AUTHOR=Song Dan , Ling Yuting , Hao Tong , Li Wenhui , Liu Wen , Ren Tongwei , Wei Zhiqiang , Liu An-an 

TITLE=A residual network with geographical and meteorological attention for multi-year ENSO forecasts

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2023.1195445

DOI=10.3389/fmars.2023.1195445

ISSN=2296-7745

ABSTRACT=As global temperatures continue to rise, El Niño events, one of the extreme weather phenomena near the equatorial Pacific Ocean, are occurring more frequently and leading to tropical cyclones, droughts, and a series of extreme weather disasters. Accurately predicting El Niño events in advance can greatly reduce the serious damage to human society, the economy, and the ecological environment. Existing works often fit historical meteorological data using deep networks, neglecting the data relation between geographical regions and meteorological factors. To overcome this problem, we propose a residual network with geographical and meteorological attention to capture important geographical information and explore the spatio-temporal correlation of different meteorological factors. Specifically, we propose two main attention modules: (1) the Geographical Semantic Information Enhancement Module (GSIEM), which selectively attends to important geographical regions and filters out irrelevant noise through a spatial-axis attention map, and (2) the Meteorological Factors Discriminating Enhancement Module (MFDEM), which aims to learn the spatio-temporal dependency of different meteorological factors using a learnable channel-axis weight map. We then integrate our proposed two attention modules into the backbone using residual connection, enhancing the model's prediction ability. Extensive experimental comparisons and ablation studies show that our method outperforms existing state-of-the-art methods, verifying the superiority and effectiveness of our model.