Published Paper Details:

The central objective of this project is to employ machine learning techniques to forecast natural disasters proactively. Utilizing statistical models applied to historical data, the system aims to predict future occurrences, incorporating Geographic Information System (GIS) data on tectonic plates and past floods. Through this approach, the model can be trained to anticipate floods and tsunamis, enabling early predictions that play a pivotal role in facilitating timely evacuation and disaster preparedness.Throughout the course of history, natural disasters have consistently posed a global-level threat, unleashing catastrophic events that cause significant harm to both lives and property. These disasters have not only eradicated entire civilizations but have also steered the course of human history. The toll exacted by natural disasters is immense, resulting in the loss of hundreds of thousands of lives and billions in property damage. Despite advancements in physical, mental, and technological aspects, there are challenges that humans cannot fully overcome, with natural disasters standing out as one such formidable force. While humanity may not possess the ability to prevent natural disasters entirely, adequate preparation lies within our control. Natural disasters can be broadly classified into geological and meteorological types. Despite ongoing efforts to predict earthquakes and other natural disasters, achieving precise predictions remains an enduring challenge.