Rainfall is one of the major source of freshwater for all the organism around the world. Rainfall prediction model provides the information regarding various climatological variables on the amount of rainfall. In recent days, Deep Learning enabled the self-learning data labels which allows to create a data-driven model for a time series dataset. It allows to make the anomaly/change detection from the time series data and also predicts the future event's data with respect to the events occurred in the past. This paper deals with obtaining models of the rainfall precipitation by using Deep Learning Architectures (LSTM and ConvNet) and determining the better architecture with RMSE of LSTM as 2.55 and RMSE of ConvNet as 2.44 claiming that for any time series dataset, Deep Learning models will be effective and efficient for the modellers.

The paper presents a fast, reliable and efficient method for improving hyperspectral image classification aided by segmentation. The Multinomial Logistic Regression(MLR) algorithm can be extended to a semi-supervised learning of the posterior class distribution using unlabeled samples actively selected from the dataset. Classification results obtained from regression model is improved by performing a maximum a posteriori segmentation as it considers the spatial information of the hyperspectral image. The addition of the spatial processing step prior to the above mentioned classification scheme improves the overall accuracy of the process. The accuracies obtained before and after applying the preprocessing are compared