Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis

About

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.

Zhengpeng Feng, Clement Atzberger, Sadiq Jaffer, Jovana Knezevic, Silja Sormunen, Robin Young, Madeline C. Lisaius, Markus Immitzer, Toby Jackson, James Ball, David A. Coomes, Anil Madhavapeddy, Andrew Blake, Srinivasan Keshav• 2025

Related benchmarks

TaskDatasetResultRank
ClassificationTreeSatAI-TS
F1 Score77.96
75
RegressionBorneo CHM (1% labels)
RMSE34.82
25
RegressionBorneo CHM (30% labels)
RMSE15.18
25
RegressionBorneo CHM (All labels)
RMSE12.21
25
Semantic segmentationAustrian Crop (1% labels)
mIoU28.2
25
Semantic segmentationAustrian Crop (30% labels)
mIoU48.29
25
Semantic segmentationAustrian Crop All labels
mIoU53.12
25
RegressionBiomassters (1% labels)
RMSE32.5
24
RegressionBiomassters (30% labels)
RMSE29.15
24
RegressionBiomassters (All labels)
RMSE27.43
24
Showing 10 of 23 rows

Other info

Follow for update