MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qin, Haoyu, Chen, Yungang, Jiang, Qianchuan, Sun, Pengchao, Ye, Xiancai, Lin, Chao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929458949128192
author Qin, Haoyu
Chen, Yungang
Jiang, Qianchuan
Sun, Pengchao
Ye, Xiancai
Lin, Chao
author_facet Qin, Haoyu
Chen, Yungang
Jiang, Qianchuan
Sun, Pengchao
Ye, Xiancai
Lin, Chao
contents Deep Learning based Weather Prediction (DLWP) models have been improving rapidly over the last few years, surpassing state of the art numerical weather forecasts by significant margins. While much of the optimization effort is focused on training curriculum to extend forecast range in the global context, two aspects remains less explored: limited area modeling and better backbones for weather forecasting. We show in this paper that MetMamba, a DLWP model built on a state-of-the-art state-space model, Mamba, offers notable performance gains and unique advantages over other popular backbones using traditional attention mechanisms and neural operators. We also demonstrate the feasibility of deep learning based limited area modeling via coupled training with a global host model.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06400
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model
Qin, Haoyu
Chen, Yungang
Jiang, Qianchuan
Sun, Pengchao
Ye, Xiancai
Lin, Chao
Atmospheric and Oceanic Physics
Machine Learning
Deep Learning based Weather Prediction (DLWP) models have been improving rapidly over the last few years, surpassing state of the art numerical weather forecasts by significant margins. While much of the optimization effort is focused on training curriculum to extend forecast range in the global context, two aspects remains less explored: limited area modeling and better backbones for weather forecasting. We show in this paper that MetMamba, a DLWP model built on a state-of-the-art state-space model, Mamba, offers notable performance gains and unique advantages over other popular backbones using traditional attention mechanisms and neural operators. We also demonstrate the feasibility of deep learning based limited area modeling via coupled training with a global host model.
title MetMamba: Regional Weather Forecasting with Spatial-Temporal Mamba Model
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2408.06400