters under the influence of dynamic factors and assist decision-makers in better prevent­
ing and responding to landslide disasters (Xu et al. 2019; Yu et al. 2022), this paper fully
considers the dynamic impact of climate change on the hazard of landslide. Located in
Changyang County, Hubei Province, this study examines landslide disasters along the
Qingjiang River. Based on the assessment of landslide susceptibility using the information
value method, the precipitation from the 1980s to 2010s and the predicted precipitation
in 2025 and 2030 were introduced as triggering factors, and the dynamic prediction
model of landslide hazard was constructed by BPNN. The dynamic hazard of landslides
in the study area in the past few decades was analyzed to predict the dynamic hazard of
landslides in the next 5-10 years. The research findings not only be used as a reference for
the system of geological disaster hazard assessment in mountainous areas but also offer
scientific decision-making and guidance for effectively preventing and mitigating moun­
tainous landslide disasters in Changyang County.

2. Study area
Along the middle and lower reaches of the Qingjiang River, the research area is situated
in Hubei Province, China. It has a strip-like distribution along the mainstream of the
Qingjiang River, spanning 42 km east to west and 12 km north to south, with a total area
of 504 km2. Over 90% of the research area consists of mountainous terrain, characterized
4 R. HUANG ET AL.

by well-developed valleys, and the overall direction of rivers and mountain ranges is pre­
dominantly east-west. The research area is situated at an elevation ranging from 141 to
1302 meters above sea level, with a general topography showing higher elevations in the
north-south direction and lower elevations in the east-west direction, as illustrated in
Figure 1. The stratigraphic lithology of the study area is mainly composed of limestone of
the Lower Triassic Daye Formation (T1d), limestone of the Upper Permian Dalong
Formation (P3d), and mud shale of the Wu Jiaping Formation (P3w). The Carboniferous
(C1-2) and Devonian (D) sandstone and siltstone strata are secondary. The Quaternary is
mainly a colluvial deposit (Q4dl þ col), which is composed of gravel, sandy soil, and clayey
soil fragments. Water resources are abundant in the research area which belongs to the
subtropics monsoon climate. The average annual precipitation is approximately
1366.2 mm, with over 75% of the total amount falling from April to September. Seasonal
heavy rainfall is the main triggering factor of landslides in Qingjiang Reservoir.
Through the high-resolution remote sensing interpretation, unmanned aerial vehicle
photography interpretation, and field investigation of the Hubei Geological Bureau, a total
of 43 landslides occurred in the Qingjiang Reservoir from the 1980s to 2010s, of which 23
were fording landslides, which account for 53.5% of all the landslides in the area.
Influenced by the overall slope structure distribution with a predominantly dip slope on
the left bank and a predominantly reverse slope on the right bank of the Qingjiang River
segment in the research area, landslides mainly occur on dip slope and skew slope. The
number of landslides gradually increases from west to east, with a higher density along
the Qingjiang River coast from Yu Xiakou Town to Ziqiu Town (Figure 1). The landslides

Figure 1. Study area location and distribution of landslides.

 GEOCARTO INTERNATIONAL 5

in the research area are mainly accumulation landslides, with small to medium scales. The
material source is primarily composed of cohesive soil, gravel soil mixed with fractured
limestone blocks, and most of them are traction-type soil landslides.

3. Methods
Figure 2 illustrates the research technical process employed in this study. Firstly, a static
susceptibility assessment index system for landslides is established using the information value
model. Using 13 influencing factors including elevation difference, slope degree, slope aspect,
slope structure, total curvature, lithology, distance to fault, distance to river, distance to road,
normalized difference vegetation index (NDVI), topographic wetness index (TWI), stream
power index (SPI), and depth of overburden. The assessment is conducted on individual slope
units, and a susceptibility zoning map is generated. Secondly, dynamic precipitation factors
are introduced considering the geological and meteorological-hydrological conditions of the
study area. The landslide dynamic hazard assessment is calculated by BPNN. Lastly, the
accuracy of both susceptibility and hazard assessment results is verified through ROC and
field investigation and validation.

3.1. Determine the mapping units

Before the landslide susceptibility and hazard assessment, the study area should be divided
into reasonable mapping units. As the fundamental units for data extraction and index
assignment, mapping units reflect both homogeneity within units and heterogeneity

Figure 2. Flow chart of this study.

6 R. HUANG ET AL.

between units. Hence, the precision of mapping units is heavily reliant on the accuracy of
input data and the resulting assessment outcomes (Sun et al. 2020). Grid units, slope
units, geomorphologic units, and watershed units are examples of frequently used map­
ping units (Ba et al. 2018). The grid unit is the most commonly used landslide disaster
unit, which has the characteristics of constant shape, easy calculation, and easy sampling
(Reichenbach et al. 2018). However, each grid unit often contains a variety of different
geological structures, because there is no direct physical relationship between geomorpho­
logical information and grid units (Chang et al. 2023). From the point of view of topog­
raphy, the slope unit can well contain the topography conditions of the study area. Each
slope unit has both internal identity and different characteristics from other slope units,
which well reflects the relationship between the mapping units and the topography (Liu
et al. 2022). Topography features play a crucial role in the formation and occurrence of
landslides, and slope units capture the topographic characteristics of the study area effect­
ively. The study area is a medium-low mountain landform. Qingjiang River passes
through its territory, forming a unique gully landform area. The mountains on both sides
of the valley are steep, and the slopes are mostly steep. Therefore, the slope units are
selected as the mapping units of this paper. Each slope unit exhibits internal homogeneity
and external heterogeneity when compared to other slope units, thus reflecting the rela­
tionship between mapping units and terrain features. In the division of slope units, the
current representative division methods are the hydrological analysis method and curva­
ture watershed method (Carrara et al. 1995; Guzzetti et al. 1999; Kai et al. 2020; Wang
et al. 2017)
In this paper, the hydrological analysis method with a good division effect and moder­
ate workload is used to divide the slope unit. This method takes the ridge line and the
valley line as the boundary of the catchment area, and takes the middle of the ridge line
and the valley line as the slope unit. This method considers both the flow movement and
the topographic factors so that it can better reflect the spatial distribution of the slope
unit in the gully landform area. It avoids the defect that the valley line cannot be identi­
fied in the plain and river areas. The digital elevation model (DEM) (https://search.asf.
alaska.edu/#/) with a spatial resolution of 12.5 m is used to divide the slope unit in
ArcGIS software. Positive and negative topographic techniques were used to extract ridge
and valley lines, while hydrological analysis techniques were used to identify slope units.
The resulting watersheds and reverse watersheds were merged to acquire slope units.
Finally, slope units were adjusted based on mountain shadows, remote sensing images,
slope aspect, and lithology to obtain a more realistic slope unit.

3.2. Factors causing landslides

Based on the unique gully landform characteristics of the study area, based on the basic
types and spatial and temporal distribution of landslides, this paper divided the influenc­
ing factors into static and dynamic parts from the availability (Table 1), operability and
scientificity, and the static susceptibility and dynamic hazard assessment system of land­
slides are established respectively.

3.2.1. Static influencing factors

The damage of landslides was heavily affected by topography, engineering geology,
hydrology and human engineering activities. According to the characteristics of the study
area, the landslide static influencing factors are divided into four categories and 13 spe­
cific indicators, which are used for landslide susceptibility mapping.
 GEOCARTO INTERNATIONAL 7

Table 1. Source of landslide influencing factors in this research.

