WaveOp-LiteFM is proposed, a lightweight neural operator flow matching framework for S2R retrieval that achieves state-of-the-art retrieval performance while substantially reducing computational costs and large-area inference over China demonstrates that WaveOp-LiteFM maintains reliable retrieval quality in large-scale...
The proposed PrecipJEPA couples a structured forecasting path with an auxiliary path that enriches its encoder from observed radar history, which improves highest-threshold CSI over the strongest baselines, while maintaining the highest mean CSI throughout the 3-hour forecast.
Yu-Feng Zhu, Dan Niu, Qi-Liang Wu et al.· 0 citations
WeatherDiagFlow connects numerical prediction, evidence-grounded reporting, and auditable verification under a leakage-controlled protocol to formulate radar nowcasting as an evidence-grounded forecast--bulletin--audit task, in which a numerical forecaster produces both future radar fields and structured diagnostic evi...
Chun-Lei Shi, Yu-Feng Zhu, Yi-Xiao Liang et al.· 0 citations
The Continuous Spatiotemporal Temperature Forecaster (CSTF) is proposed, a neural field that turns forecast lead time and output resolution into explicit queries when evaluating 2-m temperature (T2M) and achieves the best aggregate deterministic skill.
Chun-Lei Shi, Jiong Wang, Yilin Wei et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.