We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
湖北恩施地区土壤重金属高光谱反演模型研究.
- Authors
方臣; 匡华; 周小娟; 陈曦; 万翔; 刘烨青
- Abstract
Taking As, Cd, Cr, Pb, Cu and Zn as the research objects, the soil spectral data were collected by ASD surface object spectrometer. Based on spectral preprocessing and correlation analysis, partial least squares regression method was used to construct the inversion and prediction model of soil heavy metal content and spectrum. The results show that the combination of smoothing processing, first derivative, detrend and normalized scattering correction can effectively improve the inversion accuracy of the model. Based on PLSR model, analysis of six parameters inclduing RMSEC, RMSECV, RMSEP, found that compared with Cd, Cr and Zn, the measurement error of As, Pb, Cu is smaller and the correlation is higher, showing that the model can predict the three elements of As, Pb, Cu. This study would provide a technical reference for using hyperspectral remote sensing image data to rapidly monitor soil heavy metal pollution in Enshi, Hubei Province.
- Subjects
HUBEI Sheng (China); PARTIAL least squares regression; METAL content of soils; HEAVY metal toxicology; REMOTE sensing; MEASUREMENT errors; STATISTICAL correlation
- Publication
Environmental Science & Technology (10036504), 2021, Vol 44, Issue 9, p154
- ISSN
1003-6504
- Publication type
Article
- DOI
10.19672/j.cnki.1003-6504.0604.21.338