Intelligent Multimodal Retrieval and Reasoning for Geospatial Knowledge Discovery on the I-GUIDE Platform

2026-06-14

AI Summary

Traditional geospatial information portals lack semantic understanding, provenance tracing, and conversational knowledge synthesis capabilities, hindering efficient knowledge discovery across heterogeneous geoscience resources. This work presents the first production-grade, multimodal retrieval-augmented generation (RAG) system for geoscience applications, developed on the I-GUIDE platform. The system integrates keyword, vector, spatial indexing, and a Neo4j knowledge graph, and introduces a memory-aware iterative RAG framework featuring novel spatially aware retrieval routing, a refusal evaluation mechanism, and a human-in-the-loop interface. Optimized with OpenSearch and large language model (LLM) invocation, the system supports over 100 concurrent users (4.4 requests per second) on a single A100 GPU and significantly outperforms baseline approaches across 170 human-evaluated queries, particularly improving evidence coverage and answer quality in tasks involving precise entity identification, spatial constraints, and domain-specific factual reasoning.

Abstract

Geospatial knowledge discovery increasingly requires search across heterogeneous artifacts: datasets, maps, notebooks, software, publications, and the provenance links among them. Conventional geoportals support metadata and spatial filtering, but they rarely provide semantic retrieval, graph-aware provenance traversal, and conversational synthesis in one integrated system. This paper presents I-GUIDE Smart Search, a production multimodal geospatial retrieval-augmented generation (RAG) system embedded in the I-GUIDE Platform, and reports on its design, deployment, and evaluation. The system combines production-maintained OpenSearch keyword, vector, and spatial indexes with a Neo4j knowledge graph and an iterative RAG pipeline for memory-aware query augmentation, reasoning, retrieval-method routing, relevance grading, grounded generation, hallucination and relevance checking. In a single-A100 RAG deployment, I-GUIDE Smart Search supports interactive use up to about 100 concurrent simulated users, reaching 4.4 requests per second with p50 latency near 25 seconds despite 20-50 LLM calls per query. For answer quality, we evaluate a four-category benchmark of 170 unique human-filtered user-facing queries, together with ten intent-specific probe sets generated from the deployed indexes and graph. Smart Search improves retrieved evidence coverage and judged answer quality over non-retrieval and naive-RAG baselines, with the clearest gains on exact-identifier, spatially constrained, simple-recommendation, and domain-specific factual queries requiring current indexed evidence. We distill transferable deployment lessons for spatial RAG systems, covering spatial metadata quality, graph provenance, retrieval routing, interface contracts, refusal-aware evaluation, latency-cost tradeoffs, and the role of the user interface in deployed geospatial cyberinfrastructure.

Problem

• geospatial knowledge discovery
• multimodal retrieval
• semantic search
• provenance traversal
• conversational synthesis

Innovation

• multimodal retrieval
• retrieval-augmented generation (RAG)
• geospatial knowledge graph
• spatial indexing
• provenance-aware reasoning