Geode: A Zero-shot Geospatial Question-Answering Agent with Explicit Reasoning and Precise Spatio-Temporal Retrieval
Devashish Vikas Gupta, Azeez Syed Ali Ishaqui, Divya Kiran Kadiyala
TL;DR
Geode tackles the challenge of answering geospatial questions that demand real-time, multi-modal data by introducing a zero-shot QA system with explicit reasoning and precise spatio-temporal retrieval. It presents a modular architecture built around a GeoPatch data structure and a geospatial expert pool that orchestrates retrieval, inference, and visualization via an API-driven code-generation loop. The approach integrates diverse data sources (e.g., geocoding, weather, elevation) and provides map-based visual explanations, aiming to outperform prior geo-LLMs in tasks requiring up-to-date spatio-temporal insights. The work's significance lies in enabling accurate, timely geospatial reasoning and insights for applications in planning, monitoring, and safety, with an extensible design that supports adding new data modalities and experts.
Abstract
Large language models (LLMs) have shown promising results in learning and contextualizing information from different forms of data. Recent advancements in foundational models, particularly those employing self-attention mechanisms, have significantly enhanced our ability to comprehend the semantics of diverse data types. One such area that could highly benefit from multi-modality is in understanding geospatial data, which inherently has multiple modalities. However, current Natural Language Processing (NLP) mechanisms struggle to effectively address geospatial queries. Existing pre-trained LLMs are inadequately equipped to meet the unique demands of geospatial data, lacking the ability to retrieve precise spatio-temporal data in real-time, thus leading to significantly reduced accuracy in answering complex geospatial queries. To address these limitations, we introduce Geode--a pioneering system designed to tackle zero-shot geospatial question-answering tasks with high precision using spatio-temporal data retrieval. Our approach represents a significant improvement in addressing the limitations of current LLM models, demonstrating remarkable improvement in geospatial question-answering abilities compared to existing state-of-the-art pre-trained models.