Published by : International Journal of Engineering Research & Technology (IJERT)

http://www.ijert.org ISSN: 2278-0181

Vol. 9 Issue 09, September-2020

An IoT and AI based Flood Monitoring and

Rescue System

Mr. Ajim I. Pathan Ms. Aishwarya P. Kulkarni

Department of Computer Science and Engineering Department of Computer Science and Engineering
Walchand College of Engineering, Sangli Walchand College of Engineering, Sangli
Sangli,India Sangli,India

Ms. Nikita L. Gaikwad Ms. Prajakta M. Powar

Department of Computer Science and Engineering Department of Computer Science and Engineering
Walchand College of Engineering, Sangli Walchand College of Engineering, Sangli
Sangli,India Sangli,India

Prof. Anil R. Surve

Department of Computer Science and Engineering
Walchand College of Engineering, Sangli
Sangli,India

Abstract—One of the biggest natural disasters India had ever the western Maharashtra faced severe problems specifically in
faced was floods in Western Maharashtra in August 2005 and Sangli, Kolhapur and Satara districts and impacted livelihood
August 2019. The primary objective of this research is to provide of people, housing and farmlands. Kolhapur and Sangli had
an innovative and sustainable solution required to monitor flood received heavy incessant rainfall and had broken the record of
situations and perform rescue operations in the worst affected many previous years. Many of them evacuated to safer places
Sangli, Kolhapur and Satara districts. This attempt aims at but because of lack of management, precautions and
providing IoT-based flood detection and AI-based rescue technological advancement, flooding caused loss of human life,
operation through the system. This research makes use of livestock, destruction of plants, property and deterioration of
Internet of Things and Artificial Intelligence technologies to
health conditions owing to waterborne diseases. Recently in
provide a reliable and implementable solution for the above
problem. This innovative approach uses Arduino Uno
2019 there was heavy rainfall more than 2005, breaking the
microcontroller for flood detection based on rise of water level, one-month record in just 9-10 days and the water level was
humidity, atmospheric pressure and temperature measured above the danger line of Panchganga and Krishna river. The
through BMP180 sensor. Raspberry Pi has been used for heavy incessant rainfalls in Radhanagari, Kalammawadi dam
carrying out drone-based rescue operations by detecting the area, rising of urban areas near river basins in Kolhapur and
number of people stuck in flooded regions using YOLO object Sangli area, backwater of Almatti dam causes the swelling of
detection algorithm and notifying concerned authorities about Krishna and Panchganga river and so the disaster has happened
them through web portal and mobile application. and many inhabitants near the river banks of Krishna,
Panchganga and Koyana have been displaced. People faced a
Keywords— Artificial Intelligence, Drones, Flood Monitoring lot of hardship to evacuate to safer places. Hence, it is
System, Flood Rescue System, Internet of Things important to design a flood control mechanism. The pervasive
computing technology is useful in such areas, which utilizes
context to deal with relevant information and services in an
I. INTRODUCTION effective manner [6].
The world’s climate is drastically changing because of
natural calamities like hurricanes, tornadoes, volcanic This paper proposes the IoT and AI based flood monitoring
eruptions, earthquakes, tsunamis, storms, floods and which is and rescue system which is divided in two parts. The IoT-based
only the outcome of human activities such as pollution, cutting part is for prevention of flood which detects the rise in water
trees and many more hazardous activities. These natural level and triggers alarm for alerting nearby people. The AI-
disasters cause great damage and destroy the smooth living of based rescue part detects the number of people stuck in flooded
human life causing the reconstruction of all things including regions and notifies concerned authorities through web portal
the most important basic needs: food, shelter, clothing and and mobile application.
water. Section II explains previous research in related fields.
The Flood is one of the most frequent natural calamities Section III explains the methodology. Section IV analyzes the
India is ever facing. In August 2005 [9], due to heavy rainfalls,

