Realtime Flood Forecasting System

Table of content

✓ Overview
✓ Solution
✓ Team
✓ Links

• Overview

Floods are the most destructive form of natural hazards in both local and global context.This is true in terms of both loss of life and property damage. Early flood forecasting can be used to identify potential areas of flooding in order to develop mitigatory planning and evacuation programs to remove people from such areas during flooding and also to implement suitable preventive measures to avoid damage to properties.
In this project, our main objective is to build a flood forecasting system for Mi Oya river basin(Sri Lanka).Mi Oya Basin is heavily affected by seasonal flooding and droughts.

As per the available data, floods in the Mi Oya basin are unleashed due to river overflow and reservoir spilling. Out of the several reservoirs located in the basin, Tabbowa and Inginimitiya are crucial in worsening the flood impacts as these two reservoirs are frequently spilling under adverse weather conditions. As such, the prevalence of a real-time flood forecasting model with the incorporation of the reservoir operations for the entire basin is essential to alleviate the flood induced impacts while preserving the optimum volume of water in the major reservoirs in the basin.

• Solution

The proposed solution is to implement a simple data-driven or machine learning model to identify a direct mapping between the inputs(e.g., precipitation(P), temperature(T), potential evapotranspiration(PET), etc.) and outputs(In-flow level) without detailed consideration of the internal structure of the physical process.

Objectives

Realtime Flood Forecast: Real-time Flood Forecast system for early warning and flood management
Flood Inundation GIS Map: improve flood modeling and disaster response planning
Interactive Website: provide access to flood-related information, resources, and support

Machine Learning Approach

Structure of the Web Interface

Users of the System

Public Users: public users can get warning messages,view forecastsand view real time maps/data
Officials: officials can access the Control Panel and get Reports

• Team

Project Owner

Dr.Upul Jayasinghe, upuljm@eng.pdn.ac.lk

Team members

Konara K.M.S.L, e18181@eng.pdn.ac.lk
Rathnayake R.M.P.P, e18297@eng.pdn.ac.lk
Wimalasiri K.H.C.T, e18402@eng.pdn.ac.lk

• Links

Project page
Department of Computer Engineering
University of Peradeniya