让普通人用自然语言查询气象数据，秒级返回结果。
STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data
- 先解析语义模糊点，再生成精准查询语句。
- 复杂查询执行时间从小时缩短至秒级。
- 专为气象数据设计，适合科研与政策分析者使用。
欧洲联盟的地球观测计划Copernicus产生海量地球观测与气候数据，具有巨大的研究、政策和应用潜力。然而，访问这些数据需具备高级编程技能及对领域特定格式（如NetCDF或GRIB）的熟悉度。通用Text-to-SQL系统在气象领域直接应用时因存在深刻的“符号到数值”鸿沟而失效。为此，我们提出一个面向真实、可扩展气象数据探索的端到端Text-to-SQL框架。系统在生成SQL前，通过自然语言解析解决空间与语义模糊性。我们设计了STRATOS——一种时空解析代理，通过将模糊概念映射到局部本体并利用外部知识库解析空间实体，动态弥合符号到数值的差距。此外，我们的复杂度感知查询重写器重构高开销的空间谓词，使查询执行时间从数小时降至数秒。最后，我们构建了包含7,520个复杂查询对的STRATOS评估工作负载，由领域专家精心设计，用于测试系统在以往未被覆盖的复杂时空维度下的可扩展性与符号到数值转换能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。