ABSTRACT: Agriculture is the key point for survival for developing nations like India. For farming, precipitation is generally significant. Precipitation updates are helpful for evaluating water assets, farming, ecosystems and hydrology. Nowadays precipitation anticipation has become a foremost issue. Forecast of precipitation offers attention to individuals and know in advance about precipitation to avoid potential risk to shield their crop yields from severe precipitation. This study intends to investigate the dependability of integrating a data pre-processing technique called singular-spectrum-analysis (SSA) with supervised learning models called least-squares support vector regression (LS-SVR), and Random-Forest (RF), for precipitation prediction. Integrating SSA with LS-SVR and RF, the combined framework is designed and contrasted with the customary approaches (LS-SVR and RF). The presented frameworks were trained and tested utilizing monthly climate dataset which is separated into 80:20 ratios for training and testing respectively. Performance of the model was assessed using RMSE and NSE. Experimental outcomes illustrate that the proposed model can productively predict the rainfall.

KEYWORDS: Singular-Spectrum-Analysis, Supervised  Learning, Rainfall, SVR, RF, Prediction