March 10, 2026 by University of California – San Diego
Collected at: https://phys.org/news/2026-03-ai-agent-scientists-weather-climate.html
Computer scientists and weather scientists have taken the first steps toward creating an AI agent capable of analyzing and answering questions in natural language, such as English, about data from AI-driven weather and climate forecasting models. The research team from the University of California San Diego will present the first AI weather agent they developed, named Zephyrus, at the 14th International Conference on Learning Representations (ICLR) from April 23–27 in Rio de Janeiro. The research is published on the arXiv preprint server.
Recently, models driven by AI and deep learning have considerably improved weather forecasting. But analyzing the resulting data remains difficult and time-consuming. A main issue is that these types of AI models are not able to describe their findings in plain language. A secondary issue is that these models are not able to reason about text information, such as meteorology reports and weather bulletins. The UC San Diego research team aims to address both.
“Our goal is to increase access to critical data and predictions by lowering the barrier to entry to analyzing these data,” said Duncan Watson-Parris, a study co-author and faculty member at the UC San Diego Scripps Institution of Oceanography. “We want to increase the speed with which we can reason about multimodal data and learn about Earth by making it easier for students and young scientists to interact with different datasets.”
The researchers also hope the findings will lead to AI agents that will be able to bring similar advances to other disciplines, especially climate science. Meteorology was a perfect test case because it combines large, complex datasets that change over time and the need to reason about these data in plain language.
“Weather prediction is a critical scientific challenge, with profound implications spanning agriculture, disaster preparedness, transportation, and energy management,” the researchers write.
To bridge the gap between a code-driven AI model and a language-based AI agent, the researchers set up an environment that allows the agents to interact with weather models and data via code. The AI agent is capable of handling language-based queries, translating them into code, and then translating the code-generated answers into plain language.
Zephyrus performed well on simple tasks, such as finding locations with specific weather conditions, as well as weather forecasts for specific locations at certain times. But it struggles with finding locations with extreme weather and report generation. Researchers tested four frontier LLMs to power Zephyrus, and all performed with similar accuracy.
For the next iteration of the AI agent, researchers plan to use larger training datasets. Next steps also include fine-tuning open-source models for climate-focused tasks.
“Our vision is to democratize earth science. Zephyrus is a crucial step toward creating AI co-scientists that dramatically lower the barrier to entry, allowing students and researchers everywhere to access and reason about critical weather and climate data at unprecedented speeds,” said Rose Yu, study co-author and a faculty member in the UC San Diego Department of Computer Science and Engineering.
Publication details
Sumanth Varambally et al, Zephyrus: An Agentic Framework for Weather Science, arXiv (2025). DOI: 10.48550/arxiv.2510.04017
Journal information: arXiv
Leave a Reply