Semi-Automated Reporting from Environmental Monitoring Data Using a Large Language Model-Based Chatbot

Highlights: What are the main findings? MeteoChat, an LLM-based system optimized through fine-tuning and RAG, enables the automatic generation of environmental reports from meteorological datasets. The system reduces report preparation time and limits LLM hallucinations while preserving analytical accuracy and interpretability. What are the implications of the main findings? By reducing human workload, the system enables timely decision-making in environmental monitoring and emergency response contexts. The proposed framework enhances accessibility and reproducibility in environmental data communication and reporting. Producing high-quality analytical reports for the environmental domain is typically time-consuming and requires significant human expertise. This paper describes MeteoChat, a semi-automatic framework for efficiently generating specialized environmental reports from heterogeneous environmental data. MeteoChat utilizes a Large Language Model (LLM) fine-tuned and integrated with Retrieval-Augmented Generation (RAG). The system’s core is its plug-and-play philosophy, which separates analytical reasoning from the data source and the report’s intended audience. The fine-tuning phase uses data-agnostic, parameterized question–context–answer triples defined by an environmental expert to teach the LLM domain-specific analytical logic and audience-appropriate communication styles. Subsequently, the RAG phase integrates the model with actual datasets, which are processed via an Extract–Transform–Load (ETL) workflow to generate statistical summaries. This architectural separation ensures that the same reporting engine can operate on different sources, such as meteorological time series, satellite imagery, or geographical data, without additional training. Users interact with the system via a web-based conversational interface, where responses are tailored for either technical experts (using explicit calculations and tables) or the general public (using simplified, narrative language). MeteoChat has been tested with real data extracted from the micrometeorological network of ARPA Lazio.