IJERTV9IS090340 www.ijert.org 564

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 9 Issue 09, September-2020

result of the experiment. Section V concludes the paper with an to the Amazon Web Services cloud platform where data
outline of contribution and the future work. processing and analytics will be generated. Data about
atmospheric pressure, water level height, humidity and
II. LITERATURE REVIEW temperature is collected using only one sensor called pressure
sensor (BMP180 Barometric). IC ULN 2003 is used to show
Numerous literatures related to IoT-based sensors and
Computer Vision for flood monitoring and mapping were water level by blinking LED at each level. Data made
outlined [1] by Arshad B.; Ogie R.; Barthelemy J.; Pradhan B.; available on a single website and mobile application is
Verstaevel N. and Perez P. This attempt reviewed different accessible to the concerned authorities and subscribed users
applications aided with IoT and Computer Vision for better for flood monitoring and decision-making. People who
monitoring and mapping of floods. subscribe to this system can also receive alerts and
notifications regarding water level in certain areas.
Wahidah Md. Shah, F. Arif, A. A. Shahrin and Aslinda Drones can be used by integrating Raspberry pi as a rescue
Hassan presented a flood warning system [2] based on IoT that mechanism that will improve the quality of rescue operations
was able to detect water level and calculate the speed of water and help in finding people stuck in flood and providing relief
level increased and alert nearby residents. The experiments resources to needy people. With the help of camera attached to
were conducted in a controlled environment for testing the drones, pictures of flood affected areas are captured and those
implemented system. images are processed using YOLOv3 (You Only Look Once)
. Pan, J.; Yin, Y; Xiong, J.; Luo, W.; Gui, G. and Sari, H. state-of-the-art deep learning based object detection algorithm
developed a network of automated surveillance composed of of Computer Vision library named ImageAI to find the count
distant measuring stations and a control center [3]. They of people stuck in flood. It performs object detection on any
conducted tests using three methods, including the method of image using pre-trained models trained on COCO dataset.
difference, dictionary learning and deep learning. Using its ObjectDetection class allows us to detect and
recognize 80 possible objects. To make it simple, this sytem is
Elena Ridolfi and Piergiorgio Manciola proposed water only concerned about detecting number of people, ignoring
level observations from drones at a dam site [4] which makes other objects. This mechanism can help the government in
use of a sensing device composed of a drone and a camera to rescue operations and to provide required resources to needy
assess the water level. people.
A general-purpose design for context-consciously NEO6M GPS Module is used to get the latitude and
dependent flood control system with regard to longitude of the location wherever help is required. The data is
contextconsciousness was demonstrated by Widiasari I, Nugro uploaded to AWS cloud with the help of NODEMCU
L and Widyawan in the form of WSN-based flood detection ESP8266 WIFI development board. Alerts and notifications
and monitoring device model [5]. about the water level in certain areas are also sent to the
Reference [7] shows how drones can be used during the subscribed users.
times of natural disasters like Kerala floods in India. Since the The web portal and mobile application give information
ban imposed on flying drones in India had been lifted [8], they about safe places and flood affected places, so people can
can be very effective during flood rescue operations. move to safe places. Also, there is information about available
As per reference [10], drones can also be used to deliver shelters for flood victims. This system also provides facility for
critical humanitarian aid. Customized drones can be built for donations for flood victims through the web portal. Information
carrying out rescue and relief operations in a better manner about all volunteers for each area and various government
[11] [12]. schema is made available.

III. METHODOLOGY IV. RESULTS

Following results are obtained through this research at
Walchand College of Engineering, Sangli:

Fig. 1. System Architecture

Fig. 2. Total number of August 2019 Flood victims in Sangli and
As shown in Fig.1, All the data from the sensors are collected Kolhapur districts
by microcontroller Arduino Uno. NODEMCUESP8266 WIFI Fig. 2 visualizes data of 1000 people collected from collector
development board is used to upload data from Arduino Uno office of Sangli that shows total number of people affected in

IJERTV9IS090340 www.ijert.org 565

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 9 Issue 09, September-2020

August 2019 Floods in Sangli and Kolhaur districts. The X- Fig. 5. depicts average altitude observed in September 2019 at
axis shows districts whereas Y-axis represents number of Sangli. This helps to understand the water level heights
people. represented on Y-axis and X-axis.

Fig. 3. Visualization of average temperature observed in September

2019
Fig. 3. shows average temperature observed in September
2019 at Sangli. Total number of observations and average
temperature (in Celsius) for those observations are represented
on Y-axis and X-axis respectively.
Fig. 6. Android Application
The main screen of android application is shown in Fig. 6.
Options such as Maps, Governments schemes and Notices,
Funds collected, etc are available for user.

Fig. 4. Visualization of average atmospheric pressure observed in

September 2019
The average atmospheric pressure in September 2019 at Fig. 7. Web portal
Sangli can be seen in Fig. 4. The values of shown observations Fig. 7. shows web portal where users are able to see volunteers
are recorded through the system and are in Pascal unit. list, safe places list, flood status, fund collection and
distribution, flood victims and government schemes.