Assignment method
Data classification Factors Data source Data type of slope units
Landslides data Landslides inventory Department of Geological
Survey
Static influencing Elevation Difference DEM calculation Continues Majority
factors Slope Degree Continues Majority
Slope Aspect Categorical Majority
Curvature Continues Majority
Slope Structure Field investigation Categorical Majority
Distance to fault Geological map of Continues Average value
Lithology Changyang County Categorical Majority
Depth of overburden Field investigation Continues Majority
TWI DEM calculation Continues Majority
SPI Continues Majority
NDVI Landsat-8 (202107) Continues Majority
Distance to river Geological map of Continues Average value
Changyang County
Distance to road Topographic map of Continues Average value
Changyang County
Dynamic influencing Average annual Data Centre for Resource Continues Majority
factors precipitation in and Environmental
1980s-2010s, Sciences, Chinese
2025 and 2030 Academy of Sciences

The selection analysis of each influencing factor is as follows: (1) topography: the
greater the elevation difference and slope degree, the higher the sliding speed of the land­
slide formed, and the greater the impact on slope degree damage. The slope aspect has a
local influence on triggering slope instability, such as the effects of sunlight (vegetation
and cut slope building) and precipitation infiltration (soil moisture) (Chawla et al. 2019),
and most landslides in the area always occur in the south. Total curvature reflects the
geometry within slopes, which is a direct relation towards the efficiency of precipitation
infiltration. Slope structure refers to the difference between slope direction and inclination
of the bedrock of the slope body, and the density of landslides is highest on dip slope and
skew slopes. (2) engineering geology: due to the more fragmented rock and soil in the
range affected by the fault fracture zone, the number of landslides is relatively large (Das
et al. 2023). The higher mechanical strength of rocks and soils that make up the landslide
body, the less likely the landslide will occur. At the same time, the thicker the loose accu­
mulation body on slopes, the obvious stress concentration inside slopes, and the lower
stability of slopes. (3) hydrology: TWI is an indicator that can be utilized to demonstrate
effect of the terrain on runoff direction and accumulation, reflecting the spatial distribu­
tion characteristics of soil moisture. SPI can represent distribution and rate of water flow,
with lager values representing more erosive force of water flow in the area. NDVI is
a measure of vegetation density on slopes, which plays a crucial role in soil strength.
The closer slopes are to rivers, the more likely slopes toe erosion will occur, thereby
increasing the probability of slope failure (Yan et al. 2022). (4) human engineering activ­
ities: the high and steep cut slopes caused by road construction are the most significant
factors impacting slope stabilization.
After processing, each of various influencing factors were projected into the Word
Geodetic System 1984 (WGS84) coordinate system and formatted into 12.5 m resolution
grid data. This generated multi-source spatial data that could be used in spatial overlay
and modeling manipulation, preparing for subsequent conversion into slope units. When
using slope units as mapping units, each influencing factor can only have one value
8 R. HUANG ET AL.

within a slope unit. Therefore, different statistical methods need to be adopted for con­
tinuous and categorical influencing factors (Chang et al. 2023; Sun et al. 2023). Except for
distance to road, fault and river, which are the average distances for each grid within the
slope unit, the remaining influencing factors are the majority number of the influencing
factors of each grid within the slope unit. Finally, the natural break method (Wubalem
2020) is used in classifying each influencing factor.

3.2.2. Dynamic influencing factors

In the research area, there were 14, 12, 8, and 9 landslides that occurred from the 1980s
to 2010s, respectively. Based on completing the static susceptibility assessment of land­
slides, the dynamic impact factor system is formed by introducing dynamic precipitation
factors, in conjunction with the static susceptibility influencing factors, to be used for
mapping the dynamic hazard of landslides. Precipitation data was downloaded from the
Data Centre for Resource and Environmental Sciences, Chinese Academy of Sciences (Xu
2017). The type of data is average annual precipitation (year/mm), and precipitation data
for the periods of 1980s-2010s and 2010-2022 are downloaded.
The downloaded vector data were formatted into 12.5 m resolution raster data in
ArcGIS and projected in the WGS84 coordinate system, and the average annual precipita­
tion data from 2010 to 2022 were extracted based on the random points generated by
ArcGIS to form the extraction points, and the time series forecasting analysis (Liu et al.
2011) was performed by Statistical Product and Service Solutions (SPSS) software to
obtain the average annual precipitation in 2025 and 2030. Then, the predicted precipita­
tion data for the study area in 2025 and 2030 is obtained using Inverse Distance
Weighted (IDW) (Sheng et al. 2021) interpolation in ArcGIS software in Figure 3. The
majority of the precipitation data raster was assigned to slope units, and finally, the pre­
cipitation factors were categorized into five classes using the natural break method. The
precipitation data from the 1980s-2010s in the study area were used to perform the
dynamic landslide hazard analysis for the past decades, and the precipitation data from
2025 and 2030 predicted to be obtained were used to predict the dynamic landslide haz­
ard for the next 5-10 years.

3.3. Information value model

The formation of geological disasters is affected by many factors. Information value model
(Lin et al. 2021) reflects how the most disaster-causing factors and their subdivision inter­
vals are combined in a certain geological environment. Specifically, it is achieved by com­
paring the rate of occurrence of geological hazards with the frequency of regional
geological hazards under the action of a certain factor in a specific assessment unit. The
assessment steps and basic principles of the information value method are as follows (Ji
et al. 2023):

Figure 3. Flow chart of average annual precipitation forecasts for 2025 and 2030.
 GEOCARTO INTERNATIONAL 9

1. Information value formula can be expressed for each factor under different condi­
tions as follows:

Nj =N
IAj ¼ ln ðj ¼ 1, 2, 3, . . . , nÞ (1)
Sj =S
In the formula, IAj represents amount of information of landslide disaster under the
condition of factor A in j, Nj is the number of slope units of landslide
disaster distribution of factor A in j state, and N is the number of slope units with land­
slide disaster distribution in the survey area. Sj is the number of slope elements containing
A in j state, and S represents number of total slope units in investigation area.

Under the combined effect of various state factors, total landslide hazard information of a
slope unit can be defined by following formula:

X
n
Nj=N
Ii ¼ ln ðj ¼ 1, 2, 3, . . . , nÞ (2)
i¼1
Sj=S

In the formula, Ii indicates total geological disaster information for a slope unit, and n is
the number of influencing factors. The sum of information from a slope unit is used as a
comprehensive index to evaluate whether a landslide disaster occurs. The greater the
value, the more susceptible the slope unit is.

3.4. BPNN model

In this study, BPNN in an artificial neural network is used to help realize the landslide
risk assessment. The BPNN was initially proposed by Rumelhart and McClelland as a
multilayer feedforward neural network using an error backpropagation algorithm for
training (Pham et al. 2019; Rumelhart et al. 1986; Zhang et al. 2021). The BPNN is seg­
mented into three layers: input layer, hidden layer, and output layer. Neurons in neigh­
boring layers are connected, but neurons in every layer are not continuous. A BPNN can
accurately represent any continuous function. During the forward pass, the learning signal
enters the input layer, undergoes data processing in hidden layer, and produces output in
output layer. When the output does not match the desired result, network enters backpro­
pagation of error mode. After propagating backward to the hidden layer, the error
sequentially returns to the input layer. During the error backpropagation process, the
error is evenly distributed among the hidden layer units, and the weights of each neuron
are modified based on the error signal. This process of forward and backward error
propagation continues until the output reaches the desired result, and the training stops.
A learning process (including training and verification) and a prediction procedure com­
prise the BPNN model.

1. Establishment of the model

MATLAB software is used to program the BPNN model in this paper. Three-layer
topology was chosen by the BPNN model in this study: an input layer, a hidden
layer, and an output layer. Assume that there are m neurons in the input layer, n
neurons in the hidden layer, and l neurons in the output layer. The number of
10 R. HUANG ET AL.

landslide dynamic influencing factors (m ¼ 14) is the number of neurons in the input
layer of the BPNN model. Using f(x) as the activation function of the hidden layer
and g(x) as the activation function of the output layer, the mathematical equation of
BPNN can be expressed as:

!
X
m
Yi ¼ f wij Xi þ bj (3)
i¼1
ex − e−x
f ðx Þ ¼ (4)
ex þ e−x
!
X
n
Yk ¼ g wjk Yi þ bk (5)
j¼1

g ðx Þ ¼ x (6)
In the above formula, Yi represents the output of the i neuron in the hidden layer, Xi
is the output value of the i neuron in the input layer, wij represents the connection weight
between the input layer and the hidden layer, and bj is the threshold of the j neuron in
the hidden layer. Yk is the output of the k neuron in the output layer, wjk represents the
connection weight between the hidden layer and the output layer, and bk is the threshold
of the k neuron in the output layer. f(x) is the hyperbolic tangent function, and g(x) is
the linear function.

Determine the number of hidden layer neurons

The number of hidden layer neurons is usually determined by the following two for­
mulas:

n ¼ 2m þ 1 (7)

pffiffiffiffiffiffiffiffiffiffiffi
n¼
mþlþa (8)
Pb
1
b i¼1 i
ðc − ^c i Þ2
NRMSE ¼ (9)
cmax
In the above formula, a is an arbitrary natural number between 1 and 10, b is the
number of samples in the training set, ci is i actual value, ^c i is i predicted value, and cmax
is the maximum value in the actual value. By constantly trying to adjust the value of a,
the value range of the number of hidden layer neurons n is determined to be [5,29], and
the normalized root mean square error (NRMSE) of the training set is calculated to evalu­
ate the performance of the model. The number of hidden layer neurons with the smallest
NRMSE is selected as the optimal value.

