Self-Supervised Transformers for Long-Term Prediction of Landsat NDVI Time Series

Ido Faran, Nathan S. Netanyahu, Nathan S. Netanyahu, Elena Roitberg, Maxim Shoshany

2025

Abstract

Long-term satellite image time-series (SITS) analysis presents significant challenges in remote sensing, especially for heterogeneous Mediterranean landscapes, due to complex temporal dependencies, pronounced seasonality, and overarching global trends. We propose Self-Supervised Transformers for Long-Term Prediction (SST-LTP), a novel framework that combines self-supervised learning, temporal embeddings, and a Transformer-based architecture to analyze multi-decade Landsat data. Our approach leverages a self-supervised pretext task to train Transformers on unlabeled data, incorporating temporal embeddings to capture both long-term trends and seasonal variations. This architecture effectively models intricate temporal patterns, enabling accurate predictions of the Normalized Difference Vegetation Index (NDVI) across diverse temporal horizons. Using Landsat data spanning 1984–2024, SST-LTP achieves a Mean Absolute Error (MAE) of 0.0338 and an R2 value of 0.8337, outperforming traditional methods and other neural network architectures. These results highlight SST-LTP as a robust tool for long-term environmental monitoring and analysis.

Paper Citation

in Harvard Style

Faran I., Netanyahu N., Roitberg E. and Shoshany M. (2025). Self-Supervised Transformers for Long-Term Prediction of Landsat NDVI Time Series. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 542-552. DOI: 10.5220/0013381700003905

in Bibtex Style

@conference{icpram25,
author={Ido Faran and Nathan Netanyahu and Elena Roitberg and Maxim Shoshany},
title={Self-Supervised Transformers for Long-Term Prediction of Landsat NDVI Time Series},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={542-552},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013381700003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Self-Supervised Transformers for Long-Term Prediction of Landsat NDVI Time Series
SN - 978-989-758-730-6
AU - Faran I.
AU - Netanyahu N.
AU - Roitberg E.
AU - Shoshany M.
PY - 2025
SP - 542
EP - 552
DO - 10.5220/0013381700003905
PB - SciTePress