TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives
This work addresses the challenge of easily accessing and querying satellite image archives for users like researchers or analysts, though it appears incremental as it applies existing NLP methods to a new domain.
The paper tackles the problem of making Earth Observation data more accessible by developing TerraQ, a spatiotemporal question-answering engine for satellite image archives, which processes natural language requests to retrieve images based on criteria like location and coverage, resulting in a system that can handle complex queries such as 'Give me a hundred images of rivers near ports in France, with less than 20% snow coverage and more than 10% cloud coverage'.
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.