3. Sample data processing

There are landslides in all 32 slope units in the study area; therefore, to create a sam­
ple dataset, the study examined 32 slope units with landslide points (positive samples)
and 32 slope units without landslides (negative samples). The information value of
 GEOCARTO INTERNATIONAL 11

Figure 4. Flow chart of BPNN based on landslide dynamic hazard assessment.

each sample was then normalized. To create random sequences, the sample dataset is
sorted randomly. The ratio of 70% to 30% is used to randomly select the training set
and testing set. The last 19 sets of data are designated as testing data, whereas the
first 45 sets are designated as training data.

xi − xmin
Xi ¼ (10)
xmax − xmin

In the formula: xmax and xmin are the maximum and minimum values of the amount of
information of each group of samples, Xi is the amount of information of the i samples, and
Xi is the amount of information of the i samples after normalization.

When the model achieves satisfactory results with minimal error, the corresponding
year’s dynamic landslide hazard is predicted, thus obtaining the dynamic hazard zone.
The steps of using the information value and BPNN for landslide dynamic hazard assess­
ment are illustrated in Figure 4.

4. Results
4.1. Division of assessment units and factor classifications
According to the scope of the research area was separated into 200 slope units using a
12.5 m DEM and the extent of the research area, which is founded on the hydrological
12 R. HUANG ET AL.

Figure 5. Division of slope units in research area.

Table 2. Statistical table of slope unit morphological index distribution.

Morphological index Number of slope units Percentage of total slope units (%)
1 -3 196 98
3 -5 2 1
>5 2 1

analysis method and integrated with the field research. 43 landslides in this area are dis­
tributed in 32 slope units (Figure 5). The morphological rationality of slope units in the
study area was tested by the morphological index method (Li et al. 2023):
L2
F¼ (11)
4pS
In the formula: L represents the perimeter of the slope unit (m); s represents the slope
unit area (m2). When the morphological index is 1-3, it shows that the divided slope unit
fits the controlled geomorphological boundaries such as the ridge line and valley line in
the study area, which is consistent with the actual topography. The distribution of slope
unit shape index in the study area is shown in Table 2, of which 98% of the slope unit
shape index is between 1-3, which indicates that the overall shape of the slope unit in the
study area is relatively regular, which can meet the requirements of the next landslide sus­
ceptibility assessment and hazard assessment.
The primary data for assessment and prediction of landslide susceptibility and hazard, the
influencing factor parameters extracted from 200 slope units were taken as the original data.
To identify the 13 influencing factors in the static landslide susceptibility assessment index sys­
tem and the introduced dynamic precipitation influencing factors, the natural break method
was applied. This classification is intended for subsequent assessment and prediction of land­
slide susceptibility and hazard. Figure 6 illustrates the distribution of topography, engineering
geology, hydrology, and human engineering activities factors within the slope units, which are
part of the static influencing factor system for landslides. Figure 7 displays the average annual
precipitation from the 1980s to the 2010s. Figure 8 represents the average annual precipitation
for the years 2025 and 2030, which were predicted using a time series approach.
 GEOCARTO INTERNATIONAL 13

Figure 6. The landslide static influencing factor system: (a) elevation difference, (b) total curvature, (c) slope degree,
(d) slope aspect, (e) slope structure, (f) depth of overburden, (g) distance to fault, (h) distance to road, (i) distance to
river, (j) NDVI, (k) TWI, (l) SPI,(m) lithology, (n) legend of lithology.
14 R. HUANG ET AL.

Figure 7. Average annual precipitation in the 1980s-2010s: (a) PRE-1980s; (b) PRE-1990s; (c) PRE-2000s; (d) PRE-2010s.

Figure 8. Average annual precipitation forecast: (a) PRE-2025; (b) PRE-2030.

4.2. Implementation of the model

To produce two models assessing landslide susceptibility and hazard, the information value
model is based on the static influencing factor system for landslides. The information value
of 13 influencing factors was calculated separately, and the susceptibility zoning map was
generated accordingly. To establish and train the BPNN model, we utilized the information
value of the landslide dynamic influencing factor system. This model is applied to the entire
study area by ArcGIS, producing dynamic hazard zoning maps for historical periods
(1980s-2010s) as well as for future predictions (2025 and 2030).

4.2.1. Landslide susceptibility assessment

The research area includes 43 landslides and 200 slope units, with 32 slope units exhibit­
ing landslide occurrences. The information value of the 13 static influencing factors is cal­
culated using the information value model, as shown in Table 3. In some categories, there
are slope units that have not experienced landslides. To ensure proper computation, the
number of landslide-prone slope units in these categories is assigned a value of 0.01.
Figure 9 illustrates the classification intervals and information quantities for each influ­
encing factor. Taking into account the characteristics and distribution of landslide disas­
ters in the Qingjiang Reservoir, the elevation difference, slope structure, and lithology are
used as examples for explanation.

1. Spatial characteristics of landslide distribution are largely determined by the topog­

raphy. As shown in Figure 9(a), landslides mainly develop in the elevation difference
classification of 0-179m, accounting for 59% of all slope units with landslides. This
 GEOCARTO INTERNATIONAL 15

Table 3. The information on static influencing factor.

Number of
slope units
with
Number of landslides/ Number of
landslides Number of Total slope slope units/
unit by slope units by units with Total slope Information
Factor Class classification classification landslides units value
Elevation 0-179m 19 90 0.59 0.45 0.277
Difference 179-324m 6 41 0.19 0.21 −0.089
324-475m 5 30 0.16 0.15 0.041
475-661m 2 23 0.06 0.12 −0.610
661-1161m 0.01 16 0.0003 0.08 −5.545
Slope Degree 0-16.73� 9 24 0.28 0.12 0.852
16.73-26.71� 17 39 0.53 0.20 1.002
26.71-37.52� 6 45 0.19 0.23 −0.182
37.52-50.34� 0.01 69 0.0003 0.35 −7.007
50.34-79.87� 0.01 23 0.0003 0.12 −5.908
Slope Aspect North 1 23 0.03 0.115 −1.303
North-East 0.01 40 0.0003 0.20 −6.461
East 3 17 0.09 0.085 0.098
South-East 7 26 0.22 0.13 0.520
South 13 28 0.41 0.14 1.065
South-West 3 22 0.09 0.11 −0.160
West 3 18 0.09 0.09 0.041
North-West 2 26 0.06 0.13 −0.732
Curvature concave 2 6 0.06 0.03 0.734
convex 30 194 0.94 0.97 −0.034
Slope Reverse slope 3 46 0.09 0.23 −0.897
Structure Transverse slope 6 59 0.19 0.30 −0.453
Skew slope 11 57 0.34 0.29 0.187
Dip slope 12 38 0.38 0.19 0.680
Distance to 0-500m 1 16 0.03 0.08 −0.940
fault 500-1000m 3 21 0.09 0.11 −0.113
1000-1500m 3 12 0.09 0.06 0.446
1500-2000m 4 26 0.13 0.13 −0.039
>2000m 21 125 0.66 0.63 0.049
Lithology A 8 18 0.25 0.09 1.022
B 2 9 0.06 0.05 0.329
C 0.01 15 0.0003 0.08 −5.481
D 9 73 0.28 0.37 −0.261
E 0.01 1 0.0003 0.01 −2.773
F 13 84 0.41 0.42 −0.033
TWI 0.83-4.04 1 54 0.03 0.27 −2.156
4.04-5.27 23 128 0.72 0.64 0.116
5.27-6.7 8 18 0.25 0.09 1.022
SPI −4.38-2.06 0.01 1 0.0003 0.01 −2.773
2.06-3.43 18 36 0.56 0.18 1.139
3.43-4.7 14 138 0.44 0.69 −0.456
4.7-6.41 0.01 25 0.0003 0.13 −5.991
NDVI −0.002-0.015 8 18 0.25 0.09 1.022
0.015-0.022 9 48 0.28 0.24 0.159
0.022-0.028 7 66 0.22 0.33 −0.411
0.028-0.034 4 37 0.13 0.19 −0.392
0.034-0.05 4 31 0.13 0.16 −0.215
Distance to 0-200m 4 37 0.13 0.19 −0.392
river 200-400m 6 64 0.19 0.32 −0.535
400-800m 12 78 0.38 0.39 −0.039
800-1000m 5 10 0.16 0.05 1.139
>1000m 5 11 0.16 0.06 1.044
Distance to 0-50m 2 4 0.06 0.02 1.139
road 50-100m 17 39 0.53 0.20 1.002
(continued)
16 R. HUANG ET AL.

