Precipitation Nowcasting: Leveraging bidirectional LSTM and 1D CNN

2018/10/24 by Patel, Maitreya, Patel, Anery, Ghosh, Dr. Ranendu
#FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.1810.10485

Abstract

Short-term rainfall forecasting, also known as precipitation nowcasting has become a potentially fundamental technology impacting significant real-world applications ranging from flight safety, rainstorm alerts to farm irrigation timings. Since weather forecasting involves identifying the underlying structure in a huge amount of data, deep-learning based precipitation nowcasting has intuitively outperformed the traditional linear extrapolation methods. Our research work intends to utilize the recent advances in deep learning to nowcasting, a multi-variable time series forecasting problem. Specifically, we leverage a bidirectional LSTM (Long Short-Term Memory) neural network architecture which remarkably captures the temporal features and long-term dependencies from historical data. To further our studies, we compare the bidirectional LSTM network with 1D CNN model to prove the capabilities of sequence models over feed-forward neural architectures in forecasting related problems.

Related

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Deep learning for precipitation nowcasting: A survey from the perspective of time series forecasting
• Multi-Source Temporal Attention Network for Precipitation Nowcasting
• Self-supervised Spatial-Temporal Learner for Precipitation Nowcasting
• Deep Learning for Weather Forecasting: A CNN-LSTM Hybrid Model for Predicting Historical Temperature Data