Conditional GAN–Based NDVI Estimation From Multi-Frequency SAR Data in Forest Ecosystems
IEEE Geoscience and Remote Sensing Letters, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1109/lgrs.2026.3705303
- Dergi Adı: IEEE Geoscience and Remote Sensing Letters
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Compendex, Geobase, INSPEC, Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: adversarial deep learning, ALOS-2 PALSAR-2, forest phenology, SAR data fusion, Sentinel-1
- Hacettepe Üniversitesi Adresli: Evet
Özet
The combined use of remote sensing satellite imagery, particularly the extraction of optical data from Synthetic Aperture Radar (SAR) data to fill gaps, is used to overcome the disadvantages of optical data in temporal analysis. This study investigates the contribution of multi-frequency SAR data to the estimation of optical data within this context. This letter presents a SAR-based framework for estimating Sentinel-2 NDVI by fusing C-band Sentinel-1 and L-band ALOS-2 PALSAR-2 data over a heterogeneous forest ecosystem. Three machine learning approaches—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and a Conditional Generative Adversarial Network (cGAN)—were comparatively evaluated. A compact feature set derived from multi-polarization and multi-frequency SAR observations was selected to represent canopy structure. Results demonstrate that the cGAN significantly outperforms ensemble tree-based models, achieving an R2 of 0.95 and an MAE of 0.0031, while RF and XGBoost yielded R2 values below 0.55. The findings indicate that adversarial learning effectively captures the complex, nonlinear relationship between SAR backscatter and NDVI, enabling reliable all-weather vegetation monitoring in structurally complex forest environments.