Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Han, Tao, Wen, Zhibin, Chen, Zhenghao, Du, Dazhao, Guo, Song, Bai, Lei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914434613510144
author Han, Tao
Wen, Zhibin
Chen, Zhenghao
Du, Dazhao
Guo, Song
Bai, Lei
author_facet Han, Tao
Wen, Zhibin
Chen, Zhenghao
Du, Dazhao
Guo, Song
Bai, Lei
contents The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse. To address this, we introduce WEATHER-5K, a large-scale observational weather dataset that better reflects real-world conditions, supporting improved model training and evaluation. While recent TSF methods perform well on benchmarks, they lag behind operational Numerical Weather Prediction systems in capturing complex weather dynamics and extreme events. We propose PhysicsFormer, a physics-informed forecasting model combining a dynamic core with a Transformer residual to predict future weather states. Physical consistency is enforced via pressure-wind alignment and energy-aware smoothness losses, ensuring plausible dynamics while capturing complex temporal patterns. We benchmark PhysicsFormer and other TSF models against operational systems across several weather variables, extreme event prediction, and model complexity, providing a comprehensive assessment of the gap between academic TSF models and operational forecasting. The dataset and benchmark implementation are available at: https://github.com/taohan10200/WEATHER-5K.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14399
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
Han, Tao
Wen, Zhibin
Chen, Zhenghao
Du, Dazhao
Guo, Song
Bai, Lei
Machine Learning
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
The development of Time-Series Forecasting (TSF) models is often constrained by the lack of comprehensive datasets, especially in Global Station Weather Forecasting (GSWF), where existing datasets are small, temporally short, and spatially sparse. To address this, we introduce WEATHER-5K, a large-scale observational weather dataset that better reflects real-world conditions, supporting improved model training and evaluation. While recent TSF methods perform well on benchmarks, they lag behind operational Numerical Weather Prediction systems in capturing complex weather dynamics and extreme events. We propose PhysicsFormer, a physics-informed forecasting model combining a dynamic core with a Transformer residual to predict future weather states. Physical consistency is enforced via pressure-wind alignment and energy-aware smoothness losses, ensuring plausible dynamics while capturing complex temporal patterns. We benchmark PhysicsFormer and other TSF models against operational systems across several weather variables, extreme event prediction, and model complexity, providing a comprehensive assessment of the gap between academic TSF models and operational forecasting. The dataset and benchmark implementation are available at: https://github.com/taohan10200/WEATHER-5K.
title Benchmarking Physics-Informed Time-Series Models for Operational Global Station Weather Forecasting
topic Machine Learning
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2406.14399