STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data

2026-07-03

AI Summary

This study addresses the challenge of bridging the “symbolic-numerical gap” between ambiguous natural language expressions and precise spatiotemporal coordinates in meteorological Text-to-SQL systems, which typically require expert programming to access data sources like Copernicus. To overcome this limitation, the authors propose STRATOS, a novel framework that dynamically resolves vague spatiotemporal references through semantic disambiguation, alignment with external geographic knowledge bases, and ontology mapping. STRATOS further incorporates a complexity-aware query rewriting mechanism to enable efficient and accurate translation from natural language to executable SQL. The work introduces the first expert-annotated evaluation benchmark for meteorology, comprising 7,520 queries, on which STRATOS demonstrates strong effectiveness and scalability in handling complex spatiotemporal queries—reducing response times from hours to seconds.

Abstract

Copernicus, the European Union's Earth observation program, produces petabytes of Earth observation and climate data, offering immense potential for research, policy, and applications. However, access to these datasets requires advanced programming skills and familiarity with domain-specific formats such as NetCDF or GRIB. Moreover, general-purpose Text-to-SQL systems fail when applied naively to the meteorological domain due to a profound ``Symbolic-to-Numeric'' gap. To overcome these limitations, we present an end-to-end Text-to-SQL framework specifically engineered for real-world, scalable meteorological data exploration. Our system intercepts natural language to resolve spatial and semantic ambiguities \textit{before} SQL generation. We design STRATOS, a Spatio-Temporal Resolution Agent for Text-to-SQL to dynamically bridge the symbolic-to-numeric gap by mapping fuzzy concepts to a localized ontology and resolving spatial entities via external knowledge bases. Further, our complexity-aware query rewriter rewrites expensive spatial predicates, reducing execution times from hours to seconds. Last, we introduce the STRATOS Evaluation Workload, comprising 7,520 complex query pairs explicitly designed by domain experts to test scalability and symbolic-to-numeric translation across challenging spatio-temporal dimensions previously unexplored by Text-to-SQL systems.

Problem

• Symbolic-to-Numeric Gap
• Text-to-SQL
• Spatio-Temporal Data
• Meteorological Data
• Semantic Ambiguity

Innovation

• Text-to-SQL
• spatio-temporal reasoning
• symbolic-to-numeric gap
• ontology grounding
• query rewriting