STRATOS：弥合气象数据时空 Text-to-SQL 的符号到数值鸿沟

View PDF HTML (experimental)

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.

Comments:	12 pages, 5 figures
Subjects:	Databases (cs.DB); Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA)
ACM classes:	H.2.8; I.2.7; J.2
Cite as:	arXiv:2607.03501 [cs.DB]
	(or arXiv:2607.03501v2 [cs.DB] for this version)
	https://doi.org/10.48550/arXiv.2607.03501 arXiv-issued DOI via DataCite

Submission history

From: Yi Zhang [view email]
[v1] Fri, 3 Jul 2026 17:15:24 UTC (699 KB)
[v2] Wed, 11 Nov 2026 13:45:48 UTC (901 KB)