Table 3. Continued.
Number of
slope units
with
Number of landslides/ Number of
landslides Number of Total slope slope units/
unit by slope units by units with Total slope Information
Factor Class classification classification landslides units value
100-150m 8 31 0.25 0.16 0.478
150-200m 2 13 0.06 0.07 −0.039
>200m 3 113 0.09 0.57 −1.796
Depth of 5.1-6.91m 7 25 0.22 0.13 0.560
overburden 6.91-8.04m 8 68 0.25 0.34 −0.307
8.04-9.46m 5 26 0.16 0.13 0.184
9.46-10.78m 7 62 0.22 0.31 −0.349
10.78-15.74m 5 19 0.16 0.10 0.498

classification provides an information value of 0.277, indicating that landslides are

primarily distributed in low-lying areas along the Qingjiang River.
2. Slope structure is an important indicator reflecting the slope topography and overall
stability control. As depicted in Figure 9(e), slope units with landslides are predomin­
antly distributed in skew slope and dip slope. Among them, dip slopes have the high­
est occurrence, accounting for 38% of slope units in this classification, providing an
information value of 0.68.
3. Lithology serves as the material basis for geological hazards. The higher the mechan­
ical strength and integrity of the lithology, the lower the potential for geological dis­
aster occurrence, and vice versa. As indicated in Figure 9(g), landslides are mainly
spread in lithologies such as limestone, dolomitic limestone interbedded with shale
and siltstone rock formation, which collectively account for 93% of all slope units
with landslides. This indicates that landslide disasters occur in both clastic and car­
bonate rocks, typically in weaker lithologies.

The comprehensive information value of the research area was analyzed. ArcGIS soft­
ware was utilized to overlay and analyze the factors, and the results were assigned to slope
units for landslide susceptibility assessment in Qingjiang Reservoir. The natural break
method was used to classify the results of susceptibility assessment results in four grades:
low, moderate, high, and very high. Figure 10 shows the overall characteristics of landslide
susceptibility at different levels. The comparison between the susceptibility zones and
actual disaster distributions in Table 4 indicates a high correlation. No landslides were
detected in slope units classified as low or moderate-low susceptibility zones. As the sus­
ceptibility level increases, the number of actual landslide disasters increases, with 52% of
slope units belonging to very high and high susceptibility zones. While the western and
central areas in the study region have fewer documented landslides, the model evaluated
them as very high susceptibility areas, indicating a high potential for landslide develop­
ment in these regions.

4.2.2. Landslide dynamic hazard prediction

According to different years, six dynamic hazard assessment models of the landslide were
established respectively. The input layer is the amount of information value of each slope
unit in the assessment system of dynamic influencing factors. The output layer is output
‘1’ when there is a landslide disaster, and output ‘0’ when there is no landslide disaster.
Figure 11 is the structure of the BPNN model used in this paper.
 GEOCARTO INTERNATIONAL 17

Figure 9. The classification information value of each influencing factor and the scale ratio of slope units with land-
slides: (a) elevation difference, (b) slope degree, (c) slope aspect, (d) total curvature, (e) slope structure, (f) distance to
fault, (g) lithology, (h) TWI, (i) SPI, (j) NDVI, (k) distance to river, (l) distance to road, (m) depth of overburden.

1. Dynamic hazard prediction of historical landslides

The information value of precipitation factors for each decade was calculated and four
BPNN models were established accordingly (Table 5). The sample dataset consisted of
64 slope units. The positive and negative samples, as well as the output layer results,
varied depending on the occurred of landslides in each decade. Using the natural
break method, the results of the hazard assessment were grouped in four levels: low,
moderate, high, and very high (Figure 12). The distribution of landslide hazard areas
18 R. HUANG ET AL.

Figure 10. Result of landslide susceptibility on the basis of information value model.

Table 4. Landslide susceptibility zoning result.

Percentage of total Percentage of total
Susceptibility zoning Number of slope units slope units (%) Number of landslides landslides (%)
Low 24 12 0 0
Moderate 72 36 0 0
High 50 25 5 11.63
Very High 54 27 38 88.37

Figure 11. Structure of the BPNN model for landslide dynamic hazard prediction.

varied significantly across different years, reflecting the influence of annual precipita­
tion changes.
Figure 13 shows the relation observed between number of slope units and average pre­
cipitation under different levels of hazards. In the 1980s, the majority of slope units were
assigned to very high and high hazards, while in the 2010s, the largest number of slope
units were assigned to low and moderate hazard classes. In the 1980s, with 14 landslides
and an average precipitation of 1882.85 mm. The lowest number of slope units fell into
the low and moderate hazard classes, while the highest number belonged to the very high
 GEOCARTO INTERNATIONAL 19

Table 5. The information of precipitation.

Number of slope
units with Number of slope Number of slope
landslides by units with units by
Factor Class classification landslides classification Information value
1843-1863mm 2 13 45 −0.380
1864-1880mm 5 13 62 0.216
PRE-1980s 1881-1894mm 0.01 13 37 −5.483
1895-1912mm 5 13 39 0.679
1913-1938mm 1 13 17 −0.099
1011-1046mm 2 12 34 −0.019
1047-1078mm 5 12 57 0.380
PRE-1990s 1079-1106mm 4 12 46 0.371
1107-1134mm 1 12 38 −0.824
1135-1178mm 0.01 12 25 −5.011
1000-1043mm 1 8 33 −0.278
1044-1070mm 4 8 41 0.892
PRE-2000s 1071-1093mm 2 8 43 0.151
1094-1117mm 1 8 46 −0.610
1118-1157mm 0.01 8 37 −4.997
1000-1039mm 3 8 33 0.821
1040-1065mm 1 8 43 −0.542
PRE-2010s 1066-1088mm 3 8 55 0.310
1089-1115mm 1 8 49 −0.673
1116-1161mm 0.01 8 20 −4.382
1388-1399mm 0.01 32 1 −2.773
1399-1403mm 6 32 46 −0.204
PRE-2025 1403-1406mm 11 32 83 −0.188
1406-1409mm 10 32 54 0.146
1409-1418mm 5 32 16 0.669
1399-1402mm 3 32 36 −0.652
1402-1404mm 3 32 42 −0.806
PRE-2030 1404-1406mm 6 32 36 0.041
1406-1408mm 11 32 54 0.241
1408-1412mm 9 32 32 0.564

Figure 12. Landslides hazard for different ages: (a) 1980s; (b) 1990s; (c) 2000s; (d) 2010s.

and high hazard classes, with a total of 132 units. During the 1990s, there were 12 land­
slides with an average precipitation of 1086.905 mm, of which 106 slope units belonged to
very high and high hazard classes. During the 2000s, 8 landslides occurred with an aver­
age precipitation of 1084.155 mm and 88 slope units were in the high and very high haz­
ards. In the dataset for the 2010s, there were 9 landslides, with 78 slope units classified as
low and moderate hazards, and 122 slope units classified as very high and high hazards.
20 R. HUANG ET AL.

Figure 13. Slope unit numbers for different hazard areas in each model and the average annual precipitation in each
decade.

Figure 14. Landslide hazard prediction for different years: (a)2025; (b)2030.

Table 6. Landslide hazard zoning result in 2025 and 2030.

Percentage of total Percentage of total
Number of slope slope units in Number of slope slope units in
Hazard zoning units in 2025 2025 (%) units in 2030 2030 (%)
Low 52 26 32 16
Moderate 47 23.5 53 26.5
High 77 38.5 65 32.5
Very High 24 12 50 25

As average annual precipitation decreases, number of slope units that are segmented as
very high and high hazard levels also decreases.

2. Dynamic hazard prediction of landslide in the future

Based on the predicted precipitation data layer, the information value of precipitation
factors for 2025 and 2030 was calculated (Table 5). Due to the inability to determine
the number of landslides in future years, all 32 slope units with historical landslides
have been treated as positive samples, and all 32 slope units without historical landslides
have been treated as negative samples during hazard prediction. Two BPNN models
were established, and the natural break method was used to classify hazard levels in
four classes: low, moderate, high, and very high (Figure 14 and Table 6). Predictions
 GEOCARTO INTERNATIONAL 21

indicate that in 2025 and 2030, the proportion of high and very high areas will be
50.5% and 57.5%, respectively. The studied area’s share of very high and high hazard
zones for landslides exhibits a shifting tendency with variations in precipitation, suggest­
ing that future landslide occurrences in Qingjiang Reservoir may be more likely. As pre­
cipitation increases, there will also be a progressive increase in the occurrence
probability of landslides.

4.3 Validation of the model

4.3.1. ROC validation
To further validate the reliability of landslide susceptibility and hazard assessment results,
the model was evaluated using ROC. Area under curve (AUC) is an objective quantitative
measure used to assess the modeling accuracy (Arabameri et al. 2017). The diagonal line
of ROC, also known as baseline, has an AUC of 0.5 to 1, the more its value converges to
1, the better the model’s predictive accuracy. The 86 non-landslide disaster points selected
randomly in this research to match the number of existing landslide disaster points were
used as testing datasets for ROC analysis (Figure 15). Landslide susceptibility assessment
with an AUC value of 0.783, while the AUC values for historical dynamic hazard assess­
ment were 0.713, 0.835, 0.783, and 0.905, with the BPNN model for the 2010s showing
the best predictive accuracy. The model results demonstrated that the landslide hazard
assessment models for different periods fell into the satisfactory classification and showed
good consistency with the actual occurrence of disasters. In the paper, these accuracy
indicators show that the BPNN model applied is reliable and could provide dynamic pre­
diction of landslide hazard in the next 5-10 years.

