文献类型：期刊文献

英文题名：A novel method for approaching the compatibility of tree biomass estimation by multi-task neural networks

作者：Xu, Qigang[1] Lei, Xiangdong[1] Zhang, Huiru[2]

第一作者：Xu, Qigang

通信作者：Lei, XD[1]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Key Lab Forest Management & Growth Modelling, Natl Forestry & Grassland Adm, Beijing 100091, Peoples R China;[2]Chinese Acad Forestry, Expt Ctr Forestry North China, Beijing 102300, Peoples R China

年份：2022

卷号：508

外文期刊名：FOREST ECOLOGY AND MANAGEMENT

收录：;EI(收录号：20220411508143);Scopus(收录号：2-s2.0-85123191610);WOS:【SCI-EXPANDED(收录号:WOS:000784301100009)】；

基金：Acknowledgements This study was funded by National Natural Science Foundation of China (Grant No. 31870623) . We appreciated two anonymous reviewers for their insightful and constructive suggestions.

语种：英文

外文关键词：Tree biomass modeling; Multi-task learning; Artificial neural network; Loss function; Biological compatibility

摘要：It is important to guarantee the property of biological compatibility when estimating tree biomass of the total and components for carbon accounting under global climate change. The issue was successfully considered in traditional nonlinear regression models, but not for machine learning methods. A new method for approaching the compatibility of tree biomass estimation in ANN (Artificial Neural Network) was developed by using the multi-task loss function, which had the desire features of minimizing residuals and approaching biomass compatibility. The method was tested by two tree species biomass dataset and showed the desired feature. Leave one-out validation results showed that comparing ANN model with simultaneously fitting 7 outputs (stem, bark, branch, leaf, crown, trunk, aboveground) and classical loss function, the RMSE of aboveground estimation (AGB) and the mean absolute relative difference between AGB and the sum of component biomass estimations from the model developed by our new method decreased from 166.864 (kg) to 154.860 (kg) and from 4.757% to 0.071%, respectively for Abies nephrolepis dataset, and from 49.18 (kg) to 33.060 (kg) and from 5.314% to 0.636%, respectively for Acer mono dataset. It provided a trade-off solution for the error accumulation and the compatibility among components and the total estimations when using ANN for tree biomass modelling, and was useful for carbon accounting using machine learning methods.