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

arXiv: https://arxiv.org/abs/2506.12885 · HTML: https://mlsanity.com/paper/2506.12885/

## 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 (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Masksembles for Uncertainty Estimation](https://mlsanity.com/paper/2012.08334/) (2020)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [Satellite Image Time Series Classification with Pixel-Set Encoders and Temporal Self-Attention](https://mlsanity.com/paper/1911.07757/) (2019)
- [Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders](https://mlsanity.com/paper/1802.02080/) (2018)
- [ViTs for SITS: Vision Transformers for Satellite Image Time Series](https://mlsanity.com/paper/2301.04944/) (2023)
- [Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series](https://mlsanity.com/paper/2007.00586/) (2020)
- [Galileo: Learning Global & Local Features of Many Remote Sensing Modalities](https://mlsanity.com/paper/2502.09356/) (2025)
- [Crop mapping from image time series: deep learning with multi-scale label hierarchies](https://mlsanity.com/paper/2102.08820/) (2021)
- [BreizhCrops: A Time Series Dataset for Crop Type Mapping](https://mlsanity.com/paper/1905.11893/) (2019)
- [FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation](https://mlsanity.com/paper/2206.00050/) (2022)
- [TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation](https://mlsanity.com/paper/2111.02682/) (2021)
- [Leveraging Class Hierarchies with Metric-Guided Prototype Learning](https://mlsanity.com/paper/2007.03047/) (2020)
- [LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks](https://mlsanity.com/paper/2405.14438/) (2024)
- [A Sentinel-2 multi-year, multi-country benchmark dataset for crop classification and segmentation with deep learning](https://mlsanity.com/paper/2204.00951/) (2022)
- [Better, Not Just More: Data-Centric Machine Learning for Earth Observation](https://mlsanity.com/paper/2312.05327/) (2023)
- [Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding](https://mlsanity.com/paper/2203.09175/) (2022)
- [Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations](https://mlsanity.com/paper/2012.02542/) (2020)
- [EuroCropsML: A Time Series Benchmark Dataset For Few-Shot Crop Type Classification](https://mlsanity.com/paper/2407.17458/) (2024)
- [Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach](https://mlsanity.com/paper/2303.12533/) (2023)
- [Boosting Crop Classification by Hierarchically Fusing Satellite, Rotational, and Contextual Data](https://mlsanity.com/paper/2305.12011/) (2023)
- [Generalization Enhancement Strategies to Enable Cross-year Cropland Mapping with Convolutional Neural Networks Trained Using Historical Samples](https://mlsanity.com/paper/2408.06467/) (2024)
- [SITSMamba for Crop Classification based on Satellite Image Time Series](https://mlsanity.com/paper/2409.09673/) (2024)

## 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.