4.3.2. Field investigation and validation

Landslide susceptibility zoning results area are displayed in Figure 10: very high suscepti­
bility areas are more densely distributed on the north bank of the Qingjiang River, while
they are more sparsely distributed on the south bank. This distribution is closely related
to factors such as geological environmental conditions, slope structure, and human

Figure 15. ROC curve for models.

22 R. HUANG ET AL.

Figure 16. The fieldwork process. (a): very high susceptible areas; (b), (d), (f) and (g): some typical weak rock mass;
(c): slope-cutting behind the house; (e): slope-cutting to build the road; and (h): cracks behind the house.

engineering activities. Through field investigations, as shown in Figure 16, it was found
that the lithological characteristics of the very high susceptibility area are primarily com­
posed of nodular limestone, limestone interbedded with weak thin-layered carbonaceous
mudstone, dolomitic limestone interbedded with shale, and siltstone, which are weak rock
formations. These formations are mainly distributed in the downstream structural slope
areas on both sides of the Qingjiang River. Moreover, slope cutting for housing construc­
tion, road construction and other activities in the area of study have also created a signifi­
cant number of slopes with exposed faces.
Furthermore, Figure 17(a) shows some historically identified regions with very high
landslide hazards predicted by the BPNN model. Figure 17(b)–(i) displays eight typical
water-related landslides of the research area, and under the combination of precipitation
and frontal erosion by the Qingjiang River, the high-hazard zones will likely remain dan­
gerous in the future.

5. Discussion
Assessment of landslide hazard is an effective method to address the threat caused by geo­
logical hazards. This method can predict the areas where landslide disasters are likely to
occur based on historical data, topography, and triggering factors. It enables the rapid
and accurate determination of the approximate location of potential landslides, providing
essential information for the prevention and management of potential landslides. Various
methods have been used to model the susceptibility and hazard assessment of landslides,
among which the information value model and the BPNN model have been widely
applied in the field of geological disaster assessment. In this research, the information
 GEOCARTO INTERNATIONAL 23

Figure 17. Combined landslides dynamic hazard prediction and field survey map, (a): predicted very high hazard
areas, (b)-(i): pictures of typical landslides.
value model was used for static landslide susceptibility assessment, and the MATLAB
software was used to write the code to construct the BPNN model and combined with
the information value model for predicting the occurrence of landslides in the precipita­
tion susceptible areas of the Qingjiang Reservoir. Finally, the reliability of susceptibility
mapping and historical hazard mapping was validated using the ROC and field survey
validation.
This work aims to create some optimizations in comparison with earlier research to
increase the rigor of the research process and the reliability of the research findings.

1. Mapping units
Slope units created from high-resolution spatial data were used as mapping units in
the study area. Topographic and geomorphologic features are significant in the for­
mation and occurrence of landslides (Liu et al. 2022; Sun et al. 2020). Traditional
mapping units, such as grid cells, are the most commonly used landslide disaster
units due to their characteristics like constant shape, ease of computation and sam­
pling. Nevertheless, the method is independent of topographic and geomorphologic
features and may contain multiple different geological structures. The slope unit is
better able to reflect the ground morphology characteristics in the terrain spatial unit
division compared with the grid unit, because the slope unit, whose principle is based
on the ridge line and valley line to divide, is the unit of geohazard occurrence.
Compared with other mapping units, it can better represent the topographic and geo­
morphic features in a small area (Ba et al. 2018). The study area is a middle-low
mountainous landform, and the mainstream of Qingjiang River passes through its
territory, forming a unique gully geomorphologic area, with steep mountains on both
sides of the river valley and slopes that are mostly steep-slope terrain. GIS-based
slope units are able to do more accurate mapping of landslide hazards utilizing
24 R. HUANG ET AL.

landslide survey data and high-resolution spatial data (Zhao et al. 2021). Therefore,
the slope units used in this study reflect the relationship between the assessment units
and the unique valley topography and geomorphology of the study area.
2. Modeling methods
Modeling methods for landslide hazard assessment can be summarized as heuristic,
mathematical statistical and machine learning models The traditional heuristic model
assigns the weight of landslide influencing factors subjectively, resulting in relatively
low accuracy in landslide hazard prediction, while the accuracy of mathematical stat­
istical model in landslide hazard prediction is higher than that of the heuristic model
(Aditian et al. 2018; Chen et al. 2018). The information value model is a commonly
used mathematical statistical model. Based on the information entropy theory, it can
calculate the weight of various geological disaster factors and reflect their contribu­
tion to the occurrence of landslide disasters (Figure 9). Farooq and Akram (Farooq
and Akram 2021) used the information value to predict the susceptibility of land­
slides in mountainous areas, and the established model has high accuracy. Niu estab­
lished a new method for landslide prediction in soil-rock contact zones based on
information value model (Niu et al. 2024), which can better solve the relationship
between landslide risk and various factors. The machine learning model can better
solve the complex relationship between landslide hazard and various influencing fac­
tors. BPNN has the ability to learn and identify the complex nonlinear relationship
between data and can learn the rules and characteristics of landslide evolution from a
large amount of data. Xu (Xu et al. 2015) applied the BPNN model to the prediction
of landslide susceptibility in the Three Gorges Reservoir of China, and the prediction
accuracy reached 88%. Huang et al. (2020) applied heuristic, mathematical statistics
and machine learning models to landslide susceptibility prediction respectively. The
results show that the machine learning model represented by BPNN model is super­
ior to the traditional heuristic model and mathematical statistics model in prediction
accuracy and has better prediction performance.
In this paper, the combination of information value model and BPNN model is
applied to the prediction of landslide dynamic hazard. The verification results of the
model show that the combination of these two methods has high prediction accuracy
in landslide hazard prediction. The combination of information value model and
BPNN model can make more comprehensive use of data information, and improve
the accuracy and reliability of landslide hazard prediction (Chen et al. 2020; L.
Huang et al. 2021).
3. Dynamic precipitation
In previous studies, the triggering factors for landslide occurrences were often based
on precipitation return periods (Jim�enez-Per�alvarez et al. 2017; Li et al. 2019;
Tsunetaka 2021), and landslide hazard zonation was obtained by predicting the land­
slide instability probability under different return periods of extreme precipitation,
which cannot provide hazard zonation for non-extreme precipitation conditions in
the future. Due to the variable climatic conditions, this type of research is unable to
obtain the hazard zoning under normal precipitation in the future. In contrast with
previous research, this study established the dynamic influencing factors system by
combining average annual precipitation and static influencing factors. Based on his­
torical average annual precipitation predicted future actual average annual precipita­
tion and conducted dynamic hazard prediction for landslides in the next 5-10 years,
a reliable landslide hazard zoning map is made. The research results indicate that
landslide disasters in the Qingjiang Reservoir are influenced by changes in
 GEOCARTO INTERNATIONAL 25

precipitation intensity, and the spatial distribution of hazards for each year shows
obvious differences, reflecting the dynamic changing process year by year. The paper’s
research approach can generate the trend of spatial location change of landslide haz­
ard in the future and assist governments in formulating long-term risk management
strategies.
4. Sample dataset
In the process of landslide hazard prediction, different numbers of landslide sample
datasets were used according to different years. There are 43 landslides spread over
32 slope units in this study area. As shown in Figure 5, a slope unit may incorporate
a variety of landslides because these landslides have the same formation mechanism
and occur in the same slope unit. In the dynamic hazard prediction, a fixed number
of positive and negative samples were selected by choosing 32 slope units with land­
slides and 32 slope units without landslides. Different numbers of positive and nega­
tive samples were used depending on the number of landslides that occurred each
year. Therefore, each time the BPNN was used for prediction, the output data in the
training and testing states were different. The advantage of doing this is that com­
pared to the use of fixed landslide catalogs in previous studies, the hazard zonation
maps in this study clearly show the changes in landslide hazard with precipitation,
reflecting the dynamic changing process of landslide disasters for each year. We
employed field investigations, remote sensing images, and geological surveys to guar­
antee the accuracy and consistency of the 43 sets of data samples related to land­
slides. The performance of the BPNN model in this study indicates that it can learn
from limited data and offer good predictions, even though the number of samples of
43 landslides in a small area may be regarded as less than certain studies in a big
area (Achour et al. 2021; Qasimi et al. 2023). The spatial distribution of landslides is
faithfully represented by the model. The efficacy of the BPNN model in predicting
landslide hazard, even in a small area with few landslide occurrences, is demonstrated
by the results of ROC validation and field investigation cross-validation in our study.

