0% found this document useful (0 votes)
34 views

Deep Learning and Machine Learning in Hydrological

Uploaded by

aghajanlookm2
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
34 views

Deep Learning and Machine Learning in Hydrological

Uploaded by

aghajanlookm2
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.

v1

Deep learning and machine learning in hy-


drological processes climate change and earth
systems a systematic review

Sina Ardabili1, Amir Mosavi2,3*, Majid Dehghani4, Annamaria R. Varkonyi-Koczy2,5

1
Institute of Advanced Studies Koszeg, Koszeg, Hungary
2
Kalman Kando Faculty of Electrical Engineering, Obuda University, Budapest, Hungary
3
School of the Built Environment, Oxford Brookes University, Oxford OX3 0BP, UK
4
Technical and Engineering Department, Faculty of Civil Engineering, Vali-e-Asr Univer-
sity of Rafsanjan, Rafsanjan, Iran
5
Department of Mathematics and Informatics, J. Selye University, Komarno, Slovakia
*
[email protected]

Abstract. Artificial intelligence methods and application have re-


cently shown great contribution in modeling and prediction of the
hydrological processes, climate change, and earth systems. Among
them, deep learning and machine learning methods mainly have re-
ported being essential for achieving higher accuracy, robustness, ef-
ficiency, computation cost, and overall model performance. This
paper presents the state of the art of machine learning and deep
learning methods and applications in this realm and the current
state, and future trends are discussed. The survey of the advances in
machine learning and deep learning are presented through a novel
classification of methods. The paper concludes that deep learning is
still in the first stages of development, and the research is still pro-
gressing. On the other hand, machine learning methods are already
established in the fields, and novel methods with higher perfor-
mance are emerging through ensemble techniques and hybridiza-
tion.

© 2019 by the author(s). Distributed under a Creative Commons CC BY license.


Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

Keywords: Machine learning, deep learning, big data, hydrology,


climate change, global warming, hydrological model, earth sys-
tems

Nomenclatures

Artificial neural network ANN Random forest RF

Extreme learning machine ELM Deep feedforward neural net- DFNN


work

Machine learning ML Recurrent neural network RNN

Support vector machine SVM Partial least squares PLS

Wavelet neural networks WNN Discriminant analysis DA

Deep learning DL Principal component analysis PCA

Autoregressive integrated ARIMA Linear discriminant analysis LDA


moving average

Feed-forward neural net- FFNN Support vector regression SVR


works

Multi layered perceptron MLP Least-squares LS

Decision tree DT Sparse Bayesian SB

Response surface methodol- RSM Standard precipitation evapo- SPEI


ogy transpiration index

Back propagation neural net- BPNN Genetic programming GP


work

Gradient boosting decision GBDT Multi linear regression MLR


tree
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

Adaptive neuro fuzzy infer- ANFIS Moderate Resolution Imaging MODIS


ence system Spectroradiometer

Central processing unit CPU Reduced order model ROM

Fire-fly algorithm FA wise step fire-fly algorithm WSSFA

Deep neural network DNN Deep belief networks DBN

1 Introduction

Studying the hydrological processes, climate change and earth systems are of
utmost importance to expand knowledge and insight into the universe [1]. Thus,
advancing the accurate models of the earth’s various phenomena and systems
have been the center of attention [2]. Physical models have a long tradition in
simulation, understanding, and prediction of the hydrological processes, climate
change, and earth systems [3-7]. Physical models are used worldwide as the
trustworthy systems to study the environmental phenomena, climate behavior,
atmospheric and hydrological systems, and further study of the natural hazards,
extreme events, and ecosystems [8-11]. Statistical models, including the time
series analysis form another major popular group of modeling techniques widely
used by scientists for studying the earth systems and deliver insight on climate
change and hydrological related events [12-18].

