DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data

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.

Climate Informatics Workshop 2017

References in corpus (1)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

Cited by in corpus (11)

• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Short-term daily precipitation forecasting with seasonally-integrated autoencoder
• Deformation Driven Seq2Seq Longitudinal Tumor and Organs-at-Risk Prediction for Radiotherapy
• Deep multi-stations weather forecasting: explainable recurrent convolutional neural networks
• Application of LSTM architectures for next frame forecasting in Sentinel-1 images time series
• Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
• Feedback U-net for Cell Image Segmentation
• Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
• DeepSTCL: A Deep Spatio-temporal ConvLSTM for Travel Demand Prediction
• FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting
• Improving the Thermal Infrared Monitoring of Volcanoes: A Deep Learning Approach for Intermittent Image Series