The research method of this paper is devoted to predicting the hazard of landslides
through precipitation, to achieve environmental safety and sustainable regional develop­
ment. The suitable models in various study regions differ because of variances in landslide
number, geographic location, and climate conditions. We are also aware of the research
methods’ limitations, such as the model’s applicability, the kind of landslide, and the dur­
ation of the precipitation data. For the purpose of further enhancing the accuracy of land­
slide dynamic hazard assessment and prediction, future research will be conducted in the
following directions: gather more precipitation data over various time spans in areas with
the same geological background conditions; explore novel approaches and techniques; and
integrate various mathematical statistical models and machine learning models. The
framework for risk management and early warning for landslide disasters incorporates the
landslide dynamic hazard assessment model.

6. Conclusion
In this study, we constructed a reliable landslide dynamic hazard prediction model in a
landslide-prone area by combining information model with BPNN model. The theoretical
significance of this study is to calculate information value of the relationship between
influencing factors and the occurrence of landslides, and to establish a dynamic hazard
assessment index system based on the average annual precipitation. Then, develop a
26 R. HUANG ET AL.

landslide dynamic hazard prediction model based on MATLAB and BPNN. The research
method provides new ideas and methods for the establishment of geological disaster haz­
ard prediction based on mathematical statistical models and machine learning models,
and further enriches the theoretical system of geological disaster hazard assessment.
The practical significance is that the dynamic hazard prediction of mountain landslide
disasters is made, and the landslide hazard zoning results in the next 5-10 years are
obtained. The results show that the accurate prediction of the very high hazard area can
be realized according to the precipitation factors that trigger the occurrence of mountain
landslides, which provides a focused and targeted scientific prevention and control area
for disaster prevention and mitigation. On the one hand, it can effectively reduce the
potential threat of landslides to people’s personal safety and property safety. On the other
hand, it can also provide a reference for the dynamic hazard prediction of landslides in
mountainous areas, so as to determine the hazard range of regional landslides and provide
scientific basis for understanding global landslide disasters.

Acknowledgements
We the authors thank the editors and anonymous reviewers for their comments and suggestions, which
are of great help to the writing of this article.

Disclosure statement
No potential conflict of interest was reported by the author(s).

Data availability statement

The 12.5 m spatial resolution DEM used in this study was downloaded from https://search.asf.alaska.edu/#/;
Rainfall precipitation is downloaded from https://www.resdc.cn/DOI/.

References
Achour Y, Saidani Z, Touati R, Pham QB, Pal SC, Mustafa F, Sanli FB. 2021. Assessing landslide suscepti­
bility using a machine learning-based approach to achieving land degradation neutrality. Environ Earth
Sci. 80(17):575–594. doi:10.1007/s12665-021-09889-9.
Aditian A, Kubota T, Shinohara Y. 2018. Comparison of GIS-based landslide susceptibility models using
frequency ratio, logistic regression, and artificial neural network in a tertiary region of Ambon,
Indonesia. Geomorphology. 318:101–111. doi:10.1016/j.geomorph.2018.06.006.
Afungang RN, De Meneses Bateira CV, Nkwemoh CA. 2017. Assessing the spatial probability of land­
slides using GIS and informative value model in the Bamenda highlands. Arab J Geosci. 10(17):384–
398. doi:10.1007/s12517-017-3155-1.
Arabameri A, Pourghasemi HR, Yamani M. 2017. Applying different scenarios for landslide spatial
modeling using computational intelligence methods. Environ Earth Sci. 76(24):832–851. doi:10.1007/
s12665-017-7177-5.
Arabameri A, Pradhan B, Rezaei K, Sohrabi M, Kalantari Z. 2019. GIS-based landslide susceptibility map­
ping using numerical risk factor bivariate model and its ensemble with linear multivariate regression
and boosted regression tree algorithms. J Mt Sci. 16(3):595–618. doi:10.1007/s11629-018-5168-y.
Ba Q, Chen Y, Deng S, Yang J, Li H. 2018. A comparison of slope units and grid cells as mapping
units for landslide susceptibility assessment. Earth Sci Inform. 11(3):373–388. doi:10.1007/s12145-018-
0335-9.
Baeza C, Corominas J. 2001. Assessment of shallow landslide susceptibility by means of multivariate stat­
istical techniques. Earth Surf Processes Landf. 26(12):1251–1263. doi:10.1002/esp.263.
 GEOCARTO INTERNATIONAL 27

Basharat MU, Khan JA, Abdo HG, Almohamad, H. 2023. An integrated approach based landslide suscep­
tibility mapping: case of Muzaffarabad region, Pakistan. Geomatics Nat Hazards Risk. 14(1): 2210255.
doi:10.1080/19475705.2023.2210255.
Carrara A, Cardinali M, Guzzetti F. 1995. GIS technology in mapping landslide hazard. Geogr Inf Syst
Assess Nat Hazards. 5:135–175. doi:10.1007/978-94-015-8404-3_8.
Chang Z, Catani F, Huang F, Liu G, Meena SR, Huang J, Zhou C. 2023. Landslide susceptibility predic­
tion using slope unit-based machine learning models considering the heterogeneity of conditioning fac­
tors. J Rock Mech Geotech Eng. 15(5):1127–1143. doi:10.1016/j.jrmge.2022.07.009.
Chawla A, Pasupuleti S, Chawla S, Rao ACS, Sarkar K, Dwivedi R. 2019. Landslide susceptibility zonation
mapping: a case study from Darjeeling District, Eastern Himalayas, India. J Indian Soc Remote Sens.
47(3):497–511.), doi:10.1007/s12524-018-0916-6.
Chen F, Cai C, Li X, Sun T, Qian Q. 2020. Evaluation of landslide susceptibility based on information
volume and neural network model. Chin J Rock Mech Eng. 39(S1):2859–2870. doi:10.13722/j.cnki.jrme.
2019.1094.
Chen W, Peng J, Hong H, Shahabi H, Pradhan B, Liu J, Zhu A, Pei X, Duan Z. 2018. Landslide suscepti­
bility modelling using GIS-based machine learning techniques for Chongren County, Jiangxi Province,
China. Sci Total Environ. 626:1121–1135. doi:10.1016/j.scitotenv.2018.01.124.
Das J, Saha P, Mitra R, Alam A, Kamruzzaman M. 2023. GIS-based data-driven bivariate statistical mod­
els for landslide susceptibility prediction in Upper Tista Basin, India. Heliyon. 9(5):e16186. doi:10.
1016/j.heliyon.2023.e16186.
Farooq S, Akram MS. 2021. Landslide susceptibility mapping using information value method in Jhelum
Valley of the Himalayas. Arab J Geosci. 14(10):824–839. doi:10.1007/s12517-021-07147-7.
Fell R, Corominas J, Bonnard C, Cascini L, Leroi E, Savage WZ. 2008. Guidelines for landslide suscepti­
bility, hazard and risk zoning for land use planning. Eng Geol. 102(3–4):85–98. doi:10.1016/j.enggeo.
2008.03.022.
Froude MJ, Petley DN. 2018. Global fatal landslide occurrence from 2004 to 2016. Nat Hazards Earth Syst
Sci. 18(8):2161–2181. doi:10.5194/nhess-18-2161-2018.
Gokceoglu MEC. 2002. Assessment of landslide susceptibility for a landslide-prone area (north of Yenice,
NW Turkey) by fuzzy approach. Environ Geol. 41(6):720–730. doi:10.1007/s00254-001-0454-2.
Griffiths JS, Mather AE, Hart AB. 2002. Landslide susceptibility in the R�ıo Aguas catchment, SE Spain.
QJEGH. 35(1):9–17. doi:10.1144/qjegh.35.1.9.
Guzzetti F, Carrara A, Cardinali M, Reichenbach P. 1999. Landslide hazard evaluation: a review of current
techniques and their application in a multi-scale study, Central Italy. Geomorphology. 31(1-4):181–216.
doi:10.1016/S0169-555X(99)00078-1.
Guzzetti F, Reichenbach P, Cardinali M, Galli M, Ardizzone F. 2005. Probabilistic landslide hazard assess­
ment at the basin scale. Geomorphology. 72(1-4):272–299. doi:10.1016/j.geomorph.2005.06.002.
Hader PRP, Reis FAGV, Peixoto ASP. 2022. Landslide risk assessment considering socionatural factors:
methodology and application to Cubat~ao municipality, S~ao Paulo, Brazil. Nat Hazards. 110(2):1273–
1304. doi:10.1007/s11069-021-04991-4.
Huang F, Cao Z, Guo J, Jiang S, Li S, Guo Z. 2020. Comparisons of heuristic, general statistical and
machine learning models for landslide susceptibility prediction and mapping. Catena. 191:104580. doi:
10.1016/j.catena.2020.104580.
Huang F, Cao Z, Jiang S, Zhou C, Huang J, Guo Z. 2020. Landslide susceptibility prediction based on a
semi-supervised multiple-layer perceptron model. Landslides. 17(12):2919–2930. doi:10.1007/s10346-
020-01473-9.
Huang F, Chen J, Liu W, Huang J, Hong H, Chen W. 2022. Regional rainfall-induced landslide hazard
warning based on landslide susceptibility mapping and a critical rainfall threshold. Geomorphology.
408:108236. doi:10.1016/j.geomorph.2022.108236.
Huang L, Hao J, Li W, Zhou Z, Jia P. 2021. Landslide susceptibility assessment by the coupling method
of RBF neural network and information value: a case study in Min Xian, Gansu Province. Chin J Geol
Hazard Control. 32(6):116–126. doi:10.16031/j.cnki.issn.1003-8035.2021.06-14.
Huang F, Pan L, Yao C, Zhou C, Jiang Q, Chang Z. 2021. Landslide susceptibility prediction modelling
based on semi-supervised machine learning. J. Zhejiang Univ. (Eng. Sci.). 55(9):1705–1713. doi:10.
3785/j.issn.1008-973X.2021.09.012.
Huang Y, Zhao L. 2018. Review on landslide susceptibility mapping using support vector machines.
Catena. 165:520–529. doi:10.1016/j.catena.2018.03.003.
Ji J, Zhou Y, Cheng Q, Jiang S, Liu S. 2023. Landslide susceptibility mapping based on deep learning algo­
rithms using information value analysis optimization. Land. 12(6):1125. doi:10.3390/land12061125.
28 R. HUANG ET AL.

Jim�enez-Per�alvarez JD, El Hamdouni R, Palenzuela JA, Irigaray C, Chac� on J. 2017. Landslide-hazard map­
ping through multi-technique activity assessment: an example from the Betic Cordillera (southern
Spain). Landslides. 14(6):1975–1991. doi:10.1007/s10346-017-0851-6.
Jun Z, Kunlong Y, Jiajia W, Lei L, Faming H. 2016. Evaluation of landslide susceptibility for Wanzhou
district of Three Gorges Reservoir [Evaluation of landslide susceptibility for Wanzhou district of Three
Gorges Reservoir]. Chinese Journal of Rock Mechanics and Engineering. 35(2):284–296. doi:10.13722/j.
cnki.jrme.2015.0318.
Kai W, Shaojie Z, Fangqiang W. 2020. Slope unit extraction methods: advances and prospects. J Yangtze
River Sci Res Inst. 37(6):85–93. doi:10.11988/ckyyb.20190210.
Karakas G, Kocaman S, Gokceoglu C. 2023. A hybrid multi-hazard susceptibility assessment model for a
basin in Elazig Province, T€ urkiye. Int J Disaster Risk Sci. 14(2):326–341. doi:10.1007/s13753-023-
00477-y.
Kawagoe S, Kazama S, Sarukkalige PR. 2010. Probabilistic modelling of rainfall induced landslide hazard
assessment. Hydrol Earth Syst Sci. 14(6):1047–1061. doi:10.5194/hess-14-1047-2010.
Khan H, Shafique M, Khan MA, Bacha MA, Shah SU, Calligaris C. 2019. Landslide susceptibility assess­
ment using frequency ratio, a case study of northern Pakistan. Egypt J Remote Sens Space Sci. 22(1):
11–24. doi:10.1016/j.ejrs.2018.03.004.
Kim J, Lee S, Jung H, Lee S. 2018. Landslide susceptibility mapping using random forest and boosted tree
models in Pyeong-Chang, Korea. Geocarto Int. 33(9):1000–1015. doi:10.1080/10106049.2017.1323964.
Lee S, Hong S, Jung H. 2017. A support vector machine for landslide susceptibility mapping in Gangwon
Province, Korea. Sustainability. 9(1):48. doi:10.3390/su9010048.
Lee S, Lee M, Jung H. 2017. Data mining approaches for landslide susceptibility mapping in Umyeonsan,
Seoul, South Korea. Appl Sci-Basel. 7(7):683. doi:10.3390/app7070683.
Li Y, Liu X, Han Z, Dou J. 2020. Spatial proximity-based geographically weighted regression model for
landslide susceptibility assessment: A case study of Qingchuan Area, China. Appl Sci. 10(3):1107. doi:
10.3390/app10031107.
Li D, Miao F, Xie Y, Leo C. 2019. Hazard prediction for Baishuihe landslide in the three Gorges reservoir
during the extreme rainfall return period. KSCE J Civ Eng. 23(12):5021–5031. doi:10.1007/s12205-019-
1025-y.
Lin J, Chen W, Qi X, Hou H. 2021. Risk assessment and its influencing factors analysis of geological haz­
ards in typical mountain environment. J Cleaner Prod. 309:127077. doi:10.1016/j.jclepro.2021.127077.
Liu JL, Chen X, Zhang TJ. 2011. Application of time series-exponential smoothing model on urban water
demand forecasting. AMR. 183–185:1158–1162. doi:10.4028/www.scientific.net/AMR.183-185.1158.
Liu Z, Sun L, Zhang Y, Yu Z. 2022. Landslide risk evaluation based on slope unit:a case on the Western
Hubei area, China. Arab J Geosci. 15(11):1072–1084. doi:10.1007/s12517-022-10319-8.
Li X, Yang S, Li Y, Yin K, Wang W. 2023. Improved slope unit method for fine evaluation of regional
landslide susceptibility. Bull Geol Sci Technol. 42(03):81–92. doi:10.19509/j.cnki.dzkq.tb20210707.
Mehrabi M. 2022. Landslide susceptibility zonation using statistical and machine learning approaches in
Northern Lecco, Italy. Nat Hazards. 111(1):901–937. doi:10.1007/s11069-021-05083-z.
Niu HT. 2020. Smart safety early warning model of landslide geological hazard based on BP neural net­
work. Saf Sci. 123:104572. doi:10.1016/j.ssci.2019.104572.
Niu H, Shao S, Gao J, Jing H. 2024. Research on GIS-based information value model for landslide geo­
logical hazards prediction in soil-rock contact zone in southern Shaanxi. Phys Chem Earth. 133:
103515. doi:10.1016/j.pce.2023.103515.
Pan W, Fu L, Xiao H, Yu X, Li X, Zhang X, Zhao T. 2021. Risk assessment for landslide of FAST
site based on GIS and fuzzy hierarchical method. Environ Earth Sci. 80(8):320–334. doi:10.1007/
s12665-021-09571-0.
Pardeshi SD, Autade SE, Pardeshi SS. 2013. Landslide hazard assessment: recent trends and techniques.
Springerplus. 2(1):11. doi:10.1186/2193-1801-2-523.
Peruccacci S, Gariano SL, Melillo M, Solimano M, Guzzetti F, Brunetti MT. 2023. The ITAlian rainfall-
induced LandslIdes CAtalogue, an extensive and accurate spatio-temporal catalogue of rainfall-induced
landslides in Italy. Earth Syst Sci Data. 15(7):2863–2877. doi:10.5194/essd-15-2863-2023.
Petley D. 2012. Global patterns of loss of life from landslides. Geology. 40(10):927–930. doi:10.1130/
G33217.1.
Pham BT, Nguyen MD, Bui KT, Prakash I, Chapi K, Bui DT. 2019. A novel artificial intelligence
approach based on multi-layer perceptron neural network and biogeography-based optimization for
predicting coefficient of consolidation of soil. Catena. 173:302–311. doi:10.1016/j.catena.2018.10.004.
 GEOCARTO INTERNATIONAL 29

