Abstract
In recent years the machine learning has been proven as a powerful tool for predicting the rainfall
that could be useful in many sectors. This study will focus on predicting rainfall for the agriculture
sector. Indian climatic conditions vary in terms of rainfall, which can be divided and observed
on the basis of states. In addition, if rainfall is categorized state-wise; the constant & highest
trend can be observed in the state called Meghalaya. While the lowest rainfall can be observed
in both of the following states - Leh and Rajasthan. Agriculture is the crucial player in the econ-
omy of India, and it is highly dependent on agriculture and forestry, which are a ected by rainfall
[Krishna Kumar et al., 2004].
Disaster due to heavy rainfall like
oods leads to the destruction of crops which a ects the farming
sectors. If the prediction for rainfall is made by taking monthly and seasonal data of the crop into
consideration; then it would be bene cial for the agriculture sector. This study will be applying the
regression algorithms by di erent models, which can help in predicting the rainfall. To achieve such
results, this study will be using ve various regression models and select the best one among - Mul-
tiple linear regression, KNN regression, SVM(Support Vector Machine) regression, DTR(Decision
tree regression), RFE(Random forest regression. The aim is to develop a model that can predict
the rainfall that will help the agriculture sector, so that rainfall doesn't become a barrier for the
agricultural production.