학술논문

Performance Evaluation of Different Machine Learning Based Algorithms for Flood Prediction and Model for Real Time Flood Prediction
Document Type
Conference
Source
2019 5th International Conference On Computing, Communication, Control And Automation (ICCUBEA) Computing, Communication, Control And Automation (ICCUBEA), 2019 5th International Conference On. :1-7 Sep, 2019
Subject
Communication, Networking and Broadcast Technologies
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Support Vector Machines
Recurrent Neural Networks
Random Forest
Decision Tree
Naive Bayes
Logistic Regression
Language
Abstract
Floods are one of the most destructive natural calamities, which are highly complex to model. The causes leading to floods involve many parameters and climatic conditions of the region of interest and it makes a huge impact leading to loss of several lives, damages infrastructure and much more. A flood prediction model can contribute to the risk reduction, policy suggestion, minimization of the loss of human life and reduction of the property damage associated with floods.In this paper, various machine learning algorithms are tested on the collected dataset, to determine which algorithm works best and the influential parameters. In this paper we have also proposed flood prediction model for Mumbai using machine learning and developed an Android application for the same.