TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives

Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis
2/6/2025
cs.CVcs.AI

No official code found. Best implementation: AI-team-UoA/TerraQ (0 stars, last commit 2025-07-29).

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.

View on arXivView PDF

Code Implementations(1)

AI-team-UoA/TerraQCommunity71%

A spatiotemporal question-answering engine for satellite image archives.

00HTML, PythonJan 26, 20251 years ago

Similar Papers

Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language Model

84% match2026

SAR Strikes Back: A New Hope for RSVQA

83% match2025

Remote Sensing Retrieval-Augmented Generation: Bridging Remote Sensing Imagery and Comprehensive Knowledge with a Multi-Modal Dataset and Retrieval-Augmented Generation Model

82% match2025

ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models

81% match1 repo412024

Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?

81% match2026

DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding

81% match2 repos862025

Cite this paper

@article{kefalidis2025terraq,
  title  = {TerraQ: Spatiotemporal Question-Answering on Satellite Image Archives},
  author = {Sergios-Anestis Kefalidis and Konstantinos Plas and Manolis Koubarakis},
  year   = {2025},
  eprint = {2502.04415},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.04415v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.04415.svg)](https://codeofpaper.com/paper/2502.04415)

Discussion