Saved in:
Bibliographic Details
Main Authors: Feng, Zhengpeng, Atzberger, Clement, Jaffer, Sadiq, Knezevic, Jovana, Sormunen, Silja, Young, Robin, Lisaius, Madeline C., Immitzer, Markus, Jackson, Toby, Ball, James, Coomes, David A., Madhavapeddy, Anil, Blake, Andrew, Keshav, Srinivasan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.20380
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915932603940864
author Feng, Zhengpeng
Atzberger, Clement
Jaffer, Sadiq
Knezevic, Jovana
Sormunen, Silja
Young, Robin
Lisaius, Madeline C.
Immitzer, Markus
Jackson, Toby
Ball, James
Coomes, David A.
Madhavapeddy, Anil
Blake, Andrew
Keshav, Srinivasan
author_facet Feng, Zhengpeng
Atzberger, Clement
Jaffer, Sadiq
Knezevic, Jovana
Sormunen, Silja
Young, Robin
Lisaius, Madeline C.
Immitzer, Markus
Jackson, Toby
Ball, James
Coomes, David A.
Madhavapeddy, Anil
Blake, Andrew
Keshav, Srinivasan
contents Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information with respect to vegetation phenology, which is critical for many downstream tasks. Instead, we present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) EO time series that learns robust, label-efficient embeddings. During model training, TESSERA uses Barlow Twins and sparse random temporal sampling to enforce invariance to the selection of valid observations. We employ two key regularizers: global shuffling to decorrelate spatial neighborhoods and mix-based regulation to improve invariance under extreme sparsity. We find that for diverse classification, segmentation, and regression tasks, TESSERA embeddings deliver state-of-the-art accuracy with high label efficiency, often requiring only a small task head and minimal computation. To democratize access, adhere to FAIR - principles, and simplify use, we release global, annual, 10m, pixel-wise int8 embeddings together with open weights/code and lightweight adaptation heads, thus providing practical tooling for large-scale retrieval and inference at planetary scale. All code and data are available at: https://github.com/ucam-eo/tessera.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20380
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
Feng, Zhengpeng
Atzberger, Clement
Jaffer, Sadiq
Knezevic, Jovana
Sormunen, Silja
Young, Robin
Lisaius, Madeline C.
Immitzer, Markus
Jackson, Toby
Ball, James
Coomes, David A.
Madhavapeddy, Anil
Blake, Andrew
Keshav, Srinivasan
Machine Learning
Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction. Compositing addresses these issues but loses information with respect to vegetation phenology, which is critical for many downstream tasks. Instead, we present TESSERA, a pixel-wise foundation model for multi-modal (Sentinel-1/2) EO time series that learns robust, label-efficient embeddings. During model training, TESSERA uses Barlow Twins and sparse random temporal sampling to enforce invariance to the selection of valid observations. We employ two key regularizers: global shuffling to decorrelate spatial neighborhoods and mix-based regulation to improve invariance under extreme sparsity. We find that for diverse classification, segmentation, and regression tasks, TESSERA embeddings deliver state-of-the-art accuracy with high label efficiency, often requiring only a small task head and minimal computation. To democratize access, adhere to FAIR - principles, and simplify use, we release global, annual, 10m, pixel-wise int8 embeddings together with open weights/code and lightweight adaptation heads, thus providing practical tooling for large-scale retrieval and inference at planetary scale. All code and data are available at: https://github.com/ucam-eo/tessera.
title TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
topic Machine Learning
url https://arxiv.org/abs/2506.20380