Various drawbacks are associated with physical and statistical models [19-21].
Among them, the accuracy, weakness in uncertainty analysis, high computation
cost, and the need for a comprehensive amount of data, have been highlighted in
the literature [22, 23]. Machine learning and deep learning methods have seen to
tackle these shortcomings very well through their efficient computation and
intelligence [24-29]. Only during the past few years, these methods have become
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

very popular among the research communities [30-46]. Figure.1 represents the
rapid progress of machine learning and deep learning in hydrological processes,
climate change, and earth systems research and their subfields. The progressing
domination of these intelligent methods is apparent. Thus, studying the novel
methods and identifying the trend in using and advancement of these methods
would be essential.

Fig. 1. The rapid growth of using machine learning and deep learning for
modeling and prediction of the hydrological processes, climate change and
earth systems (source: web of science)

Literature includes a number of review papers on machine learning and


deep learning methods [30-46]. There exists a number of papers where the
applications domains of the ML methods have been evaluated [47-62]. How-
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

ever, there is a gap in investigating the algorithmic advancements and appli-


cation domains considering the hydrological processes, climate change, and
earth systems. Consequently, the contribution of this paper is set to present
the state of the art of machine learning and deep learning methods used for
modeling the above-mentioned systems and identify the application areas.

2 Machine learning methods

In this section, the machine learning methods have been classified into the
following popular subsections, i.e., tree-based, support vector-based, neural net-
work-based, and hybrids and ensembles. Further, there are investigated accord-
ing to their popularity and applications domains. The summary of the methods
are provided in the tables bellow and methods are reviewed according to their
efficiency and accuracy

Table 1. Top studies developed by ML methods in hydrology

References Contribution Method Research domain

To estimate the hydrologic RF -Machine learning


disturbance index for
streams by the use of Ran- -Watershed man-
[63] dom forest agement

SVM,
To develop different ma- ELM, -Machine learning
chine learning methods for RF,
[64]
the estimation of daily ref- M5Tree, -Reference evapo-
erence evapotranspiration and transpiration
GBDT
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

To develop ML methods RF,


for the prediction of the ANN, -Machine learning
[65] wheat production yield in and SVM
the presence of satellite -Hydrological data
and climate data

To develop ML methods RF and -Machine learning


for the estimation of the ANN
[66]
atmospheric daily pollen -Daily pollen con-
concentration centration

To develop ML methods MLP, -Machine learning


for the prediction of water SVR,
[67]
flow forecasting as a hy- RBF, and -Hydrologic pa-
drological parameter ANFIS rameter

To develop an innovative
-Machine learning
ML method for the predic-
ELM-
[68] tion of daily solar radia-
MODIS -Daily solar radia-
tion (monthly average val-
tion
ues)

Fox and Magoulick [63] developed a study to estimate the hydrologic disturb-
ance index for streams by the use of Random forest in the presence of fish
community and hydrologic data and landscape metrics for gaged streams as the
training dataset. RF has been introduced as one of the effective methods for this
task. RF also has been proposed in a study by Fan et al. [64], who developed
SVM and ELM methods in comparison with different tree-based ensemble
methods for the estimation of daily reference evapotranspiration in the presence
of meteorological data. Tree-based ensemble methods included RF, M5tree,
gradient boosting decision tree, and extreme gradient boosting. Evaluations have
been performed using determination coefficient, root means a square error and
means absolute error. Based on comparisons, RF could provide a higher accuracy
compared with that of other methods.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

In another study, Cai et al. [65] developed different ML methods for the
prediction of wheat production yield by integrating hydrological data, including
satellite and climate data. This study also could successfully present a
comparison of the performance of methods using the determination coefficient.
Methods included the least absolute shrinkage and selection operator, RF, ANN,
and SVM. In all datasets, the highest determination coefficient value was owned
by SVM followed by RF. Zewdie et al. [66] developed ML methods including
RF and ANN for the prediction of atmospheric daily pollen concentration for the
comparison with next-generation weather radar. Comparisons have been
performed using correlation coefficient values. Based on results, RF and ANN
could provide similar performance in the prediction of target values with a high
correlation coefficient value.

