TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives

Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis

Keywords: Question-Answering, Knowledge Graph, Geospatial, Temporal, Earth Observation, SPARQL, Language and Learning

TL;DR: A Text-to-SPARQL system that targets Earth Observation archives.

Abstract:

TerraQ is a spatiotemporal question-answering engine for satellite image archives. It is a natural language processing system that is built to process requests for satellite images satisfying certain criteria. The requests can refer to image metadata and entities from a specialized knowledge base (e.g., the Emilia-Romagna region). With it, users can make requests like “Give me a hundred images of rivers near ports in France, with less than 20\% snow coverage and more than 10\% cloud coverage”, thus making Earth Observation data more easily accessible, in-line with the current landscape of digital assistants. This paper will be presented at the 2025 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2025, https://www.2025.ieeeigarss.org/). IGARSS is the premier conference in the Remote Sensing field where, in recent years, much AI-related research for the remote sensing domain appears. It is also available as a preprint (https://www.arxiv.org/abs/2502.04415).

2. Language and Learning

Submission Number: 21