文献类型： 外文期刊

作者： Chen, Bangqian ¹ ; Yun, Tin ² ; Ma, Jun ³ ; Kou, Weili ⁴ ; Li, Hailiang ⁵ ; Yang, Chuan ¹ ; Xiao, Xiangming ⁶ ; Zhang, Xi ¹ ;

作者机构： 1.Chinese Acad Trop Agr Sci CATAS, Rubber Res Inst RRI, State Key Lab Incubat Base Cultivat & Physiol Tro, Danzhou Invest & Expt Stn Trop Cops, Haikou 571101, Hainan, Peoples R China

2.Nanjing Forestry Univ, Sch Informat Sci & Technol, Nanjing 210037, Peoples R China

3.Fudan Univ, Inst Biodivers Sci, Minist Educ, Key Lab Biodivers Sci & Ecol Engn, 2005 Songhu Rd, Shanghai 200438, Peoples R China

4.Southwest Forestry Univ, Coll Big Data & Intelligence Engn, Kunming 650224, Yunnan, Peoples R China

5.Chinese Acad Trop Agr Sci CATAS, Inst Sci & Tech Informat, Haikou 571101, Hainan, Peoples R China

6.Univ Oklahoma, Ctr Spatial Anal, Dept Microbiol & Plant Biol, Norman, OK 73019 USA

关键词： biomass; rubber plantations; stand age; random forest; stratified k-fold cross-validation

期刊名称：REMOTE SENSING （ 影响因子：4.848； 五年影响因子：5.353 ）

ISSN：

年卷期： 2020 年 12 卷 23 期

页码：

收录情况： SCI

摘要： Rubber (Hevea brasiliensis Muell.) plantations constitute one of the most important agro-ecosystems in the tropical region of China and Southeast Asia, playing an important role in the carbon budget there. Accurately obtaining their biomass over a large area is challenging because of difficulties in acquiring the Diameter at Breast Height (DBH) through remote sensing and the problem of biomass saturation. The stand age, which is closely related to the forest biomass, was proposed for biomass estimation in this study. A stand age map at an annual scale for Hainan Island, which is the second largest natural rubber production base in China, was generated using all Landsat and Sentinel-2 (LS2) data (1987-2017). Scatter plots and the correlation coefficient method were used to explore the relationship (e.g., biomass saturation) between rubber biomass and different LS2-based variables. Subsequently, a regression model fitted with the stand age (R-2 = 0.96) and a Random Forest (RF) model parameterizing with LS2-based variables and/or the stand age were respectively employed to estimate rubber biomass for Hainan Island. The results show that rubber biomass was saturated around 65 Mg/ha with all LS2-based variables. The regression model estimated biomass accurately (R-2 = 0.79 and Root Mean Square Error (RMSE) = 14.00 Mg/ha) and eliminated the saturation problem significantly. In addition to LS2-based variables, adding a stand age parameter to the RF models was found to significantly improve the prediction accuracy (R-2 = 0.82-0.96 and RMSE = 4.08-10.59 Mg/ha, modeling using samples of different biomass sizes). However, all RF models overestimated the biomass of young plantations and underestimated the biomass of old plantations. A hybrid model integrating the optimal results of RF and regression models reduced estimation bias and generated the best performance (R-2 = 0.83 and RMSE = 12.48 Mg/ha). The total rubber biomass of Hainan Island in 2017 was about 5.40 x 10(7) Mg. The northward and westward expansions after 2000 had great impact on the biomass distribution, leading to a higher biomass density for the inland coastal strip from south to northeast and a lower biomass density in the northern and western regions.