A Modular LLM-Agent System for Transparent Multi-Parameter Weather Interpretation
Daniil Sukhorukov, Andrei Zakharov, Nikita Glazkov, Katsiaryna Yanchanka, Vladimir Kirilin, Maxim Dubovitsky, Roman Sultimov, Yuri Maksimov, Ilya Makarov
TL;DR
Weather forecasts are translated into interpretable narratives with explainable reasoning. The paper introduces AI-Meteorologist, a modular LLM-agent framework that converts structured forecast data into causal, narrative bulletins using in-context prompting without fine-tuning. It demonstrates the approach on multi-location data, showing detection of fronts and anomalies, with explicit reasoning and confidence assessments. The work suggests extensions to multilingual support, ensemble data, and self-refinement loops to enhance reliability and usefulness for meteorologists and climate analytics.
Abstract
Weather forecasting is not only a predictive task but an interpretive scientific process requiring explanation, contextualization, and hypothesis generation. This paper introduces AI-Meteorologist, an explainable LLM-agent framework that converts raw numerical forecasts into scientifically grounded narrative reports with transparent reasoning steps. Unlike conventional forecast outputs presented as dense tables or unstructured time series, our system performs agent-based analysis across multiple meteorological variables, integrates historical climatological context, and generates structured explanations that identify weather fronts, anomalies, and localized dynamics. The architecture relies entirely on in-context prompting, without fine-tuning, demonstrating that interpretability can be achieved through reasoning rather than parameter updates. Through case studies on multi-location forecast data, we show how AI-Meteorologist not only communicates weather events but also reveals the underlying atmospheric drivers, offering a pathway toward AI systems that augment human meteorological expertise and support scientific discovery in climate analytics.