Knowledge Management System Of Institute Of Botany,CAS
| Estimation of degraded grassland aboveground biomass using machine learning methods from terrestrial laser scanning data | |
Xu, Kexin1; Su, Yanjun1; Liu, Jin1; Hu, Tianyu1; Jin, Shichao1; Ma, Qin1; Zhai, Qiuping2; Wang, Rui1; Zhang, Jing1; Li, Yumei1; Liu, Hon An3; Guo, Qinghua1
| |
| 2020 | |
| Source Publication | ECOLOGICAL INDICATORS
 |
| ISSN | 1470-160X |
| Volume | 108 |
| Abstract | Aboveground biomass (AGB) is an important indicator for grassland ecosystem assessment, management and utilization. Remote sensing technologies have driven the development of grassland AGB estimation from labor-intensive to highly-efficient. However, optical image-based remote sensing methods are fraught with uncertainty issues due to the saturation effects. In this study, we evaluated the capability of the emerging terrestrial laser scanning (TLS) technique in estimating grassland AGB in the northern agro-pastoral ecotone of China. Seven variables (i.e., canopy cover, canopy volume, mean height, maximum height, minimum height, range of height, and standard deviation of height) were extracted from the TLS data of 30 plots across the northern agro-pastoral ecotone of China, and were used to build regression models with field measured AGB using four regression methods, which are simple regression (SR) model, stepwise multiple regression (SMR) model, random forest (RF) model and artificial neural network (ANN) model. The results demonstrate that TLS is a feasible technique for extracting grassland structural parameters. Mean grass height and canopy cover obtained from TLS data have good correspondence with field measurements (R-2 > 0.7, p-values < 0.001). Among the four regression models, the SMR model yields the highest prediction accuracy (R-2 = 0.84, RMSE = 48.89 g/m(2)), followed by the RF model (R-2 = 0.78, RMSE = 68.72 g/m(2)), the SR model (R-2 = 0.80, RMSE = 86.4 g/m(2)), and the ANN model (R-2 = 0.73, RMSE = 101.40 g/m(2)). Minimum grass height and canopy coverage are the two most important variables influencing the prediction accuracy of the SMR model, and the prediction accuracy of the SMR model increases with the increase of point density. The results of this study can provide guidance for choosing the optimal model and data collection method for estimating degraded grassland AGB using TLS in agro-pastoral ecotone. |
| Keyword | Aboveground biomass (AGB) Degraded grassland Machine learning Northern agro-pastoral ecotone Terrestrial laser scanning (TLS) |
| Subject Area | Biodiversity Conservation ; Environmental Sciences |
| DOI | 10.1016/j.ecolind.2019.105747 |
| Indexed By | SCI |
| Language | 英语 |
| WOS Keyword | ARTIFICIAL NEURAL-NETWORK ; AIRBORNE LIDAR DATA ; RANDOM FOREST ; CANOPY COVER ; PREDICTION ; CARBON ; SHRUB ; ANN |
| WOS Research Area | Biodiversity & Conservation ; Environmental Sciences & Ecology |
| WOS ID | WOS:000493902400066 |
| Publisher | ELSEVIER |
| Subtype | Article |
| Publication Place | AMSTERDAM |
| EISSN | 1872-7034 |
| Funding Organization | National Key R&D Program of China [2016YFC0500202] ; Frontier Science Key Programs of the Chinese Academy of Sciences [QYZDY-SSW-SMC011] ; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [41871332] ; CAS Pioneer Hundred Talents Program |
| Corresponding Author Email | guo.qinghua@gmail.com |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.ibcas.ac.cn/handle/2S10CLM1/21968 |
| Collection | 植被与环境变化国家重点实验室 |
| Affiliation | 1.Chinese Acad Sci, Inst Bot, State Key Lab Vegetat & Environm Change, Beijing 100093, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Linyi Univ, Shandong Prov Key Lab Soil Conservat & Environm P, Coll Resources & Environm, Linyi 276000, Shandong, Peoples R China 4.Peking Univ, Coll Urban & Environm Sci, Beijing 100871, Peoples R China |
| Recommended Citation GB/T 7714 | Xu, Kexin,Su, Yanjun,Liu, Jin,et al. Estimation of degraded grassland aboveground biomass using machine learning methods from terrestrial laser scanning data[J]. ECOLOGICAL INDICATORS,2020,108. |
| APA | Xu, Kexin.,Su, Yanjun.,Liu, Jin.,Hu, Tianyu.,Jin, Shichao.,...&Guo, Qinghua.(2020).Estimation of degraded grassland aboveground biomass using machine learning methods from terrestrial laser scanning data.ECOLOGICAL INDICATORS,108. |
| MLA | Xu, Kexin,et al."Estimation of degraded grassland aboveground biomass using machine learning methods from terrestrial laser scanning data".ECOLOGICAL INDICATORS 108(2020). |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| 1-s2.0-S1470160X1930（4794KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Application Full Text | |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment