Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran)

Combining Sentinel-2A optical imagery with ALOS-2 PALSAR-2 radar data significantly improves the accuracy of estimating forest aboveground biomass (AGB) compared to using either dataset alone. A case study in Iran’s Hyrcanian Forest demonstrated that Support Vector Regression (SVR) models, when trained on combined Sentinel-ALOS datasets, achieved the highest prediction accuracy (R² = 0.73, RMSE = 38.68), outperforming Gaussian Processes (GP), Random Forests (RF), and Multi-Layer Perceptron Neural Networks (MPL). While Sentinel-2A alone provided reasonable results, ALOS-2 PALSAR-2 data yielded poor performance when used independently. This study highlights the potential of integrating multi-sensor remote sensing with machine learning to enhance biomass estimation in UNESCO World Heritage Sites like the Hyrcanian Forests.

Vafaei, S., Soosani, J., Adeli, K., Fadaei, H., Naghavi, H., Pham, T., & Tien Bui, D. (2018). Improving Accuracy Estimation of Forest Aboveground Biomass Based on Incorporation of ALOS-2 PALSAR-2 and Sentinel-2A Imagery and Machine Learning: A Case Study of the Hyrcanian Forest Area (Iran). Remote Sensing, 10(2), 172. https://doi.org/10.3390/rs10020172