DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data

TL;DR

DeepRain employs ConvLSTM neural networks to predict rainfall from multichannel radar data, significantly improving accuracy over traditional methods, demonstrating the potential of deep learning in weather forecasting.

Contribution

The paper introduces DeepRain, a novel ConvLSTM-based model for rainfall prediction using 3D multichannel radar data, achieving notable accuracy improvements.

Findings

ConvLSTM reduces RMSE by 23% compared to linear regression.

DeepRain effectively models spatiotemporal radar data for rainfall prediction.

Experimental results validate the model's superior performance in precipitation forecasting.

Abstract

Accurate rainfall forecasting is critical because it has a great impact on people's social and economic activities. Recent trends on various literatures show that Deep Learning (Neural Network) is a promising methodology to tackle many challenging tasks. In this study, we introduce a brand-new data-driven precipitation prediction model called DeepRain. This model predicts the amount of rainfall from weather radar data, which is three-dimensional and four-channel data, using convolutional LSTM (ConvLSTM). ConvLSTM is a variant of LSTM (Long Short-Term Memory) containing a convolution operation inside the LSTM cell. For the experiment, we used radar reflectivity data for a two-year period whose input is in a time series format in units of 6 min divided into 15 records. The output is the predicted rainfall information for the input data. Experimental results show that two-stacked ConvLSTM reduced RMSE by 23.0% compared to linear regression.