Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis–NIR spectral library

European Journal of Soil Science - Tập 66 Số 4 - Trang 679-687 - 2015
Zhou Shi1, Wenjun Ji2,1, Raphael A. Viscarra Rossel3, Songchao Chen1, Yue Zhou1
1Institute of Applied Remote Sensing and Information Technology, College of Environmental and Resource Sciences, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China
2Department of Bioresource Engineering; McGill University; 21,111 Lakeshore Road Montreal H9X 3V9 Canada
3CSIRO Land and Water, Bruce E. Butler Laboratory GPO Box 1666 Canberra Australian Capital Territory 2601 Australia

Tóm tắt

SummaryWe need to determine the best use of soil vis–NIR spectral libraries that are being developed at regional, national and global scales to predict soil properties from new spectral readings. To reduce the complexity of a calibration dataset derived from the Chinese vis–NIR soil spectral library (CSSL), we tested a local regression method that combined geographical sub‐setting with a local partial least squares regression (local‐PLSR) that uses a limited number of similar vis–NIR spectra (k‐nearest neighbours). The central idea of the local regression, and of other local statistical approaches, is to derive a local prediction model by identifying samples in the calibration dataset that are similar, in spectral variable space, to the samples used for prediction. Here, to derive our local regressions we used Euclidean distance in spectral space between the calibration dataset and prediction samples, and we also used soil geographical zoning to account for similarities in soil‐forming conditions. We tested this approach with the CSSL, which comprised 2732 soil samples collected from 20 provinces in the People's Republic of China to predict soil organic matter (SOM). Results showed that the prediction accuracy of our spatially constrained local‐PLSR method (R2 = 0.74, RPIQ = 2.6) was better than that from local‐PLSR (R2 = 0.69, RPIQ = 2.3) and PLSR alone (R2 = 0.50, RPIQ = 1.5). The coupling of a local‐PLSR regression with soil geographical zoning can improve the accuracy of local SOM predictions using large, complex soil spectral libraries. The approach might be embedded into vis–NIR sensors for laboratory analysis or field estimation.

Từ khóa


Tài liệu tham khảo

Bao S.D., 1981, Soil and Agricultural Chemistry Analysis

10.1016/j.trac.2010.05.006

10.1016/j.geoderma.2007.04.021

10.1016/j.geoderma.2005.04.025

10.1029/JB089iB07p06329

10.1016/j.chemolab.2011.11.003

10.1016/j.geoderma.2013.07.016

Gong Z.T., 1999, Chinese Soil Taxonomy

10.1016/j.geoderma.2009.12.021

10.1255/jnirs.883

IUSS Working Group WRB2007.World Reference Base for Soil Resources 2006. First update 2007. World Soil Resources Reports No 103 FAO Rome.

Ji W., 2012, