mlsanityData to 14 Oct 2026

T3S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series

arXiv 2506.12885 ↗First posted 15 Jun 2025cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Crop type classification from optical satellite time series remains limited in its ability to generalize across growing seasons, particularly when crop phenology shifts due to inter-annual weather variability. This hampers deployment in operational settings where current-year labels are unavailable. In addition, uncertainty quantification is often overlooked, reducing the reliability of such approaches for practical crop monitoring. Inspired by ecophysiological principles, we introduce Thermal Time-based Temporal Sampling (T3S), a simple, model-agnostic method that replaces calendar time with thermal time. By re-indexing satellite observations by cumulative growing degree days, T3S aligns phenologically equivalent growth stages across years, reducing temporal redundancy while concentrating on the most biologically informative periods. We evaluate T3S across three architecturally distinct backbones on (i) SwissCrop, a new country-scale, multi-year Sentinel-2 dataset with paired temperature data that we publicly release, and (ii) the cross-region TimeMatch benchmark spanning Denmark and France. Across these settings, T3S consistently improves cross-year and cross-region crop classification over several state-of-the-art baselines, including thermal positional encoding, with particularly strong gains in uncertainty calibration, robustness under label scarcity, and early-season prediction, while requiring no architectural modification. Code and dataset are available at https://github.com/moturkoglu/T3S.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 15 Jun 2025.

Builds on

29 of 55 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  7. 2021Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networkscited by 143
  8. 2020Masksembles for Uncertainty Estimationcited by 88
  9. 2019Self-attention for raw optical Satellite Time Series Classificationcited by 75
  10. 2019Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attentioncited by 71
  11. 2018Multi-Temporal Land Cover Classification with Sequential Recurrent Encoderscited by 61
  12. 2023ViTs for SITS: Vision Transformers for Satellite Image Time Seriescited by 56
17 more
  1. 2020Lightweight Temporal Self-Attention for Classifying Satellite Image Time Seriescited by 55
  2. 2025Galileo: Learning Global & Local Features of Many Remote Sensing Modalitiescited by 43
  3. 2021Crop mapping from image time series: deep learning with multi-scale label hierarchiescited by 42
  4. 2019BreizhCrops: A Time Series Dataset for Crop Type Mappingcited by 34
  5. 2022FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulationcited by 24
  6. 2021TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimationcited by 21
  7. 2020Leveraging Class Hierarchies with Metric-Guided Prototype Learningcited by 20
  8. 2024LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networkscited by 20
  9. 2022A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learningcited by 19
  10. 2023Better, Not Just More: Data-Centric Machine Learning for Earth Observationcited by 19
  11. 2022Generalized Classification of Satellite Image Time Series with Thermal Positional Encodingcited by 14
  12. 2020Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equationscited by 12
  13. 2024EuroCropsML: A Time Series Benchmark Dataset For Few-Shot Crop Type Classificationcited by 11
  14. 2023Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approachcited by 8
  15. 2023Boosting Crop Classification by Hierarchically Fusing Satellite, Rotational, and Contextual Datacited by 8
  16. 2024Generalization Enhancement Strategies to Enable Cross-year Cropland Mapping with Convolutional Neural Networks Trained Using Historical Samplescited by 6
  17. 2024SITSMamba for Crop Classification based on Satellite Image Time Seriescited by 4

Built on by

Not cited yet.