Seeing Inside the Storm: Improving Nowcasting by Integrating Meteorological Drivers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiu, Minghui, Chen, Jun, Chen, Lin, Chen, Weifeng, Zhong, Shuxin, Liu, Zhidan, Zhang, Yu, Wu, Kaishun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914593917370368
author Qiu, Minghui
Chen, Jun
Chen, Lin
Chen, Weifeng
Zhong, Shuxin
Liu, Zhidan
Zhang, Yu
Wu, Kaishun
author_facet Qiu, Minghui
Chen, Jun
Chen, Lin
Chen, Weifeng
Zhong, Shuxin
Liu, Zhidan
Zhang, Yu
Wu, Kaishun
contents Most nowcasting systems, built on radar reflectivity, focus on current precipitation, ignoring the atmospheric precursors -- such as low-level convergence, turbulent eddies, and latent heating -- that offer a fleeting window to foresee storm birth. We introduce MeteoLogist, a physics-inspired radar intelligence framework that models the full life cycle of convection -- from its precursors to organized storm evolution. However, exploiting these precursors is non-trivial: they originate from multiple meteorological drivers -- thermodynamic, kinematic, and microphysical -- that evolve asynchronously (C1) and remain spatially fragmented (C2). To this end, MeteoLogist designs three tightly integrated components. The Physics-Tailored Encoders process radar echoes according to their intrinsic physical scales and semantics, forming thermodynamic, kinematic, and microphysical streams that capture distinct dynamical regimes. The Temporal-Phase Aligner addresses C1 by leveraging causal temporal attention to capture when and how different drivers interact and activate. The Cross-Field Spatial Aggregator addresses C2 through cross-regional fusion, aligning weak and scattered precursors across neighboring cells to expose upstream triggers and enforce spatial coherence. Evaluated on 3D-NEXRAD (2020--2022, US-wide), MeteoLogist boosts high-impact detection (CSI40) by +9.7% over strong baselines, and achieves a remarkable 37.67% gain during the storm-developing stage -- demonstrating true foresight in sensing storms before they appear. The code can be found in the supplementary material.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24067
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Seeing Inside the Storm: Improving Nowcasting by Integrating Meteorological Drivers
Qiu, Minghui
Chen, Jun
Chen, Lin
Chen, Weifeng
Zhong, Shuxin
Liu, Zhidan
Zhang, Yu
Wu, Kaishun
Atmospheric and Oceanic Physics
Machine Learning
Most nowcasting systems, built on radar reflectivity, focus on current precipitation, ignoring the atmospheric precursors -- such as low-level convergence, turbulent eddies, and latent heating -- that offer a fleeting window to foresee storm birth. We introduce MeteoLogist, a physics-inspired radar intelligence framework that models the full life cycle of convection -- from its precursors to organized storm evolution. However, exploiting these precursors is non-trivial: they originate from multiple meteorological drivers -- thermodynamic, kinematic, and microphysical -- that evolve asynchronously (C1) and remain spatially fragmented (C2). To this end, MeteoLogist designs three tightly integrated components. The Physics-Tailored Encoders process radar echoes according to their intrinsic physical scales and semantics, forming thermodynamic, kinematic, and microphysical streams that capture distinct dynamical regimes. The Temporal-Phase Aligner addresses C1 by leveraging causal temporal attention to capture when and how different drivers interact and activate. The Cross-Field Spatial Aggregator addresses C2 through cross-regional fusion, aligning weak and scattered precursors across neighboring cells to expose upstream triggers and enforce spatial coherence. Evaluated on 3D-NEXRAD (2020--2022, US-wide), MeteoLogist boosts high-impact detection (CSI40) by +9.7% over strong baselines, and achieves a remarkable 37.67% gain during the storm-developing stage -- demonstrating true foresight in sensing storms before they appear. The code can be found in the supplementary material.
title Seeing Inside the Storm: Improving Nowcasting by Integrating Meteorological Drivers
topic Atmospheric and Oceanic Physics
Machine Learning
url https://arxiv.org/abs/2605.24067