BERT Bi-modal self-supervised learning for crop classification using Sentinel-2 and Planetscope
Authors:
Open Access
- 1 May 2025
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Remote Sensing
- Vol. 6, 1555887
Abstract
Crop identification and monitoring of crop dynamics are essential for agricultural planning, environmental monitoring, and ensuring food security. Recent advancements in remote sensing technology and state-of-the-art machine learning have enabled large-scale automated crop classification. However, these methods rely on labeled training data, which requires skilled human annotators or extensive field campaigns, making the process expensive and time-consuming. Self-supervised learning techniques have demonstrated promising results in leveraging large unlabeled datasets across domains. Yet, self-supervised representation learning for crop classification from remote sensing time series remains under-explored due to challenges in curating suitable pretext tasks. While bimodal self-supervised approaches combining data from Sentinel-2 and Planetscope sensors have facilitated pre-training, existing methods primarily exploit the distinct spectral properties of these complementary data sources. In this work, we propose novel self-supervised pre-training strategies inspired from BERT that leverage both the spectral and temporal resolution of Sentinel-2 and Planetscope imagery. We carry out extensive experiments comparing our approach to existing baseline setups across nine test cases, in which our method outperforms the baselines in eight instances. This pre-training thus offers an effective representation of crops for tasks such as crop classification.Keywords
This publication has 35 references indexed in Scilit:
- Bi-modal contrastive learning for crop classification using Sentinel-2 and PlanetscopeFrontiers in Remote Sensing, 2024
- Transformer-based land use and land cover classification with explainability using satellite imageryScientific Reports, 2024
- Early Crop Identification Study Based on Sentinel-1/2 Images with Feature Optimization StrategyAgriculture, 2024
- A Survey on Self-Supervised Learning: Algorithms, Applications, and Future TrendsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Self-Supervised Spatio-Temporal Representation Learning of Satellite Image Time SeriesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024
- Extended Vision Transformer (ExViT) for Land Use and Land Cover Classification: A Multimodal Deep Learning FrameworkIEEE Transactions on Geoscience and Remote Sensing, 2023
- Crop harvests for direct food use insufficient to meet the UN’s food security goalNature Food, 2022
- Emerging Properties in Self-Supervised Vision Transformers2021
- Optuna2019
- Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational ServicesRemote Sensing of Environment, 2012