Zero-Shot Satellite Image Retrieval through Joint Embeddings: Application to Crisis Response

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Walsh, James, Fawcett, William, Colverd, Grace, Ramos-Pollán, Raúl
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911702059057152
author Walsh, James
Fawcett, William
Colverd, Grace
Ramos-Pollán, Raúl
author_facet Walsh, James
Fawcett, William
Colverd, Grace
Ramos-Pollán, Raúl
contents Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imagery but lack the natural-language grounding needed for intuitive query, and full contrastive training of a remote-sensing CLIP-style model requires paired data and compute that are unavailable at global scale. To allow natural language querying at global scales, we present GeoQuery, a zero-shot retrieval system that sidesteps data and compute constraints through a two-stage semantic and visual search, leveraging a natural language embedding of a subset (proxy) of global data. Rather than training a joint encoder, we generate language descriptions for a 100k proxy subset of global Sentinel-2 tiles and optimise the description-generation prompt so that distances in the resulting text-embedding space correlate with distances in the frozen CLAY visual-embedding space. Queries are resolved in two stages, with a text-similarity search over the proxy subset followed by a visual nearest-neighbour search over worldwide CLAY embeddings On 76 disaster-location queries covering UK floods, US wildfires, and US droughts, GeoQuery achieves 31.6\% accuracy within 50\,km, with the strongest performance on floods (50\% within 50\,km) where terrain features are well captured by RGB embeddings. Deployed within a crisis response system called \ECHO{}, GeoQuery identified vulnerable areas during Brisbane's 2025 Cyclone Alfred, with downstream flood simulations reproducing historical patterns. Prompt-aligned proxies offer a practical bridge between EO foundation models and operational retrieval when full contrastive training is out of reach.
format Preprint
id arxiv_https___arxiv_org_abs_2605_05405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Shot Satellite Image Retrieval through Joint Embeddings: Application to Crisis Response
Walsh, James
Fawcett, William
Colverd, Grace
Ramos-Pollán, Raúl
Computer Vision and Pattern Recognition
Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imagery but lack the natural-language grounding needed for intuitive query, and full contrastive training of a remote-sensing CLIP-style model requires paired data and compute that are unavailable at global scale. To allow natural language querying at global scales, we present GeoQuery, a zero-shot retrieval system that sidesteps data and compute constraints through a two-stage semantic and visual search, leveraging a natural language embedding of a subset (proxy) of global data. Rather than training a joint encoder, we generate language descriptions for a 100k proxy subset of global Sentinel-2 tiles and optimise the description-generation prompt so that distances in the resulting text-embedding space correlate with distances in the frozen CLAY visual-embedding space. Queries are resolved in two stages, with a text-similarity search over the proxy subset followed by a visual nearest-neighbour search over worldwide CLAY embeddings On 76 disaster-location queries covering UK floods, US wildfires, and US droughts, GeoQuery achieves 31.6\% accuracy within 50\,km, with the strongest performance on floods (50\% within 50\,km) where terrain features are well captured by RGB embeddings. Deployed within a crisis response system called \ECHO{}, GeoQuery identified vulnerable areas during Brisbane's 2025 Cyclone Alfred, with downstream flood simulations reproducing historical patterns. Prompt-aligned proxies offer a practical bridge between EO foundation models and operational retrieval when full contrastive training is out of reach.
title Zero-Shot Satellite Image Retrieval through Joint Embeddings: Application to Crisis Response
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.05405