Kovačević et al. [67] developed a study for the prediction of water flow using
MLP, SVR, RBF, and ANFIS methodologies. Evaluation of results and
comparison of the performance of methods have been performed using the
employment of root mean square error, mean absolute error, and determination
coefficient. The best method was ANFIS, followed by SVR with a linear kernel.
Ghimire et al. [68] developed a novel ML method entitled the integrated ELM-
MODIS. The proposed method has been compared with basic ELM, GP, ANN-
GA, ANN-PSO, GA-SVR, and online sequential ELM methods in terms of
determination coefficient, root mean square error and mean absolute error. Based
on the results, the proposed method could significantly increase the estimation
performance followed by hybrid GA-SVR and hybrid ANN-GA methods. The
overall detailed results in terms of accuracy, reliability, and sustainability have
been presented in table 2 for further considerations and applications.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

Table 2. the comparison results of ML-based methods in hydrology

Method Application Accu- Reliability Sustainabil- Reference


racy ity

RF Estimation ++ ++ ++ [63]

RF Estimation +++ ++ ++ [64]

M5Tree Estimation ++ + + [64]

ELM Estimation + + + [64]

SVM Estimation +++ +++ ++ [65]

RF Estimation ++ ++ + [65]

NN Estimation ++ + + [65]

RF Estimation ++ ++ + [66]

ANN Estimation ++ ++ + [66]

ANFIS Estimation +++ ++ ++ [67]


Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

SVR-
Linear Estimation ++ ++ ++ [67]
kernel

RBF Estimation ++ ++ + [67]

MLP Estimation ++ + + [67]

ELM-
Estimation +++ +++ +++ [68]
MODIS

GA-SVR Estimation ++ ++ ++ [68]

ANN-GA Estimation ++ ++ + [68]

3 Deep learning methods

Deep learning techniques are considered as a significant part of ML methods


based on ANN. DL techniques have been widely applied in analyzing,
estimating, designing, filtering, processing, recognition, and detection tasks. The
most popular DL methods are DNN, DBN, RNN, and CNN techniques.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

10

Table 3. Top studies developed by DL techniques in hydrology

Method Research do-


References Contribution main

To develop a DL method for -Deep learning


LSTM-
[69] the prediction and estimation
ROM
of flood -Flood prediction

-Deep learning
To develop a DL technique
[70] for making a model for moni- DFNN
-Drought predic-
toring drought accurately.
tion

To develop DL technique for -CNN


the analysis of atmospheric
[71] CNN
imaging of Cherenkov Tele- -Atmospheric im-

scopes aging

-Deep learning
To develop a DL technique
[72] for the estimation of tropical CNN
-Tropical cy-
cyclones and their precursors
clones

-Deep learning
To develop an innovative DL
[73] method for the prediction of DL-FA
-Hydrological
hydrological processes.
processes
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

11

Hu et al. [69] developed a novel LSTM integrated by ROM method as an


innovative DL method for the prediction of time-series flooding. This integrated
method could successfully cop with the prediction of Spatio-temporal
distribution of floods because it can use the advantage of both ROM and LSTM
methods. The evaluation of results has been performed using root mean square
error in the presence of different predicted periods. The validation data was
included in the Okushiri tsunami test datasets. This method presented a high
accuracy as well as reducing the cost of CPU. This can increase the sustainability
of the proposed method significantly.

Shen et al. [70] developed DL technique architecture entitled deep feed-


forward neural network for the prediction of SPEI as one of the main factors of
drought in the presence of multi-source remote sensing data. The proposed
method provided a good correlation with meteorological and agricultural
droughts. Evaluating data included SPEI in Henan Province, China, which
indicated a high-performance value.

