The idea of this paper is to predict daily rainfall from satellite observation for disaster management using artificial intelligence. It uses multi-stacked LSTM for the prediction of daily rainfall. The model uses 40 years of NASA dataset of Yamuna Nagar district in Haryana, India during the period 1980 - 2020 for the training purpose. The results show that LSTM based neural networks are better alternative to forecast general weather conditions when compared with traditional methods.