OPTIMAL DEPLOYMENT OF RESCUE UNITS IN FLOOD DISASTERS USING MACHINE LEARNINGID: 3543 Abstract :Flood-related Disasters Usually Lead To Great Challenges To Peoples Lives, Transportation Means, And Rescue Operations During Emergency Times. It Is Hard To Develop Any Kind Of Rescue Plan Because Of Sudden Changes In The Environment. Traditional Approaches Towards Flood Management Involve Manual Coordination, Late Communication, And Stationary Flood Detection Techniques That May Hamper Rescue Operations And Decrease Efficiency. Besides, Existing Solutions Are Not Able To Provide Intelligent Route Planning And Protected Data Transmission In Disaster Scenarios. An Intelligent Flood Management System That Relies On Such Technologies As Artificial Intelligence (AI), Geographic Information Systems (GIS), Blockchain, And Edge– Cloud Computing Is Suggested As A Solution In The Paper. A Random Forest Classifier Is Implemented In Order To Predict Floods Based On Environmental Parameters, Including Rainfall Amount, Humidity, Slope, Drainage, And Temperature. Reinforcement Learning Is Used To Find Appropriate Routes In Line With Flood-related Circumstances And Road Conditions. Blockchain Technology Will Ensure The Protection And Transparency Of Communication Among Rescue Agencies. According To Experimental Results, The Proposed Intelligent System Helps Increase Coordination And Prediction Efficiency With The Accuracy Rate Reaching 96.3%. Keywords: Flood Disaster Management, Artificial Intelligence, Random Forest, Reinforcement Learning, Geographic Information System (GIS), Blockchain Technology, Edge Computing, Flood Risk Prediction, Rescue Route Optimization, Machine Learning |
Published:15-7-2026 Issue:Vol. 26 No. 7 (2026) Page Nos:567-580 Section:Articles License:This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. How to CiteYECHU HARSHITHA, OPTIMAL DEPLOYMENT OF RESCUE UNITS IN FLOOD DISASTERS USING MACHINE LEARNING , 2026, International Journal of Engineering Sciences and Advanced Technology, 26(7), Page 567-580, ISSN No: 2250-3676. |