This study presents a semisupervised approach for employing deep learning change detection models to identify vegetation clearance events in arable cropping systems, using bitemporal Sentinel-2 imagery. The resulting change maps are aggregated to estimate the frequency of relevant farming activities (i.e., harvesting, plowing, chemical desiccation, etc.), serving as a proxy for quantifying agricultural intensification. To address the extensive training data requirements of the model architectures, we generate pseudolabels based on rule-based criteria applied to vegetation and soil spectral indices, identifying instances of above-ground biomass removal between image pairs. We explore two training strategies, including fine-tuning pretrained models on a benchmark dataset and training models from scratch, applied in two agricultural regions of central Greece (Larissa and Viotia). Model performance is validated against in-situ and photo-interpretation data, demonstrating robust performance and a detection rate exceeding 85% for harvest events. The most accurate models are then deployed to estimate agricultural intensification over the period 2021–2023. Results reveal high spatial variability in the number of detected changes, indicating differences in land management intensity depending on the region, cultivation year, and crop type. This cost-efficient framework enables scalable monitoring of land use dynamics, offering insights into farmers’ activity patterns and supporting the development of sustainable land management recommendations.
28 July 2025 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Classification of grasslands has an important role in environmental monitoring, and management. This study compares and evaluates the performance of various machine learning and deep learning algorithms in grassland classification using remote sensing data from Sentinel-1 and Sentinel-2 satellites. Sentinel-1 satellite provide Synthetic Aperture Radar data, which captures structural and moisture-related information. Sentinel-2 captures high-resolution optical images with rich spectral details. Both datasets from Sentinel-1 and Sentinel-2 satellites were used to train and evaluate a variety of machine learning models including Random Forest, Support Vector Machines, Logistic Regression, XGBoost and Deep Neural Networks. The results of this study show that Random Forest performs best on Sentinel-1 data and Neural Networks perform best when it comes to grassland classification using Sentinel-2 data. These results show how important it is to select a model based on the characteristics and the nature of the dataset.
Accurate soil moisture (SM) estimation is critical for precision agriculture, water resources management and climate monitoring. Yet, existing satellite SM products are too coarse (>1km) for farm-level applications. We present a high-resolution (10m) SM estimation framework for vegetated areas across Europe, combining Sentinel-1 SAR, Sentinel-2 optical imagery and ERA-5 reanalysis data through machine learning. Using 113 International Soil Moisture Network (ISMN) stations spanning diverse vegetated areas, we compare modality combinations with temporal parameterizations, using spatial cross-validation, to ensure geographic generalization. We also evaluate whether foundation model embeddings from IBM-NASA's Prithvi model improve upon traditional hand-crafted spectral features. Results demonstrate that hybrid temporal matching - Sentinel-2 current-day acquisitions with Sentinel-1 descending orbit - achieves R^2=0.514, with 10-day ERA5 lookback window improving performance to R^2=0.518. Foundation model (Prithvi) embeddings provide negligible improvement over hand-crafted features (R^2=0.515 vs. 0.514), indicating traditional feature engineering remains highly competitive for sparse-data regression tasks. Our findings suggest that domain-specific spectral indices combined with tree-based ensemble methods offer a practical and computationally efficient solution for operational pan-European field-scale soil moisture monitoring.