A Disaster Prediction Ensemble Classifier Using Artificial Intelligence
V. Bharathi, A. Saranya, Garima Shukla, Deepika Shekhawat, Vanshaj Awasthi, C. N. S. Vinoth Kumar · 2024
Natural and man-made disasters may have severe impacts, but disaster prediction can help lessen such effects. The natural catastrophes that strike India on a regular basis cause immense devastation in terms of human lives and material possessions. Predicting the start and development of disasters in real-time is essential for reducing their effect. For more precise and trustworthy catastrophe predictions, this research presents an AI-powered catastrophe Ensemble B-Classifier network (DE BCN). The DPEC ensemble technique improves forecast accuracy over individual models by integrating various predictive outputs from numerous machine learning models that specialise in distinct kinds of disasters. This is where the data was originally pulled from Kaggle. To finish off the preprocessing, the norma clash filter was used. The next step is to use the optimisation method known as mustard twin swarm to extract characteristics that are connected to the tragedy. With any luck, the calamity Ensemble-B Classifier network will be able to forecast the calamity. Python and the Kaggle database were the environments used to carry out the investigation. According to the results of the simulations, the suggested approach is better than the current standard for predicting the catastrophic state.