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

• URL: http://arxiv.org/abs/2511.23387v1
• Date: Fri, 28 Nov 2025 17:27:06 GMT
• Title: Hierarchical AI-Meteorologist: LLM-Agent System for Multi-Scale and Explainable Weather Forecast Reporting
• Authors: Daniil Sukhorukov, Andrei Zakharov, Nikita Glazkov, Katsiaryna Yanchanka, Vladimir Kirilin, Maxim Dubovitsky, Roman Sultimov, Yuri Maksimov, Ilya Makarov,
• Abstract summary: Hierarchical AI-Meteorologist generates explainable weather reports using a hierarchical forecast reasoning and weather keyword generation.<n>Our framework performs multi-scale reasoning across hourly, 6-hour, and daily aggregations to capture both short-term dynamics and long-term trends.
• Score: 3.0354231393746685
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Agentic Spatio-Temporal Grounding via Collaborative Reasoning [80.83158605034465]
  Temporal Video Grounding aims to retrieve thetemporal tube of a target object or person in a video given a text query.<n>We propose the Agentic Spatio-Temporal Grounder (ASTG) framework for the task of STVG towards an open-world and training-free scenario.<n>Specifically, two specialized agents SRA (Spatial Reasoning Agent) and TRA (Temporal Reasoning Agent) constructed leveraging on modern Multimoal Large Language Models (MLLMs)<n>Experiments on popular benchmarks demonstrate the superiority of the proposed approach where it outperforms existing weakly-supervised and zero-shot approaches by a margin
  arXiv  Detail & Related papers  (2026-02-10T10:16:27Z)
• TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks [12.114998959919978]
  It is unclear whether strong forecasting performance reflects genuine temporal understanding or the ability to reason under contextual and event-driven conditions.<n>We introduce TemporalBench, a multi-domain benchmark designed to evaluate temporal reasoning behavior under progressively richer informational settings.<n>By controlling access to future targets and contextual information, the benchmark enables a diagnostic analysis of whether models can correctly interpret temporal patterns.
  arXiv  Detail & Related papers  (2026-02-05T01:02:19Z)
• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• A Modular LLM-Agent System for Transparent Multi-Parameter Weather Interpretation [3.0354231393746685]
  This paper introduces AI-Meteorologist, an explainable LLM-agent framework that converts raw numerical forecasts into scientifically grounded narrative reports.<n>Unlike conventional forecast outputs presented as dense tables or unstructured time series, our system performs agent-based analysis across multiple meteorological variables.<n>We show how AI-Meteorologist not only communicates weather events but also reveals the underlying atmospheric drivers.
  arXiv  Detail & Related papers  (2025-11-28T22:24:40Z)
• Agentic AI Framework for Cloudburst Prediction and Coordinated Response [0.8697317909540486]
  The paper outlines an agentic artificial intelligence system to study atmospheric water-cycle intelligence.<n>The framework uses autonomous but cooperative agents that reason, sense, and act throughout the entire event lifecycle.<n>It provides a platform of scalable adaptive and learning-based climate resilience.
  arXiv  Detail & Related papers  (2025-11-27T21:33:03Z)
• Adaptive Spatio-Temporal Graphs with Self-Supervised Pretraining for Multi-Horizon Weather Forecasting [3.5137191090796054]
  We propose a self-supervised learning framework that leveragestemporal-temporal structures to improve multi-variable weather prediction.<n>Our approach achieves superior performance compared to traditional numerical prediction weather (NWP) models.<n>The framework provides a scalable and label-efficient solution for future data-driven weather systems.
  arXiv  Detail & Related papers  (2025-10-28T10:52:15Z)
• Zephyrus: An Agentic Framework for Weather Science [47.611521052984365]
  Foundation models for weather science are pre-trained on vast amounts of structured numerical data and outperform traditional weather forecasting systems.<n>Large language models (LLMs) excel at understanding and generating text but cannot reason about high-dimensional meteorological datasets.<n>We bridge this gap by building a novel agentic framework for weather science.<n>We design Zephyrus, a multi-turn LLM-based weather agent that iteratively analyzes weather datasets, observes results, and refines its approach through conversational feedback loops.
  arXiv  Detail & Related papers  (2025-10-05T03:34:08Z)
• RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts [25.396253136103432]
  We introduce an MLLM-based weather forecast analysis method, RadarQA, integrating key physical attributes with detailed assessment reports.<n>We show that RadarQA outperforms existing general MLLMs across all evaluation settings.
  arXiv  Detail & Related papers  (2025-08-17T08:50:07Z)
• Exploring Multimodal AI Reasoning for Meteorological Forecasting from Skew-T Diagrams [4.036372578802888]
  Vision-Language Models (VLMs) have shown promise in other scientific domains, but their application to meteorological diagram interpretation remains largely unexplored.<n>We present a lightweight AI assistant that interprets Skew-T diagrams using a small language model (LM) and a small VLM fine-tuned to emulate human forecasters.
  arXiv  Detail & Related papers  (2025-08-17T01:36:31Z)
• WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning [69.82211470647349]
  We introduce the first generalist weather foundation model (WeatherGFM)<n>It addresses a wide spectrum of weather understanding tasks in a unified manner.<n>Our model can effectively handle up to ten weather understanding tasks, including weather forecasting, super-resolution, weather image translation, and post-processing.
  arXiv  Detail & Related papers  (2024-11-08T09:14:19Z)
• Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection [67.40407388422514]
  We design a conceptual fine-grained causal model named TBN Granger Causality. Second, we propose an end-to-end deep generative model called TacSas, which discovers TBN Granger Causality in a generative manner. We test TacSas on climate benchmark ERA5 for climate forecasting and the extreme weather benchmark of NOAA for extreme weather alerts.
  arXiv  Detail & Related papers  (2024-08-08T06:47:21Z)
• Towards an end-to-end artificial intelligence driven global weather forecasting system [57.5191940978886]
  We present an AI-based data assimilation model, i.e., Adas, for global weather variables. We demonstrate that Adas can assimilate global observations to produce high-quality analysis, enabling the system operate stably for long term. We are the first to apply the methods to real-world scenarios, which is more challenging and has considerable practical application potential.
  arXiv  Detail & Related papers  (2023-12-18T09:05:28Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• Federated Prompt Learning for Weather Foundation Models on Devices [37.88417074427373]
  On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing. This paper propose Federated Prompt Learning for Weather Foundation Models on Devices (FedPoD) FedPoD enables devices to obtain highly customized models while maintaining communication efficiency.
  arXiv  Detail & Related papers  (2023-05-23T16:59:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.