Abstract :

Floods Are Among The Most Destructive Natural Disasters, Causing Extensive Damage To Life, Property, And Infrastructure. Accurate And Timely Flood Prediction Is Crucial For Effective Disaster Management And Mitigation. Traditional Hydrological And Statistical Models Often Struggle To Capture The Complex Nonlinear Relationships Between Multiple Environmental Factors Such As Rainfall, River Flow, Soil Moisture, And Topography. To Address This Limitation, This Study Proposes An Integrated Flood Prediction Framework Using Deep Convolutional Neural Networks (Deep CNN). The Proposed Model Integrates Multisource Data, Including Meteorological, Hydrological, And Satellite Imagery, To Learn Spatial And Temporal Dependencies Associated With Flood Occurrences. Deep CNNs Automatically Extract High-level Features From Raw Data, Reducing The Need For Manual Feature Engineering And Improving Prediction Accuracy. Experimental Results Demonstrate That The Deep CNN Model Outperforms Traditional Machine Learning Algorithms Such As Random Forest And SVM In Terms Of Accuracy, Precision, And Recall. This Integrated Approach Provides A Reliable And Data-driven Solution For Real-time Flood Forecasting And Early Warning Systems. The Proposed Model Can Support Disaster Management Authorities In Making Timely Decisions, Minimizing Economic Loss, And Safeguarding Human Lives

Published:

03-11-2025

Issue:

Vol. 25 No. 11 (2025)

Page Nos:

11-16

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite