Machine Learning-based Rainfall Prediction on Indian Agriculture Land

The Indian agriculture sector boasts the second-largest agricultural land area globally, serving as a crucial source of employment for nearly half of the Indian population and playing a significant role in driving the country's economy. The Indian agriculture sector has undergone significant growth and expansion in recent decades. The weather and the surrounding environment significantly influence agricultural productivity, both in terms of quality and quantity. Errorless weather forecasting has the potential to impact the scheduling of planting and harvesting activities, as well as influence spending on essential agricultural inputs, such as irrigation, insecticides, fertilizers, and herbicides. The productivity of agriculture is significantly influenced by rainfall, making it one of the primary factors to consider. Disaster rains or no rains can create situations like floods or droughts that will lead to disaster reduction in crop productivity. Machine learning (ML) and deep learning (DL) algorithms have emerged as highly effective tools for making predictions in various fields in recent years. The main objective of this paper is to conduct a comparison-based analysis of ML and DL methods for predicting rainfall with the help of the meteorological dataset gathered for the agricultural land of Surguja, located in the Chhattisgarh, region of India.