Attef: Convolutional lstm encoder-forecaster with attention module for precipitation nowcasting

Wei Fang, Lin Pang, Weinan Yi, Victor S. Sheng

Research output: Contribution to journalArticlepeer-review

Abstract

Precipitation nowcasting has become an essential technology underly-ing various public services ranging from weather advisories to citywide rainfall alerts. The main challenge facing many algorithms is the high non-linearity and temporal-spatial complexity of the radar image. Convolutional Long Short-Term Memory (ConvLSTM) is appropriate for modeling spatiotemporal variations as it integrates the convolution operator into recurrent state transition functions. How-ever, the technical characteristic of encoding the input sequence into a fixed-size vector cannot guarantee that ConvLSTM maintains adequate sequence representations in the information flow, which affects the performance of the task. In this paper, we propose Attention ConvLSTM Encoder-Forecaster(AttEF) which allows the encoder to encode all spatiotemporal information in a sequence of vec-tors. We design the attention module by exploring the ability of ConvLSTM to mergespace-time features and draw spatial attention. Specifically, several variants of ConvLSTM are evaluated: (a) embedding global-channel attention block (GCA-block) in ConvLSTM Encoder-Decoder, (b) embedding GCA-block in FconvLSTM Encoder-Decoder, (c) embedding global-channel-spatial attention block (GCSA-block) in ConvLSTM Encoder-Decoder. The results of the evaluation indicate that GCA-ConvLSTM produces the best performance of all three variants. Based on this, a new frame work which integrates the global-channel attention into the ConvLSTM encoder-forecaster is derived to model the compli-cated variations. Experimental results show that the main reason for the blurring of visual performance is the loss of crucial spatiotemporal information. Integrat-ing the attention module can resolve this problem significantly.

Original languageEnglish
Pages (from-to)453-466
Number of pages14
JournalIntelligent Automation and Soft Computing
Volume30
Issue number2
DOIs
StatePublished - 2021

Keywords

  • Attention mechanism
  • Convolutional LSTM
  • Precipitation nowcasting
  • Sequence-to-sequence model

Fingerprint

Dive into the research topics of 'Attef: Convolutional lstm encoder-forecaster with attention module for precipitation nowcasting'. Together they form a unique fingerprint.

Cite this