Estimating the Aboveground Biomass of Urban Trees by Combining Optical and Lidar Data: A Case Study of Hengqin, Zhuhai, China

Abstract

The aboveground biomass (AGB) of trees plays an important role in the urban ecological environment. Unlike forest biomass estimation, the estimation of AGB of urban trees is greatly influenced by human activities and has strong spatial heterogeneity. In this study, taking Hengqin, China, as an example, we extract the tree area accurately and design a collaborative scheme of optical and lidar data. Finally, five evaluation models are used, including two deep learning models (deep belief network and stacked sparse autoencoder), two machine learning models (random forest and support vector regression), and a geographically weighted regression model. The experimental results show that the deep learning model is effective. The result of the stacked sparse autoen - coder, which is the best model, is that R2 = 0.768 and root mean square error = 18.17 mg/ha. The results show that our method can be applied to estimate the AGB of urban trees, which greatly influences urban ecological construction.