Fig. 8. Test image for counting people stuck in flood

As shown in Fig. 8, 10 out of 11 people have been detected
correctly that can be very helpful in rescue operations for
finding how many people are stuck in flood at particular
Fig. 5. Visualization of average altitude observed in September 2019 location.

IJERTV9IS090340 www.ijert.org 566

(This work is licensed under a Creative Commons Attribution 4.0 International License.)
 Published by : International Journal of Engineering Research & Technology (IJERT)
http://www.ijert.org ISSN: 2278-0181
Vol. 9 Issue 09, September-2020

V. CONCLUSION [5] Indrastanti Widiasari, Lukito Nugroho, Widyawan Widyawan, A general

purpose model for context aware based flood monitoring system, Jurnal
The IoT-based early detection of the flood helps to save Teknologi, June, 2016
many lives and enables real-time updates about water level to [6] Anil Surve, Vijay Ghorpade, Pervasive Context-Aware Computing
nearby people so they can relocate to safe places with their Survey of Context-aware ubiquitious middleware systems, International
Journal of Engineering Research and Technology, ISSN 0974-3154,
valuables. The detection helps to prevent damage of houses Volume 10, Number 1, 2017
and businesses due to floods. This innovative approach assists [7] Prince Diwaker, Kerala floods and drones, Geospatial World Forum,
concerned authorities to have access to real-time data in order Aug 22, 2018. Accessed on: Aug 30, 2019. [Online]. Available:
to generate reports and perform analysis. express gratitude to https://www.geospatialworld.net/blogs/kerala-floods-and-drones/
Walchand College of Engineering, Sangli for providing [8] Lysander Fernandes, Flying drones is now legal in India, here's all you
opportunity for conducting this research. need to know, The News Minute, Dec 02, 2018. Accessed on: Sept 15,
2019. [Online]. Available:
https://www.thenewsminute.com/article/flying-drones-now-legalindia-
ACKNOWLEDGMENT heres-all-you-need-know-92558
We express gratitude to Walchand College of Engineering, [9] Shoumojit Banerjee, Kolhapur, Sangli face renewed flood threat as
Sangli for providing an opportunity for conducting this heavy rain batters western Maharashtra, The Hindu, Sept 10, 2019.
research. Accessed on: Sept 16, 2019. [Online]. Available:
https://www.thehindu.com/news/states/kolhapur-sangli-face-
renewedflood-threat-as-heavy-rain-batters-western-maharashtra/
REFERENCES article29378391.ece
[1] Bilal Arshad, Robert Ogie, Johan Barthelemy, Biswajeet Pradhan, [10] Sam Sherman, Using drones to deliver critical humanitarian aid,
Nicolas Verstaevel and Pascal Perez, “Computer Vision and IoTBased Medium, Jun 7, 2018. Accessed on: Oct 3, 2019. [Online]. Available:
Sensors in Flood Monitoring and Mapping: A Systematic Review”, Nov https://medium.com/frontier-technology-livestreaming/using-dronesto-
16, 2019 deliver-critical-humanitarian-aid-1b578253fb76
[2] Wahidah Md. Shah, F. Arif, A. A. Shahrin and Aslinda Hassan, “The [11] "HOW TO BUILD YOUR OWN DRONE FOR $99”, May 6, 2018.
Implementation of an IoT-Based Flood Alert System”, International Accessed on: Oct 10, 2019. [Online]. Available:
Journal of Advanced Computer Science and Applications(IJACSA), https://thedronegirl.com/2018/05/06/build-your-own-drone/
Volume 9 Issue 11, 2018 [12] Jack Brown, HOW TO BUILD A DRONE: CONSTRUCT YOUR
[3] Pan, J.; Yin, Y; Xiong, J.; Luo, W.; Gui, G. and Sari, H., “Deep DRONE FROM SCRATCH. Accessed on: Oct 14, 2019. [Online].
Learning-Based Unmanned Surveillance Systems for Observing Water Available: https://www.mydronelab.com/blog/how-to-build-adrone.html
Levels”, IEEE Access, Volume 6, Nov 28, 2018
[4] Ridolfi, E. and Manciola, P., “Water Level Measurements from Drones:
A Pilot Case Study at a Dam Site”, Water 2018, Volume 10, Issue 3,
Mar 9, 2018

IJERTV9IS090340 www.ijert.org 567

(This work is licensed under a Creative Commons Attribution 4.0 International License.)