Knowledge Resource Center for Ecological Environment in Arid Area
DOI | 10.7717/peerj.5714 |
Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy | |
Ding, Jianli1,2; Yang, Aixia1,3; Wang, Jingzhe1,2; Sagan, Vasit4; Yu, Danlin5,6 | |
通讯作者 | Yu, Danlin |
来源期刊 | PEERJ |
ISSN | 2167-8359 |
出版年 | 2018 |
卷号 | 6 |
英文摘要 | Soil organic carbon (SOC) is an important soil property that has profound impact on soil quality and plant growth. With 140 soil samples collected from Ebinur Lake Wetland National Nature Reserve, Xinjiang Uyghur Autonomous Region of China, this research evaluated the feasibility of visible/near infrared (VIS/NIR) spectroscopy data (350-2,500 nm) and simulated EO-1 Hyperion data to estimate SOC in arid wetland regions. Three machine learning algorithms including Ant Colony Optimization-interval Partial Least Squares (ACO-iPLS), Recursive Feature Elimination-Support Vector Machine (RF-SVM), and Random Forest (RF) were employed to select spectral features and further estimate SOC. Results indicated that the feature wavelengths pertaining to SOC were mainly within the ranges of 745-910 nm and 1,911-2,254 nm. The combination of RF-SVM and first derivative pre-processing produced the highest estimation accuracy with the optimal values of R-t (correlation coefficient of testing set), RMSEt and RPD of 0.91, 0.27% and 2.41, respectively. The simulated EO-1 Hyperion data combined with Support Vector Machine (SVM) based recursive feature elimination algorithm produced the most accurate estimate of SOC content. For the testing set, R-t was 0.79, RMSEt was 0.19%, and RPD was 1.61. This practice provides an efficient, low-cost approach with potentially high accuracy to estimate SOC contents and hence supports better management and protection strategies for desert wetland ecosystems. |
英文关键词 | Ebinur lake wetland Desert wetland soil Soil organic carbon Machine learning |
类型 | Article |
语种 | 英语 |
国家 | Peoples R China ; USA |
收录类别 | SCI-E |
WOS记录号 | WOS:000447542900002 |
WOS关键词 | NEAR-INFRARED-SPECTROSCOPY ; DIFFUSE-REFLECTANCE SPECTROSCOPY ; ARTIFICIAL NEURAL-NETWORK ; RANDOM FORESTS ; LAND-USE ; SPATIAL VARIABILITY ; REGIONAL-SCALE ; LEAST-SQUARES ; MATTER ; CHINA |
WOS类目 | Multidisciplinary Sciences |
WOS研究方向 | Science & Technology - Other Topics |
来源机构 | 新疆大学 |
资源类型 | 期刊论文 |
条目标识符 | http://119.78.100.177/qdio/handle/2XILL650/212045 |
作者单位 | 1.Xinjiang Univ, Coll Resources & Environm Sci, Higher Educ Inst, Key Lab Smart City & Environm Modelling, Urumqi, Peoples R China; 2.Xinjiang Univ, Key Lab Oasis Ecol, Urumqi, Peoples R China; 3.Qinzhou Univ, Coll Resources & Environm Sci, Qinzhou, Peoples R China; 4.St Louis Univ, Dept Earth & Atmospher Sci, St Louis, MO 63103 USA; 5.Montclair State Univ, Dept Earth & Environm Studies, Montclair, NJ USA; 6.Renmin Univ China, Sch Sociol & Populat Studies, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Ding, Jianli,Yang, Aixia,Wang, Jingzhe,et al. Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy[J]. 新疆大学,2018,6. |
APA | Ding, Jianli,Yang, Aixia,Wang, Jingzhe,Sagan, Vasit,&Yu, Danlin.(2018).Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy.PEERJ,6. |
MLA | Ding, Jianli,et al."Machine-learning-based quantitative estimation of soil organic carbon content by VIS/NIR spectroscopy".PEERJ 6(2018). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。