# Generalized Classification of Satellite Image Time Series with Thermal Positional Encoding

arXiv: https://arxiv.org/abs/2203.09175 · HTML: https://mlsanity.com/paper/2203.09175/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 65 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks](https://mlsanity.com/paper/2107.07933/) (2021)
- [Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding](https://mlsanity.com/paper/2106.02795/) (2021)
- [Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series](https://mlsanity.com/paper/1811.10166/) (2018)
- [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)
- [Recent Advances in Domain Adaptation for the Classification of Remote Sensing Data](https://mlsanity.com/paper/2104.07778/) (2021)
- [Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders](https://mlsanity.com/paper/1802.02080/) (2018)
- [Learning to Encode Position for Transformer with Continuous Dynamical Model](https://mlsanity.com/paper/2003.09229/) (2020)
- [Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series](https://mlsanity.com/paper/2007.00586/) (2020)
- [TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation](https://mlsanity.com/paper/2111.02682/) (2021)
- [Land Cover Classification via Multi-temporal Spatial Data by Recurrent Neural Networks](https://mlsanity.com/paper/1704.04055/) (2017)
- [DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn](https://mlsanity.com/paper/1809.07589/) (2018)
- [EuroCrops: A Pan-European Dataset for Time Series Crop Type Classification](https://mlsanity.com/paper/2106.08151/) (2021)
- [Resilient In-Season Crop Type Classification in Multispectral Satellite Observations using Growth Stage Normalization](https://mlsanity.com/paper/2009.10189/) (2020)

## Built on by (most cited first, 14 of 14)

- [Deep Learning for Satellite Image Time Series Analysis: A Review](https://mlsanity.com/paper/2404.03936/) (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)
- [Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting](https://mlsanity.com/paper/2212.08208/) (2022)
- [Revisiting the Encoding of Satellite Image Time Series](https://mlsanity.com/paper/2305.02086/) (2023)
- [Satellite Image Time Series Semantic Change Detection: Novel Architecture and Analysis of Domain Shift](https://mlsanity.com/paper/2407.07616/) (2024)
- [Paving the way toward foundation models for irregular and unaligned Satellite Image Time Series](https://mlsanity.com/paper/2407.08448/) (2024)
- [Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data](https://mlsanity.com/paper/2402.00743/) (2024)
- [Self-supervised learning -- A way to minimize time and effort for precision agriculture?](https://mlsanity.com/paper/2204.02100/) (2022)
- [SwissCrop25: A National Multi-Year Benchmark for Operational Crop Mapping](https://mlsanity.com/paper/2608.09497/) (2026)
- [On the use of Graphs for Satellite Image Time Series](https://mlsanity.com/paper/2505.16685/) (2025)
- [T3S: Think in Thermal Time for Generalizable Crop Mapping from Satellite Image Time Series](https://mlsanity.com/paper/2506.12885/) (2025)
- [PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction](https://mlsanity.com/paper/2605.23478/) (2026)
- [SPEAR NeXT Causal Latent Forecasting Across Multiple Horizons for Spectral Temporal Earth Representation Learning](https://mlsanity.com/paper/2609.16871/) (2026)

## Abstract (arXiv)

Large-scale crop type classification is a task at the core of remote sensing efforts with applications of both economic and ecological importance. Current state-of-the-art deep learning methods are based on self-attention and use satellite image time series (SITS) to discriminate crop types based on their unique growth patterns. However, existing methods generalize poorly to regions not seen during training mainly due to not being robust to temporal shifts of the growing season caused by variations in climate. To this end, we propose Thermal Positional Encoding (TPE) for attention-based crop classifiers. Unlike previous positional encoding based on calendar time (e.g. day-of-year), TPE is based on thermal time, which is obtained by accumulating daily average temperatures over the growing season. Since crop growth is directly related to thermal time, but not calendar time, TPE addresses the temporal shifts between different regions to improve generalization. We propose multiple TPE strategies, including learnable methods, to further improve results compared to the common fixed positional encodings. We demonstrate our approach on a crop classification task across four different European regions, where we obtain state-of-the-art generalization results.