Shilon et al. [71] developed a convolutional neural network method for the
analysis of aerial imaging of Cherenkov Telescopes. This imaging system has a
significant role in finding very high energy γ-ray emitters. The training phase
was performed using datasets generated from Monte-Carlo simulated events and
testing phase was performed on both measured and simulations data. CNN could
successfully cope with the task with high accuracy. CNN also has been employed
by Matsuoka et al. [72] who developed a CNN technique for the estimation of
tropical cyclones. The training process was performed in the presence of
longwave radiation outgoing during twenty-year simulation which has been
calculated by employing a cloud-resolving global atmospheric simulation. The
evaluation has been performed using the probability of detection factor.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

12

Xu et al. [73] integrated deep learning and fire-fly algorithm for training the
SVR method with optimized parameters. Also, the performance of the developed
methods has been compared with other methods in term of determination
coefficient. Based on results, the highest correlation coefficient was owned by
wise step fire-fly based SVR algorithm followed by DLFA based SVR algorithm
in training step, but in testing step the accuracy of DLFA based SVR method has
been significantly reduced. This reduction caused the lowest sustainability index
for this method.

Table 4. the comparison results of DL based methods

Method Application Accuracy Reliabil- Sustaina- Reference


ity bility

LSTM-
Estimation +++ +++ +++ [69]
ROM

DFNN Estimation +++ +++ ++ [70]

CNN Detection +++ +++ +++ [71]

CNN Estimation +++ +++ +++ [72]

WSSFA-
Estimation +++ +++ +++ [73]
SVR
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

13

DLFA-
Estimation ++ + + [73]
SVR

FA-SVR Estimation ++ ++ ++ [73]

4 Conclusions

The survey of the advances in machine learning and deep learning are pre-
sented through a novel classification of methods. The paper concludes that deep
learning is still in the first stages of development, and the research is still pro-
gressing. On the other hand, the machine learning methods are already estab-
lished in the fields, and novel methods with higher performance are emerging
through ensemble techniques and hybridization. Similar trends have also been
reported in the other application domains [74-83].

Acknowledgments

This publication has been supported by the Project: "Support of research and
development activities of the J. Selye University in the field of Digital Slovakia
and creative industry" of the Research & Innovation Operational Programme
(ITMS code: NFP313010T504) co-funded by the European Regional Develop-
ment Fund.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

14

References

1. Taylor, R.G., et al., Ground water and climate change. Nature climate
change, 2013. 3(4): p. 322.

2. Wang, C., et al., Most of the Northern Hemisphere Permafrost Remains


under Climate Change. Scientific reports, 2019. 9(1): p. 3295.

3. Baynes, E.R.C., et al., Beyond equilibrium: Re-evaluating physical


modelling of fluvial systems to represent climate changes. Earth-Science
Reviews, 2018. 181: p. 82-97.

4. Bouhal, T., et al., Technical feasibility of a sustainable Concentrated


Solar Power in Morocco through an energy analysis. Renewable and
Sustainable Energy Reviews, 2018. 81: p. 1087-1095.

5. Carrassi, A., et al., Data assimilation in the geosciences: An overview of


methods, issues, and perspectives. Wiley Interdisciplinary Reviews:
Climate Change, 2018. 9(5).

6. He, C., et al., Review and comparison of empirical thermospheric mass


density models. Progress in Aerospace Sciences, 2018. 103: p. 31-51.

7. Hill, J., H. Buddenbaum, and P.A. Townsend, Imaging Spectroscopy of


Forest Ecosystems: Perspectives for the Use of Space-borne
Hyperspectral Earth Observation Systems. Surveys in Geophysics,
2019. 40(3): p. 553-588.

8. Qin, W., et al., Comparison of deterministic and data-driven models for


solar radiation estimation in China. Renewable and Sustainable Energy
Reviews, 2018. 81: p. 579-594.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

15

9. Raseman, W.J., et al., Emerging investigators series: A critical review


of decision support systems for water treatment: Making the case for
incorporating climate change and climate extremes. Environmental
Science: Water Research and Technology, 2017. 3(1): p. 18-36.

