Search

The aim of this study was to evaluate the utility of Sentinel-1/2 time-series for monitoring selective logging in temperate forests. Ten stands were selectively logged with 5 to 28% of the existing growing stock volume being extracted. The analysis was focused on backscatter coefficient and surface reflectance changes for dates immediately prior and past the logging period. Monthly information on leaf area index (from terrestrial laser scanning) and vegetation water content (from destructive sampling) was used to support the analysis. The analysis suggested that monitoring selective logging using Sentinel-1/2 imagery is challenging in temperate montane forests due to a range of factors, including logging time and duration, saturation of C-band wavelength, and relatively small changes in canopy cover that cannot be reliably picked up by the optical sensor.

The aim of this study was to evaluate the utility of deep learning (DL) approaches to estimate forest growing stock volume from L-band SAR data over areas characterized by diverse species composition. For comparison, parametric models were also used. When using one independent variable (i.e. HV backscatter coefficient) the lowest estimation errors were observed for the empirical model followed by Random Forests (RF). Increasing the number of independent variables resulted in marginally more accurate results for the machine learning approaches. However, for the studied area, DL approaches did not improve GSV retrieval when compared to RF or empirical modelling suggesting that L-band data sensitivity to GSV values is the main limiting factor.