Qasimi AB, Isazade V, Enayat E, Nadry Z, Majidi AH. 2023. Landslide susceptibility mapping in
Badakhshan province, Afghanistan: a comparative study of machine learning algorithms. Geocarto
International. 38(1):2248082. doi:10.1080/10106049.2023.2248082.
Reichenbach P, Rossi M, Malamud BD, Mihir M, Guzzetti F. 2018. A review of statistically-based land­
slide susceptibility models. Earth Sci Rev. 180:60–91. doi:10.1016/j.earscirev.2018.03.001.
Rumelhart DE, Hinton GE, Williams RJ. 1986. Learning representations by back-propagating error.
Nature. 323(6088):533–536. doi:10.1038/323533a0.
Shahzad N, Ding X, Abbas S. 2022. A comparative assessment of machine learning models for landslide
susceptibility mapping in the rugged terrain of Northern Pakistan. Appl Sci -Basel. 12(5):2280. doi:10.
3390/app12052280.
Sheng J, Yu P, Zhang H, Wang Z. 2021. Spatial variability of soil Cd content based on IDW and RBF in
Fujiang River, Mianyang, China. J Soils Sediments. 21(1):419–429. doi:10.1007/s11368-020-02758-1.
Singh K, Kumar V. 2018. Hazard assessment of landslide disaster using information value method and
analytical hierarchy process in highly tectonic Chamba region in bosom of Himalaya. J Mt Sci. 15(4):
808–824. doi:10.1007/s11629-017-4634-2.
Skrzypczak I, Kokoszka W, Zientek D, Tang Y, Kogut J. 2021. Landslide hazard assessment map as an
element supporting spatial planning: the Flysch Carpathians region study. Remote Sens. 13(2):317. doi:
10.3390/rs13020317.
Sui H, Su T, Hu R, Wang D, Zheng Z. 2022. Study on the risk assessment method of rainfall landslide.
Water. 14(22):3678. doi:10.3390/w14223678.
Sun X, Chen J, Han X, Bao Y, Zhan J, Peng W. 2020. Application of a GIS-based slope unit method for
landslide susceptibility mapping along the rapidly uplifting section of the upper Jinsha River, South-
Western China. Bull Eng Geol Environ. 79(1):533–549. doi:10.1007/s10064-019-01572-5.
Sun D, Gu Q, Wen H, Xu J, Zhang Y, Shi S, Xue M, Zhou X. 2023. Assessment of landslide susceptibility
along mountain highways based on different machine learning algorithms and mapping units by
hybrid factors screening and sample optimization. Gondwana Res. 123:89–106. doi:10.1016/j.gr.2022.07.
013.
Tan Q, Bai M, Zhou P, Hu J, Qin X. 2021. Geological hazard risk assessment of line landslide based on
remotely sensed data and GIS. Measurement. 169:108370. doi:10.1016/j.measurement.2020.108370.
Tang Y, Yin K, Liu L, Zhang L, Fu X. 2017. Dynamic assessment of rainfall-induced shallow landslide
hazard. J Mt Sci. 14(7):1292–1302. doi:10.1007/s11629-016-4353-0.
Tsunetaka H. 2021. Comparison of the return period for landslide-triggering rainfall events in Japan based
on standardization of the rainfall period. Earth Surf Processes Landf. 46(14):2984–2998. doi:10.1002/
esp.5228.
Tyagi A, Kamal Tiwari R, James N. 2022. A review on spatial, temporal and magnitude prediction of
landslide hazard. J Asian Earth Sci: x. 7:100099. doi:10.1016/j.jaesx.2022.100099.
Versain LD, Banshtu RS, Pandey DD. 2019. Comparative evaluation of GIS based landslide hazard
zonation maps using different approaches. J Geol Soc India. 93(6):684–692. doi:10.1007/s12594-019-
1247-0.
Wang T, Dahal A, Fang Z, van Westen C, Yin K, Lombardo L. 2024. From spatio-temporal landslide sus­
ceptibility to landslide risk forecast. Geosci Front. 15(2):101765. doi:10.1016/j.gsf.2023.101765.
Wang H, Ji F, Zhan X, Tan C, Feng C. 2022. Sensitivity evaluation of landslide geological hazards based
on multi-source remote sensing data. Optik (Stuttgart):170481. doi:10.1016/j.ijleo.2022.170481.
Wang M, Liu M, Yang S, Shi P. 2014. Incorporating triggering and environmental factors in the analysis
of earthquake-induced landslide hazards. Int J Disaster Risk Sci. 5(2):125–135. doi:10.1007/s13753-014-
0020-7.
Wang F, Xu P, Wang C, Wang N, Jiang N. 2017. Application of a GIS-based slope unit method for land­
slide susceptibility mapping along the Longzi River, Southeastern Tibetan Plateau, China. IJGI. 6(6):
172. doi:10.3390/ijgi6060172.
Wubalem A. 2020. Modeling of landslide susceptibility in a part of Abay Basin, northwestern Ethiopia.
Open Geosciences. 12(1):1440–1467. doi:10.1515/geo-2020-0206.
Wubalem A, Meten M. 2020. Landslide susceptibility mapping using information value and logistic
regression models in Goncha Siso Eneses area, northwestern Ethiopia. SN Appl Sci. 2(5):807. doi:10.
1007/s42452-020-2563-0.
Xu X. 2017. The spatial interpolation data set of the annual state of meteorological elements in China:
resource and Environment Science and Data Registration and publishing system.
Xu K, Guo Q, Li Z, Xiao J, Qin Y, Chen D, Kong C. 2015. Landslide susceptibility evaluation based on
BPNN and GIS: a case of Guojiaba in the Three Gorges Reservoir Area. Int J Geogr Inf Sci. 29(7):
1111–1124. doi:10.1080/13658816.2014.992436.
30 R. HUANG ET AL.

Xu R, Li X, Hu K, Nie Y. 2019. A dynamic hazard assessment for mountain hazards in Hengduan moun­
tain area. J Catastrophol. 34(03):196–201. doi:10.3969/j.issn.1000-811X.2019.03.036.
Yan G, Cheng H, Jiang Z, Teng L, Tang M, Shi T, Jiang Y, Yang G, Zhou Q. 2022. Recognition of Fluvial
Bank erosion along the main stream of the Yangtze River. Engineering. 19:50–61. doi:10.1016/j.eng.
2021.03.027.
Yang S. 2017. Assessment of rainfall-induced landslide susceptibility using GIS-based slope unit approach.
J Perform Constr Facil. 31(4):04017026. doi:10.1061/(ASCE)CF.1943-5509.0000997.
Yang H, Dong J, Guo X. 2023. Geohazards and risk assessment along highway in Sichuan Province,
China. J Mt Sci. 20(6):1695–1711. doi:10.1007/s11629-022-7500-9.
Yu C, Chen J. 2020. Application of a GIS-based slope unit method for landslide susceptibility mapping in
Helong City: comparative assessment of ICM, AHP, and RF model. Symmetry-Cult Sci. 12(11):1848.
doi:10.3390/sym12111848.
Yu W, Li X, Yao J, Zheng L. 2022. Dynamic evaluation of the risk of landslide disasters in the
China⁃Pakistan economic corridor under the background of climate change. Cience Technol Eng.
22(35):15518–15527.
Zangmene FL, Ngapna MN, Ateba MCB, Mboudou GMM, Defo PLW, Kouo RT, Dongmo AK, Owona S.
2023. Landslide susceptibility zonation using the analytical hierarchy process (AHP) in the Bafoussam-
Dschang region (West Cameroon). Adv Space Res. 71(12):5282–5301. doi:10.1016/j.asr.2023.02.014.
Zeng T, Gong Q, Wu L, Zhu Y, Yin K, Dario P. 2023. Double-index rainfall warning and probabilistic
physically based model for fast-moving landslide hazard analysis in subtropical-typhoon area.
Landslides. doi:10.1007/s10346-023-02187-4.
Zhang S, Li C, Peng J, Zhou Y, Wang S, Chen Y, Tang Y. 2023. Fatal landslides in China from 1940 to
2020: occurrences and vulnerabilities. Landslides. 20(6):1243–1264. doi:10.1007/s10346-023-02034-6.
Zhang Y, Tang J, Liao R, Zhang M, Zhang Y, Wang X, Su Z. 2021. Application of an enhanced BP neural
network model with water cycle algorithm on landslide prediction. Stoch Environ Res Risk Assess.
35(6):1273–1291. doi:10.1007/s00477-020-01920-y.
Zhao Z, Liu ZY, Xu C. 2021. Slope unit-based landslide susceptibility mapping using certainty factor, sup­
port vector machine, random forest, CF-SVM and CF-RF models. Front Earth Sci. 9:589630. doi:10.
3389/feart.2021.589630.
Zhao J, Zhang Q, Wang D, Wu W, Yuan R. 2022. Machine learning-based evaluation of susceptibility to
geological hazards in the Hengduan Mountains Region, China. Int J Disaster Risk Sci. 13(2):305–316.
doi:10.1007/s13753-022-00401-w.
Zou F, Che E, Long M. 2023. Quantitative assessment of geological hazard risk with different hazard
indexes in mountainous areas. J Cleaner Prod. 413:137467. doi:10.1016/j.jclepro.2023.137467.