10. Schenato, L., A review of distributed fibre optic sensors for geo-
hydrological applications. Applied Sciences (Switzerland), 2017. 7(9).

11. Seixas, M., et al., Active bending and tensile pantographic bamboo
hybrid amphitheater structure. Journal of the International Association
for Shell and Spatial Structures, 2017. 58(3): p. 239-252.

12. Aslam, R.A., S. Shrestha, and V.P. Pandey, Groundwater vulnerability


to climate change: A review of the assessment methodology. Science of
the Total Environment, 2018. 612: p. 853-875.

13. Devi, R.M., et al., Understanding the linkages between climate change
and forest. Current Science, 2018. 114(5): p. 987-996.

14. Estévez, J., et al., Introduction to the special issue on “hydro-


meteorological time series analysis and their relation to climate
change”. Acta Geophysica, 2018. 66(3): p. 317-318.

15. Flowers, G.E., Hydrology and the future of the Greenland Ice Sheet.
Nature Communications, 2018. 9(1).

16. Mudelsee, M., Trend analysis of climate time series: A review of


methods. Earth-Science Reviews, 2019. 190: p. 310-322.

17. Murray, N.J., et al., The role of satellite remote sensing in structured
ecosystem risk assessments. Science of the Total Environment, 2018.
619-620: p. 249-257.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

16

18. Rhein, M., Taking a close look at ocean circulation: Ocean circulation
patterns in the North Atlantic provide a benchmark for climate models.
Science, 2019. 363(6426): p. 456-457.

19. Newton, R.J. and J.S. McClary, The flux and impact of wastewater
infrastructure microorganisms on human and ecosystem health. Current
Opinion in Biotechnology, 2019. 57: p. 145-150.

20. Royapoor, M., A. Antony, and T. Roskilly, A review of building climate


and plant controls, and a survey of industry perspectives. Energy and
Buildings, 2018. 158: p. 453-465.

21. Sun, Z., et al., Evaluating and comparing remote sensing terrestrial GPP
models for their response to climate variability and CO 2 trends. Science
of the Total Environment, 2019. 668: p. 696-713.

22. Akpoti, K., A.T. Kabo-bah, and S.J. Zwart, Agricultural land suitability
analysis: State-of-the-art and outlooks for integration of climate change
analysis. Agricultural Systems, 2019. 173: p. 172-208.

23. Lyubchich, V., et al., Insurance risk assessment in the face of climate
change: Integrating data science and statistics. Wiley Interdisciplinary
Reviews: Computational Statistics, 2019. 11(4).

24. Akhter, M.N., et al., Review on forecasting of photovoltaic power


generation based on machine learning and metaheuristic techniques.
IET Renewable Power Generation, 2019. 13(7): p. 1009-1023.

25. Al Tarhuni, B., et al., Large scale residential energy efficiency


prioritization enabled by machine learning. Energy Efficiency, 2019.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

17

26. Mosavi, A., P. Ozturk, and K.W. Chau, Flood prediction using machine
learning models: Literature review. Water (Switzerland), 2018. 10(11).

27. Ponsero, A.J. and B.L. Hurwitz, The promises and pitfalls of machine
learning for detecting viruses in aquatic metagenomes. Frontiers in
Microbiology, 2019. 10(MAR).

28. Shen, C., A Transdisciplinary Review of Deep Learning Research and


Its Relevance for Water Resources Scientists. Water Resources
Research, 2018. 54(11): p. 8558-8593.

29. Zhu, X.X., et al., Deep Learning in Remote Sensing: A Comprehensive


Review and List of Resources. IEEE Geoscience and Remote Sensing
Magazine, 2017. 5(4): p. 8-36.

30. Aram, F., et al., Design and validation of a computational program for
analysing mental maps: Aram mental map analyzer. Sustainability
(Switzerland), 2019. 11(14).

31. Asadi, E., et al., Groundwater Quality Assessment for Drinking and
Agricultural Purposes in Tabriz Aquifer, Iran. 2019.

32. Asghar, M. Z.; Subhan, F.; Imran, M.; Kundi, F.M.; Shamshirband, S.;
Mosavi, A.; Csiba, P.; R. Várkonyi-Kóczy, A. Performance Evaluation
of Supervised Machine Learning Techniques for Efficient Detection of
Emotions from Online Content. Pre-prints 2019, 2019080019 (doi:
10.20944/preprints201908.0019.v1).

33. Bemani, A.; Baghban, A.; Shamshirband, S.; Mosavi, A.; Csiba, P.;
Várkonyi-Kóczy, A.R. Applying ANN, ANFIS, and LSSVM Models for
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

18

Estimation of Acid Sol-vent Solubility in Supercritical CO2. Preprints


2019, 2019060055 (doi: 10.20944/preprints201906.0055.v2).

34. Choubin, B., et al., Snow avalanche hazard prediction using machine
learning methods. Journal of Hydrology, 2019. 577.

35. Choubin, B., et al., An ensemble prediction of flood susceptibility using


multivariate discriminant analysis, classification and regression trees,
and support vector machines. Science of the Total Environment, 2019.
651: p. 2087-2096.

36. Dehghani, M., et al., Prediction of hydropower generation using Grey


wolf optimization adaptive neuro-fuzzy inference system. Energies,
2019. 12(2).

37. Dineva, A., et al., Review of soft computing models in design and control
of rotating electrical machines. Energies, 2019. 12(6).

38. Dineva, A., et al., Multi-Label Classification for Fault Diagnosis of


Rotating Electrical Machines. 2019.

39. Farzaneh-Gord, M., et al., Numerical simulation of pressure pulsation


effects of a snubber in a CNG station for increasing measurement
accuracy. Engineering Applications of Computational Fluid Mechanics,
2019. 13(1): p. 642-663.

40. Ghalandari, M., et al., Investigation of submerged structures’ flexibility


on sloshing frequency using a boundary element method and finite
element analysis. Engineering Applications of Computational Fluid
Mechanics, 2019. 13(1): p. 519-528.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

19

41. Ghalandari, M., et al., Flutter speed estimation using presented


differential quadrature method formulation. Engineering Applications
of Computational Fluid Mechanics, 2019. 13(1): p. 804-810.

42. Karballaeezadeh, N., et al., Prediction of remaining service life of


pavement using an optimized support vector machine (case study of
Semnan–Firuzkuh road). Engineering Applications of Computational
Fluid Mechanics, 2019. 13(1): p. 188-198.

43. Menad, N.A., et al., Modeling temperature dependency of oil - water


relative permeability in thermal enhanced oil recovery processes using
group method of data handling and gene expression programming.
Engineering Applications of Computational Fluid Mechanics, 2019.
13(1): p. 724-743.

44. Mohammadzadeh, S., et al., Prediction of Compression Index of Fine-


Grained Soils Using a Gene Expression Programming Model.
Infrastructures, 2019. 4(2): p. 26.

45. Mosavi, A. and M. Edalatifar, A Hybrid Neuro-Fuzzy Algorithm for


Prediction of Reference Evapotranspiration, in Lecture Notes in
Networks and Systems. 2019, Springer. p. 235-243.

46. Mosavi, A., A. Lopez, and A.R. Varkonyi-Koczy, Industrial


applications of big data: State of the art survey, D. Luca, L. Sirghi, and
C. Costin, Editors. 2018, Springer Verlag. p. 225-232.

47. Mosavi, A. and T. Rabczuk, Learning and intelligent optimization for


material design innovation, D.E. Kvasov, et al., Editors. 2017, Springer
Verlag. p. 358-363.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

20

48. Mosavi, A., T. Rabczuk, and A.R. Varkonyi-Koczy, Reviewing the novel
machine learning tools for materials design, D. Luca, L. Sirghi, and C.
Costin, Editors. 2018, Springer Verlag. p. 50-58.

49. Mosavi, A., et al., State of the art of machine learning models in energy
systems, a systematic review. Energies, 2019. 12(7).

50. Mosavi, A., et al., Prediction of multi-inputs bubble column reactor


using a novel hybrid model of computational fluid dynamics and
machine learning. Engineering Applications of Computational Fluid
Mechanics, 2019. 13(1): p. 482-492.

51. Mosavi, A. and A.R. Varkonyi-Koczy, Integration of machine learning


and optimization for robot learning, R. Jablonski and R. Szewczyk,
Editors. 2017, Springer Verlag. p. 349-355.

52. Nosratabadi, S., et al., Sustainable business models: A review.


Sustainability (Switzerland), 2019. 11(6).

53. Qasem, S.N., et al., Estimating daily dew point temperature using
machine learning algorithms. Water (Switzerland), 2019. 11(3).

54. Rezakazemi, M., A. Mosavi, and S. Shirazian, ANFIS pattern for


molecular membranes separation optimization. Journal of Molecular
Liquids, 2019. 274: p. 470-476.

55. Riahi-Madvar, H., et al., Comparative analysis of soft computing


techniques RBF, MLP, and ANFIS with MLR and MNLR for predicting
grade-control scour hole geometry. Engineering Applications of
Computational Fluid Mechanics, 2019. 13(1): p. 529-550.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

21

56. Shabani, S.; Samadianfard, S.; Taghi Sattari, M.; Shamshirband, S.;
Mosavi, A.; Kmet, T.; R. Várkonyi-Kóczy, A. Modeling Daily Pan
Evaporation in Humid Cli-mates Using Gaussian Process Regression.
Preprints 2019, 2019070351 (doi: 10.20944/preprints201907.0351.v1).

57. Shamshirband, S.; Hadipoor, M.; Baghban, A.; Mosavi, A.; Bukor J.;
Annamaria R. Varkonyi-Koczy, Developing an ANFIS-PSO Model to
predict mercury emissions in Combustion Flue Gases. Preprints 2019,
2019070165 (doi: 10.20944/preprints201907.0165.v1).

58. Shamshirband, S., et al., Ensemble models with uncertainty analysis for
multi-day ahead forecasting of chlorophyll a concentration in coastal
waters. Engineering Applications of Computational Fluid Mechanics,
2019. 13(1): p. 91-101.

59. Shamshirband, S., A. Mosavi, and T. Rabczuk, Particle swarm


optimization model to predict scour depth around bridge pier. arXiv
preprint arXiv:1906.08863, 2019.

60. Taherei Ghazvinei, P., et al., Sugarcane growth prediction based on


meteorological parameters using extreme learning machine and
artificial neural network. Engineering Applications of Computational
Fluid Mechanics, 2018. 12(1): p. 738-749.

61. Torabi, M., et al., A Hybrid clustering and classification technique for
forecasting short-term energy consumption. Environmental Progress
and Sustainable Energy, 2019. 38(1): p. 66-76.

62. Torabi, M., et al., A Hybrid Machine Learning Approach for Daily
Prediction of Solar Radiation, in Lecture Notes in Networks and
Systems. 2019, Springer. p. 266-274.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

22

63. Fox, J.T. and D.D. Magoulick, Predicting hydrologic disturbance of


streams using species occurrence data. Science of the Total
Environment, 2019. 686: p. 254-263.

64. Fan, J., et al., Evaluation of SVM, ELM and four tree-based ensemble
models for predicting daily reference evapotranspiration using limited
meteorological data in different climates of China. Agricultural and
Forest Meteorology, 2018. 263: p. 225-241.

65. Cai, Y., et al., Integrating satellite and climate data to predict wheat
yield in Australia using machine learning approaches. Agricultural and
Forest Meteorology, 2019. 274: p. 144-159.

66. Zewdie, G.K., et al., Estimating the daily pollen concentration in the
atmosphere using machine learning and NEXRAD weather radar data.
Environmental Monitoring and Assessment, 2019. 191(7).

67. Kovačević, M., et al., Application of artificial neural networks for


hydrological modelling in karst. Gradjevinar, 2018. 70(1): p. 1-10.

68. Ghimire, S., et al., Self-adaptive differential evolutionary extreme


learning machines for long-term solar radiation prediction with
remotely-sensed MODIS satellite and Reanalysis atmospheric products
in solar-rich cities. Remote Sensing of Environment, 2018. 212: p. 176-
198.

69. Hu, R., et al., Rapid spatio-temporal flood prediction and uncertainty
quantification using a deep learning method. Journal of Hydrology,
2019. 575: p. 911-920.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

23

70. Shen, R., et al., Construction of a drought monitoring model using deep
learning based on multi-source remote sensing data. International
Journal of Applied Earth Observation and Geoinformation, 2019. 79: p.
48-57.

71. Shilon, I., et al., Application of deep learning methods to analysis of


imaging atmospheric Cherenkov telescopes data. Astroparticle Physics,
2019. 105: p. 44-53.

72. Matsuoka, D., et al., Deep learning approach for detecting tropical
cyclones and their precursors in the simulation by a cloud-resolving
global nonhydrostatic atmospheric model. Progress in Earth and
Planetary Science, 2018. 5(1).

73. Xu, L., et al., Simulation and prediction of hydrological processes based
on firefly algorithm with deep learning and support vector for
regression. International Journal of Parallel, Emergent and Distributed
Systems, 2019.

74. Ardabili, S., Mosavi, A., Mahmoudi, Mesri Gundoshmian, T,


Nosratabadi, S., Var-konyi-Koczy, A., Modelling temperature variation
of mushroom growing hall us-ing artificial neural networks, Preprints
2019.

75. Mesri Gundoshmian, T., Ardabili, S., Mosavi, A., Varkonyi-Koczy, A.,
Prediction of combine harvester performance using hybrid machine
learning modeling and re-sponse surface methodology, Preprints 2019.

76. Ardabili, S., Mosavi, A., Varkonyi-Koczy, A., Systematic review of


deep learning and machine learning models in biofuels research,
Preprints 2019.
Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 15 August 2019 doi:10.20944/preprints201908.0166.v1

24

77. Ardabili, S., Mosavi, A., Varkonyi-Koczy, A., Advances in machine


learning model-ing reviewing hybrid and ensemble methods, Preprints
2019.

78. Ardabili, S., Mosavi, A., Varkonyi-Koczy, A., Building Energy


information: demand and consumption prediction with Machine
Learning models for sustainable and smart cities, Preprints 2019.

79. Ardabili, S., Mosavi, A., Dehghani, M., Varkonyi-Koczy, A., Deep
learning and machine learning in hydrological processes climate change
and earth systems a systematic review, Preprints 2019.

80. Mohammadzadeh D., Karballaeezadeh, N., Mohemmi, M., Mosavi, A.,


Varkonyi-Koczy A., Urban Train Soil-Structure Interaction Modeling
and Analysis, Preprints 2019.

81. Mosavi, A., Ardabili, S., Varkonyi-Koczy, A., List of deep learning
models, Preprints 2019.

82. Nosratabadi, S., Mosavi, A., Keivani, R., Ardabili, S., Aram, F., State of
the art sur-vey of deep learning and machine learning models for smart
cities and urban sustainability, Preprints 2019.

83. Perez, H.; H.M. Tah, J.; Mosavi, A.. Deep Learning for Detecting
Building Defects Using Convolutional Neural Networks. Preprints 2019,
2019080068 (doi: 10.20944/preprints201908.0068.v1).

You might also like