S ynoptic B ench : evaluating vision-language models on generating weather forecast discussions of the future
Environmental Data Science · 2026 · 5
DOI: 10.1017/eds.2026.10050 ↗Kurz gefasst
Fachartikel in der Zeitschrift Environmental Data Science, online erschienen am 14.07.2026. Verfasst von Timothy Higgins und 2 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advances in visual-language models (VLMs) have led to significant improvements in a plethora of complex multimodal tasks like image captioning, report generation, and visual perception. However, generating text from meteorological data is highly challenging because the atmosphere is a chaotic system that is rapidly changing at various spatial and temporal scales. Given the complexity of atmospheric phenomena, it is critical to verifiably quantify the effectiveness of existing VLMs on weather forecasting data. In this work, we present S ynoptic B ench , a high-quality dataset consisting of 1,367,041 text samples of Area Forecast Discussions created by the National Weather Service over the continental United States paired to images of 500 mb geopotential height, 2 m temperature, and 850 mb wind velocity in weather forecasts. We also present Synoptic Phenomena Alignment and Coverage Evaluation (S pace ), a novel evaluation framework that can be used to effectively estimate the quality of text descriptions of synoptic weather phenomena. Extensive experiments on generating forecast discussions using state-of-the-art VLMs show the sensitivity of existing evaluation metrics in this domain and enable further exploration into synoptic weather and climate text generation.
Zitieren
APA
Higgins, T., Mamalakis, A., & Agarwal, C. (2026). S ynoptic B ench : evaluating vision-language models on generating weather forecast discussions of the future. Environmental Data Science, 5. https://doi.org/10.1017/eds.2026.10050
Vancouver
Higgins T, Mamalakis A, Agarwal C. S ynoptic B ench : evaluating vision-language models on generating weather forecast discussions of the future. Environmental Data Science. 2026;5. doi:10.1017/eds.2026.10050
BibTeX
@article{Higgins2026,
author = {Higgins, Timothy and Mamalakis, Antonios and Agarwal, Chirag},
title = {S ynoptic B ench : evaluating vision-language models on generating weather forecast discussions of the future},
journal = {Environmental Data Science},
year = {2026},
volume = {5},
doi = {10.1017/eds.2026.10050}
}
EUVIMED