Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi
{"title":"MambaDS:利用地形约束选择性状态空间建模进行近地表气象场降维分析","authors":"Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi","doi":"arxiv-2408.10854","DOIUrl":null,"url":null,"abstract":"In an era of frequent extreme weather and global warming, obtaining precise,\nfine-grained near-surface weather forecasts is increasingly essential for human\nactivities. Downscaling (DS), a crucial task in meteorological forecasting,\nenables the reconstruction of high-resolution meteorological states for target\nregions from global-scale forecast results. Previous downscaling methods,\ninspired by CNN and Transformer-based super-resolution models, lacked tailored\ndesigns for meteorology and encountered structural limitations. Notably, they\nfailed to efficiently integrate topography, a crucial prior in the downscaling\nprocess. In this paper, we address these limitations by pioneering the\nselective state space model into the meteorological field downscaling and\npropose a novel model called MambaDS. This model enhances the utilization of\nmultivariable correlations and topography information, unique challenges in the\ndownscaling process while retaining the advantages of Mamba in long-range\ndependency modeling and linear computational complexity. Through extensive\nexperiments in both China mainland and the continental United States (CONUS),\nwe validated that our proposed MambaDS achieves state-of-the-art results in\nthree different types of meteorological field downscaling settings. We will\nrelease the code subsequently.","PeriodicalId":501166,"journal":{"name":"arXiv - PHYS - Atmospheric and Oceanic Physics","volume":"59 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling\",\"authors\":\"Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi\",\"doi\":\"arxiv-2408.10854\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In an era of frequent extreme weather and global warming, obtaining precise,\\nfine-grained near-surface weather forecasts is increasingly essential for human\\nactivities. Downscaling (DS), a crucial task in meteorological forecasting,\\nenables the reconstruction of high-resolution meteorological states for target\\nregions from global-scale forecast results. Previous downscaling methods,\\ninspired by CNN and Transformer-based super-resolution models, lacked tailored\\ndesigns for meteorology and encountered structural limitations. Notably, they\\nfailed to efficiently integrate topography, a crucial prior in the downscaling\\nprocess. In this paper, we address these limitations by pioneering the\\nselective state space model into the meteorological field downscaling and\\npropose a novel model called MambaDS. This model enhances the utilization of\\nmultivariable correlations and topography information, unique challenges in the\\ndownscaling process while retaining the advantages of Mamba in long-range\\ndependency modeling and linear computational complexity. Through extensive\\nexperiments in both China mainland and the continental United States (CONUS),\\nwe validated that our proposed MambaDS achieves state-of-the-art results in\\nthree different types of meteorological field downscaling settings. We will\\nrelease the code subsequently.\",\"PeriodicalId\":501166,\"journal\":{\"name\":\"arXiv - PHYS - Atmospheric and Oceanic Physics\",\"volume\":\"59 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Atmospheric and Oceanic Physics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.10854\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Atmospheric and Oceanic Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.10854","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling
In an era of frequent extreme weather and global warming, obtaining precise,
fine-grained near-surface weather forecasts is increasingly essential for human
activities. Downscaling (DS), a crucial task in meteorological forecasting,
enables the reconstruction of high-resolution meteorological states for target
regions from global-scale forecast results. Previous downscaling methods,
inspired by CNN and Transformer-based super-resolution models, lacked tailored
designs for meteorology and encountered structural limitations. Notably, they
failed to efficiently integrate topography, a crucial prior in the downscaling
process. In this paper, we address these limitations by pioneering the
selective state space model into the meteorological field downscaling and
propose a novel model called MambaDS. This model enhances the utilization of
multivariable correlations and topography information, unique challenges in the
downscaling process while retaining the advantages of Mamba in long-range
dependency modeling and linear computational complexity. Through extensive
experiments in both China mainland and the continental United States (CONUS),
we validated that our proposed MambaDS achieves state-of-the-art results in
three different types of meteorological field downscaling settings. We will
release the code subsequently.