# WeatherQA: Can Multimodal Language Models Reason about Severe Weather?

arXiv: https://arxiv.org/abs/2406.11217 · HTML: https://mlsanity.com/paper/2406.11217/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 17 Jun 2024.

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [FuXi: A cascade machine learning forecasting system for 15-day global weather forecast](https://mlsanity.com/paper/2306.12873/) (2023)
- [CLIMATE-FEVER: A Dataset for Verification of Real-World Climate Claims](https://mlsanity.com/paper/2012.00614/) (2020)
- [FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead](https://mlsanity.com/paper/2304.02948/) (2023)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models](https://mlsanity.com/paper/2404.07973/) (2024)
- [ClimateBert: A Pretrained Language Model for Climate-Related Text](https://mlsanity.com/paper/2110.12010/) (2021)
- [ACE: A fast, skillful learned global atmospheric model for climate prediction](https://mlsanity.com/paper/2310.02074/) (2023)
- [ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change](https://mlsanity.com/paper/2401.09646/) (2024)
- [Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey](https://mlsanity.com/paper/2312.03014/) (2023)
- [On the Foundations of Earth and Climate Foundation Models](https://mlsanity.com/paper/2405.04285/) (2024)
- [chatClimate: Grounding Conversational AI in Climate Science](https://mlsanity.com/paper/2304.05510/) (2023)
- [ClimaText: A Dataset for Climate Change Topic Detection](https://mlsanity.com/paper/2012.00483/) (2020)
- [ClimateBERT-NetZero: Detecting and Assessing Net Zero and Reduction Targets](https://mlsanity.com/paper/2310.08096/) (2023)
- [Towards Answering Climate Questionnaires from Unstructured Climate Reports](https://mlsanity.com/paper/2301.04253/) (2023)

## Built on by (most cited first, 22 of 22)

- [Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models](https://mlsanity.com/paper/2501.14818/) (2025)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning](https://mlsanity.com/paper/2506.10521/) (2025)
- [LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding](https://mlsanity.com/paper/2605.27365/) (2026)
- [CLLMate: A Multimodal Benchmark for Weather and Climate Events Forecasting](https://mlsanity.com/paper/2409.19058/) (2024)
- [OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data](https://mlsanity.com/paper/2505.23522/) (2025)
- [MSEarth: A Multimodal Benchmark for Earth Science Phenomenon Discovery with MLLMs](https://mlsanity.com/paper/2505.20740/) (2025)
- [Zephyrus: An Agentic Framework for Weather Science](https://mlsanity.com/paper/2510.04017/) (2025)
- [RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts](https://mlsanity.com/paper/2508.12291/) (2025)
- [LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight](https://mlsanity.com/paper/2511.20648/) (2025)
- [A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation](https://mlsanity.com/paper/2504.17200/) (2025)
- [TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?](https://mlsanity.com/paper/2606.13148/) (2026)
- [Domain Specific Benchmarks for Evaluating Multimodal Large Language Models](https://mlsanity.com/paper/2506.12958/) (2025)
- [MeteorPred: A Meteorological Multimodal Large Model and Dataset for Severe Weather Event Prediction](https://mlsanity.com/paper/2508.06859/) (2025)
- [Omni-Weather: A Unified Multimodal Model for Weather Radar Understanding and Generation](https://mlsanity.com/paper/2512.21643/) (2025)
- [Charting Empirical Laws for LLM Fine-Tuning in Scientific Multi-Discipline Learning](https://mlsanity.com/paper/2602.11215/) (2026)
- [SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents](https://mlsanity.com/paper/2607.24588/) (2026)
- [WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report Generation](https://mlsanity.com/paper/2605.07522/) (2026)
- [S2SServiceBench: A Multimodal Benchmark for Last-Mile S2S Climate Services](https://mlsanity.com/paper/2602.14017/) (2026)
- [K-MetBench: A Multi-Dimensional Benchmark for Fine-Grained Evaluation of Expert Reasoning, Locality, and Multimodality in Meteorology](https://mlsanity.com/paper/2604.24645/) (2026)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)
- [EarthAlign: Learning Language-Aligned Representations of Earth System Data](https://mlsanity.com/paper/2610.14624/) (2026)

## Abstract (arXiv)

Severe convective weather events, such as hail, tornadoes, and thunderstorms, often occur quickly yet cause significant damage, costing billions of dollars every year. This highlights the importance of forecasting severe weather threats hours in advance to better prepare meteorologists and residents in at-risk areas. Can modern large foundation models perform such forecasting? Existing weather benchmarks typically focus only on predicting time-series changes in certain weather parameters (e.g., temperature, moisture) with text-only features. In this work, we introduce WeatherQA, the first multimodal dataset designed for machines to reason about complex combinations of weather parameters (a.k.a., ingredients) and predict severe weather in real-world scenarios. The dataset includes over 8,000 (multi-images, text) pairs for diverse severe weather events. Each pair contains rich information crucial for forecasting -- the images describe the ingredients capturing environmental instability, surface observations, and radar reflectivity, and the text contains forecast analyses written by human experts. With WeatherQA, we evaluate state-of-the-art vision language models, including GPT4, Claude3.5, Gemini-1.5, and a fine-tuned Llama3-based VLM, by designing two challenging tasks: (1) multi-choice QA for predicting affected area and (2) classification of the development potential of severe convection. These tasks require deep understanding of domain knowledge (e.g., atmospheric dynamics) and complex reasoning over multimodal data (e.g., interactions between weather parameters). We show a substantial gap between the strongest VLM, GPT4o, and human reasoning. Our comprehensive case study with meteorologists further reveals the weaknesses of the models, suggesting that better training and data integration are necessary to bridge this gap. WeatherQA link: https://github.com/chengqianma/WeatherQA.