How to Embed Matters: Evaluation of EO Embedding Design Choices

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gilch, Luis, Wittmann, Isabelle, Nitsche, Maximilian, Jakubik, Johannes, Ewald, Arne, Brunschwiler, Thomas
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918434191704064
author Gilch, Luis
Wittmann, Isabelle
Nitsche, Maximilian
Jakubik, Johannes
Ewald, Arne
Brunschwiler, Thomas
author_facet Gilch, Luis
Wittmann, Isabelle
Nitsche, Maximilian
Jakubik, Johannes
Ewald, Arne
Brunschwiler, Thomas
contents Earth observation (EO) missions produce petabytes of multispectral imagery, increasingly analyzed using large Geospatial Foundation Models (GeoFMs). Alongside end-to-end adaptation, workflows make growing use of intermediate representations as task-agnostic embeddings, enabling models to compute representations once and reuse them across downstream tasks. Consequently, when GeoFMs act as feature extractors, decisions about how representations are obtained, aggregated, and combined affect downstream performance and pipeline scalability. Understanding these trade-offs is essential for scalable embedding-based EO workflows, where compact embeddings can replace raw data while remaining broadly useful. We present a systematic analysis of embedding design in GeoFM-based EO workflows. Leveraging NeuCo-Bench, we study how backbone architecture, pretraining strategy, representation depth, spatial aggregation, and representation combination influence EO task performance. We demonstrate the usability of GeoFM embeddings by aggregating them into fixed-size representations more than 500x smaller than the raw input data. Across models, we find consistent trends: transformer backbones with mean pooling provide strong default embeddings, intermediate ResNet layers can outperform final layers, self-supervised objectives exhibit task-specific strengths, and combining embeddings from different objectives often improves robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10658
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How to Embed Matters: Evaluation of EO Embedding Design Choices
Gilch, Luis
Wittmann, Isabelle
Nitsche, Maximilian
Jakubik, Johannes
Ewald, Arne
Brunschwiler, Thomas
Computer Vision and Pattern Recognition
Earth observation (EO) missions produce petabytes of multispectral imagery, increasingly analyzed using large Geospatial Foundation Models (GeoFMs). Alongside end-to-end adaptation, workflows make growing use of intermediate representations as task-agnostic embeddings, enabling models to compute representations once and reuse them across downstream tasks. Consequently, when GeoFMs act as feature extractors, decisions about how representations are obtained, aggregated, and combined affect downstream performance and pipeline scalability. Understanding these trade-offs is essential for scalable embedding-based EO workflows, where compact embeddings can replace raw data while remaining broadly useful. We present a systematic analysis of embedding design in GeoFM-based EO workflows. Leveraging NeuCo-Bench, we study how backbone architecture, pretraining strategy, representation depth, spatial aggregation, and representation combination influence EO task performance. We demonstrate the usability of GeoFM embeddings by aggregating them into fixed-size representations more than 500x smaller than the raw input data. Across models, we find consistent trends: transformer backbones with mean pooling provide strong default embeddings, intermediate ResNet layers can outperform final layers, self-supervised objectives exhibit task-specific strengths, and combining embeddings from different objectives often improves robustness.
title How to Embed Matters: Evaluation of EO Embedding Design Choices
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.10658