QueryPlot：使用自然语言查询生成矿产勘探的地质证据层

Mineral prospectivity mapping requires the synthesis of heterogeneous geological knowledge, including textual deposit models and geospatial datasets, to identify regions likely to host specific mineral deposit types. This traditional process is often manual and knowledge-intensive. QueryPlot is a semantic retrieval and mapping framework that integrates large-scale geological text corpora with geological map data using modern Natural Language Processing techniques. The system curates descriptive deposit models for over 120 deposit types and transforms the State Geologic Map Compilation (SGMC) polygons into structured textual representations. Given a user-defined natural language query, the system encodes both queries and region descriptions using a pre-trained model, enabling efficient information retrieval and visualization. This approach significantly enhances the efficiency and accuracy of mineral exploration.