8 August 2016 Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery
Author Affiliations +
J. of Applied Remote Sensing, 10(3), 035010 (2016). doi:10.1117/1.JRS.10.035010
Biomass is one significant biophysical parameter of a forest ecosystem, and accurate biomass estimation on the regional scale provides important information for carbon-cycle investigation and sustainable forest management. In this study, Landsat satellite imagery data combined with field-based measurements were integrated through comparisons of five regression approaches [stepwise linear regression, K-nearest neighbor, support vector regression, random forest (RF), and stochastic gradient boosting] with two different candidate variable strategies to implement the optimal spatial above-ground biomass (AGB) estimation. The results suggested that RF algorithm exhibited the best performance by 10-fold cross-validation with respect to R2 (0.63) and root-mean-square error (26.44  ton/ha). Consequently, the map of estimated AGB was generated with a mean value of 89.34  ton/ha in northwestern Zhejiang Province, China, with a similar pattern to the distribution mode of local forest species. This research indicates that machine-learning approaches associated with Landsat imagery provide an economical way for biomass estimation. Moreover, ensemble methods using all candidate variables, especially for Landsat images, provide an alternative for regional biomass simulation.
© 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)
Chaofan Wu, Huanhuan Shen, Aihua Shen, Jinsong Deng, Muye Gan, Jinxia Zhu, Hongwei Xu, Ke Wang, "Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery," Journal of Applied Remote Sensing 10(3), 035010 (8 August 2016). https://doi.org/10.1117/1.JRS.10.035010

Biological research

Earth observing sensors


Data modeling

Remote sensing


Performance modeling


Back to Top