Integration of synthetic aperture radar and multispectral data for aboveground biomass retrieval in Zagros oak forests, Iran: an attempt on Sentinel imagery

• Published in: International journal of remote sensing Vol. 41; no. 20; pp. 8069 - 8095
• Main Authors: Safari, Amir, Sohrabi, Hormoz
• Format: Journal Article
• Language: English
• Published: London Taylor & Francis 17.10.2020; Taylor & Francis Ltd
• Subjects: Accessibility; Artificial neural networks; Backscatter; Backscattering; Biomass; Coefficients; Forest biomass; Genetic algorithms; Imagery; Mapping; Model accuracy; Modelling; Neural networks; Radar; Radar data; Ratios; Remote sensing; Remote sensors; Removal; Retrieval; Root-mean-square errors; SAR (radar); Screening; Statistical analysis; Statistical methods; Statistical models; Synthetic aperture radar; Texture
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/01431161.2020.1771789

The use of freely accessible Sentinel-1 synthetic aperture radar (S-1 SAR) and Sentinel-2 multispectral instrument (S-2 MSI) data are currently a feasible way of mapping forest aboveground biomass (AGB) over large areas. Despite the extensive mapping of forest AGB by remote sensing, how to effectively combine different sensors data, selecting the proper statistical modelling method, and variable screening are still poorly understood. This paper presents a framework for Sentinel-based AGB estimation through the use of four variable screening techniques, namely, genetic algorithm (GA), least absolute shrinkage and selection operator (LASSO), boruta, and removal-based; and three statistical modelling methods including multiple linear regression (MLR), artificial neural network (ANN), and random forest (RF). These methods were examined across two forested sites with different levels of human activity (highly-degraded: HD and minorly-degraded: MD) in Zagros coppice oak forests. We used backscatter coefficients and texture metrics of S-1 SAR, in addition to raw bands, simple band ratios, vegetation indices and texture metrics of S-2 MSI to extract 53 explanatory variables. Our findings showed that GA and removal-based variable screening techniques outperformed the others and RF and MLR statistical modelling methods obtained the best results. The use of different variable screening techniques and modelling methods demonstrated higher accuracies of AGB estimates for the MD site compared to the HD site. S-2 MSI (Coefficient of determination (R 2 ) = 0.76 and Root Mean Square Error (RMSE) = 35.08% of the mean) provided a higher accuracy than S-1 SAR (R 2  = 0.42 and RMSE = 52.94% of the mean). Overall, the study demonstrates encouraging results in the retrieval and predictive mapping of the AGB of Zagros forests using the freely accessible Sentinel imagery.