UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations
Abstract
Global In-situ Observation (GIO) provides fine-scale, direct records of the global weather system from sparse point stations, making it an indispensable source for capturing localized and transient dynamics beyond the reach of satellite gridded data, and playing a critical role in key fields such as numerical weather prediction, disaster prevention, and agriculture. However, GIO exhibits strong spatiotemporal incompleteness, severely impairing accurate and real-time in-situ weather modeling. Unlike existing methods waiting for completed AI-ready data with extra introduced errors, in this work, we explore UniGIO, a novel generative framework for directly modeling global in-situ weather dynamics from native incomplete GIO. By generating missing data from observed ones annotated by masks, it unifies the coexisting forecasting, imputation, and generation under arbitrary missing ratios. Between the missing and observed, UniGIO captures station and region level complementarity through the Observation Mixer and Event Aligner, which diffuse discrete observations into continuous spaces where weather processes naturally span multiple stations. We further establish temporal dependencies with pattern shifts using the Adaptive Temporal Mixer, and track extreme events in chaotic local weather systems through a Mixture-ofExperts structure. Steady and extreme events are adapted in decoder by a Local Refiner. Extensive experiments on the up-todate largest global station weather dataset Weather-5K validate its SOTA performance with 11%, 12%, and 5% advantages on accuracy, fidelity, and extreme event capture, delivering a novel holistic solution for weather modeling in GIO networks.
Related
- P-stationary structural equation modeling: Causal effect identification under temporally incomplete observations
- Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
- Generative diffusion models for spatiotemporal influenza forecasting
- Instance Optimal Sparse Recovery from Nonlinear Observations: A Unified Framework
- Why we should condition denoising diffusion generative models on windows of past observations
BibTeX
@misc{yang2026unigio,
title = {{UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations}},
author = {Songru Yang and Zili Liu and Tao Han and Ben Fei and Lei Bai and Chang Liu and Zhengxia Zou and Xiangyang Ji and Wanli Ouyang and Zhenwei Shi},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22217},
eprint = {2609.22217},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22217},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations
AU - Songru Yang
AU - Zili Liu
AU - Tao Han
AU - Ben Fei
AU - Lei Bai
AU - Chang Liu
AU - Zhengxia Zou
AU - Xiangyang Ji
AU - Wanli Ouyang
AU - Zhenwei Shi
PY - 2026
DA - 2026/09/02
PB - arXiv
DO - 10.48550/arxiv.2609.22217
UR - https://arxiv.org/abs/2609.22217
AB - Global In-situ Observation (GIO) provides fine-scale, direct records of the global weather system from sparse point stations, making it an indispensable source for capturing localized and transient dynamics beyond the reach of satellite gridded data, and playing a critical role in key fields such as numerical weather prediction, disaster prevention, and agriculture. However, GIO exhibits strong spatiotemporal incompleteness, severely impairing accurate and real-time in-situ weather modeling. Unlike existing methods waiting for completed AI-ready data with extra introduced errors, in this work, we explore UniGIO, a novel generative framework for directly modeling global in-situ weather dynamics from native incomplete GIO. By generating missing data from observed ones annotated by masks, it unifies the coexisting forecasting, imputation, and generation under arbitrary missing ratios. Between the missing and observed, UniGIO captures station and region level complementarity through the Observation Mixer and Event Aligner, which diffuse discrete observations into continuous spaces where weather processes naturally span multiple stations. We further establish temporal dependencies with pattern shifts using the Adaptive Temporal Mixer, and track extreme events in chaotic local weather systems through a Mixture-ofExperts structure. Steady and extreme events are adapted in decoder by a Local Refiner. Extensive experiments on the up-todate largest global station weather dataset Weather-5K validate its SOTA performance with 11%, 12%, and 5% advantages on accuracy, fidelity, and extreme event capture, delivering a novel holistic solution for weather modeling in GIO networks.
ER -