Deep Learning Approach for Heavy Rainfall Prediction Using Himawari-8 And RDCA Data

High-intensity rainfall in a short period can increase the likelihood of landslides and floods. The disaster mitigation process will be too late in such a short period. The absence of an early warning system also worsens this. Therefore, an accurate prediction system is needed to predict heavy rainfall. By utilizing real-time observation data from Himawari-8, Rapidly Developing Cumulus Area (RDCA) can predict the possibility of heavy rainfall. However, RDCA has not been able to make predictions for a long period. Therefore, we propose a heavy rainfall prediction model from a deep learning perspective in this research by utilizing cloud observation data from Himawari-8 and RDCA index data. In this study, a Convolutional Long-Short Term Memory Model (ConvLSTM) with an encoder-forecaster architecture is designed to perform heavy rainfall prediction. The results of the model training process show that the performance increases as the training iterations grow. In addition, in experiments with test data, the model also produces probability values that are close to the same as the RDCA index value. This can be seen from the SSIM value, which is close to one.