Machine learning and geostatistical approaches for estimating aboveground biomass in Chinese subtropical forests

Abstract

BackgroundAboveground biomass (AGB) is a fundamental indicator of forest ecosystem productivity and health and hence plays an essential role in evaluating forest carbon reserves and supporting the development of targeted forest management plans.MethodsHere, we proposed a random forest/co-kriging framework that integrates the strengths of machine learning and geostatistical approaches to improve the mapping accuracies of AGB in northern Guangdong Province of China. We used Landsat time-series observations, Advanced Land Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) data, and National Forest Inventory (NFI) plot measurements, to generate the forest AGB maps at three time points (1992, 2002 and 2010) showing the spatio-temporal dynamics of AGB in the subtropical forests in Guangdong, China.ResultsThe proposed model was capable of mapping forest AGB using spectral, textural, topographical variables and the radar backscatter coefficients in an effective and reliable manner. The root mean square error of the plot-level AGB validation was between 15.62 and 53.78 t∙ha− 1, the mean absolute error ranged from 6.54 to 32.32 t∙ha− 1, the bias ranged from − 2.14 to 1.07 t∙ha− 1, and the relative improvement over the random forest algorithm was between 3.8% and 17.7%. The largest coefficient of determination (0.81) and the smallest mean absolute error (6.54 t∙ha− 1) were observed in the 1992 AGB map. The spectral saturation effect was minimized by adding the PALSAR data to the modeling variable set in 2010. By adding elevation as a covariable, the co-kriging outperformed the ordinary kriging method for the prediction of the AGB residuals, because co-kriging resulted in better interpolation results in the valleys and plains of the study area.ConclusionsValidation of the three AGB maps with an independent dataset indicated that the random forest/co-kriging performed best for AGB prediction, followed by random forest coupled with ordinary kriging (random forest/ordinary kriging), and the random forest model. The proposed random forest/co-kriging framework provides an accurate and reliable method for AGB mapping in subtropical forest regions with complex topography. The resulting AGB maps are suitable for the targeted development of forest management actions to promote carbon sequestration and sustainable forest management in the context of climate change.