Comparison of three models of forest biomass estimation
三种森林生物量估测模型的比较分析

Aims Quantitative estimation of forest biomass is significant to studies of global carbon storage and carbon cycle. Our objective is to develop models to estimate forest biomass accurately. Methods Multi-stepwise regression model, traditional back propagation (BP) neutral network model and BP neutral network model based on Gaussian error function (Erf-BP) were developed to estimate forest biomass in Changbai Mountain of Heilongjiang, China according to TM imagery and 133 plots of forest inventory data. There were 71 dependent variables of geoscience and remote sensing. Important findings The precisions and root mean square errors of multi-stepwise regression model, traditional BP neutral network model and Erf-BP were 75%, 26.87 t·m–2; 80.92%, 21.44 t·m–2 and 82.22%, 20.83 t·m–2, respectively. Therefore, the relations between forest biomass and various factors can be better modeled and described by the improved Erf-BP.