Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting

TL;DR

This paper introduces a hierarchical LLM-based system for weather reporting that improves interpretability and robustness by multi-scale reasoning and keyword validation, enabling coherent and explainable meteorological narratives.

Contribution

It presents a novel hierarchical framework for weather report generation that integrates multi-scale reasoning and keyword validation for enhanced interpretability and factual consistency.

Findings

Hierarchical reasoning improves report coherence.

Keyword validation enhances factual accuracy.

System outperforms flat models in interpretability.

Abstract

We present the Hierarchical AI-Meteorologist, an LLM-agent system that generates explainable weather reports using a hierarchical forecast reasoning and weather keyword generation. Unlike standard approaches that treat forecasts as flat time series, our framework performs multi-scale reasoning across hourly, 6-hour, and daily aggregations to capture both short-term dynamics and long-term trends. Its core reasoning agent converts structured meteorological inputs into coherent narratives while simultaneously extracting a few keywords effectively summarizing the dominant meteorological events. These keywords serve as semantic anchors for validating consistency, temporal coherence and factual alignment of the generated reports. Using OpenWeather and Meteostat data, we demonstrate that hierarchical context and keyword-based validation substantially improve interpretability and robustness of LLM-generated weather narratives, offering a reproducible framework for semantic evaluation of automated meteorological reporting and advancing agent-based scientific reasoning.