SynopticBench: Evaluating Vision-Language Models on Generating Weather Forecast Discussions of the Future

arXiv:2604.16451v1 Announce Type: new Abstract: 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 SynopticBench, 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 500mb geopotential height, 2 meter temperature, and 850mb wind velocity in weather forecasts. We also present Synoptic Phenomena Alignment and Coverage Evaluation (SPACE), 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.

Related

• Decompose, Look, and Reason: Reinforced Latent Reasoning for VLMs
• GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
• OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
• Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging
• Towards Responsible Multimodal Medical Reasoning via Context-Aligned Vision-Language Models

Source: arXiv cs.CL | 2026-04-21