One of the most frequent natural disasters in the world, flooding affects millions of people annually and causes significant economic losses as well as human tragedies, with India bearing a disproportionate amount of the burden. Reducing these effects requires effective early warning systems, yet many vulnerable communities still struggle to make use of them. Scientists and programmers are using advances in machine learning (ML) and artificial intelligence (AI) to bridge this gap by creating a trustworthy flood prediction system. This state-of-the-art system aims to offer more cost-effective choices that perform better at predicting floods caused by precipitation. This prediction system’s primary job is to forecast potential flood events by utilizing previous rainfall data to create predictive models. The model looks at rainfall patterns specific to different locations to determine the likelihood of a flood event. Its growth depends on the utilization of extensive district-level rainfall information from India, which serve as the foundation for training and enhancing the prediction models. A range of machine learning (ML) techniques, such as XGBoost and K-Nearest Neighbors (KNN), are used to train predictive algorithms. These algorithms were chosen because of their ability to handle complex datasets and extract meaningful patterns that relate the amount of rainfall with the probability of floods. Through recurrent training and validation against past flood events, the models are improved to reliably determine whether a region is in danger of flooding based on measured rainfall amounts.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Flood Risk Assesment System using Logistic Regression


    Contributors:


    Publication date :

    2024-11-06


    Size :

    526522 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Risk assesment system of autonomous driving road

    LEE MYUNG SU / KIM TAE HYEONG / YUN HYEONG SEOK et al. | European Patent Office | 2022

    Free access

    Modern Methods for Collision Risk Assesment

    Saez-Bo, Daniel / Maric, Nina / Arias, Eduardo et al. | TIBKAT | 2023


    Driving risk status prediction using Bayesian networks and logistic regression

    Yan, Lixin / Huang, Zhen / Zhang, Yishi et al. | Wiley | 2017

    Free access

    Driving risk status prediction using Bayesian networks and logistic regression

    Yan, Lixin / Huang, Zhen / Zhang, Yishi et al. | IET | 2017

    Free access