Jando93/SINTETIC_logging_detection: SINTETIC - Satellite alert system against illegal logging

The proposed approach - developed in the framework of the EU Horizon Project SINTETIC - supports periodic detection of forest anomalies potentially related to logging activities through the integration of multi-sensor satellite time series. The methodology combines Sentinel‑2 multispectral (MS) imagery and Sentinel‑1 Synthetic Aperture Radar (SAR) data to exploit their complementary sensitivity to canopy condition and forest structural changes. Disturbances are identified as statistically and/or physically meaningful deviations from expected vegetation state and canopy structure, derived from spectral indices and SAR backscatter change metrics. The analysis is based on a systematic comparison between current observations and a multi-year historical baseline, designed to represent the expected seasonal and structural variability of vegetation and land-surface conditions. Outputs are generated automatically at a configurable temporal frequency. In the current configuration, the system operates on a weekly cycle, producing disturbance indicators and alert layers at 7‑day intervals. The complete workflow was implemented in Google Earth Engine (GEE) using the Python API, enabling scalable access to multi-temporal Copernicus archives and efficient processing over large forested areas. The processing chain follows a semi-automatic architecture in which satellite observations are periodically ingested, composited, masked, and transformed into spatially explicit disturbance metrics (including temporal compositing, change detection logic, and object-based segmentation), as described in the dedicated methodological sections. The resulting alert products and associated metadata are then intended to be integrated into the WP3 geodatabase, ensuring harmonized storage within SINTETIC project system.

For this application, please refer to:

De Luca, G. et al. (2026). Towards Semi-automatic Detection of Illegal Logging: Integrating Optical and SAR Satellite Imagery with StanForD Field-Machine Data. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2025 Workshops. ICCSA 2025. Lecture Notes in Computer Science, vol 15899. Springer, Cham. https://doi.org/10.1007/978-3-031-97663-6_36