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

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.