Ada Naïve Bayesian Algorithm for Predicting the Intensity of Rain to Improve the Accuracy

The Indian subcontinent is the globe's more vulnerable disaster area. A coast border for such area was approximately 7516 kilometres long, including 132 kilometres at Lakshadweep, 5400 kilometres in a major landmass, and 1900 kilometres on an Andaman. Almost 10percent of every major disaster that has developed across the globe has occurred in this territory. According to estimates from 2008 to 2021, a disaster impacted a total of over 370 thousand population across India. Throughout the pre-monsoon seasons, storm development is roughly 30percent on the Bay of Bengal & 25percent on an Arabian Ocean. Thousands of people died as a result of a hurricane, which also caused significant damage to governmental & corporate property. As a result, predicting the intensity of rain is increasingly necessary & critical. An XG Boost (severe Gradients Booster) technique is used in the next part of the study to forecast the development & intensity of rain around the Bay of Bengal, & their effectiveness was evaluated using SVM models. Several lives have been rescued as a result of great scientific growth & improvement at detecting rain far in ahead, such as Gaja & Fani, from IMD. During the last step of this study, the hybrids technique integrating a genetics algorithm and an XGBoost method (GA-XGBoost) is presented for forecasting the intensity for subtropical cyclones (TCs) at the Bay of Bengal (BoB) using data by the Indian Meteorology Department (IMD). Moreover, while comparing current methods, the outcomes of a hybrid approach for TC information are superior.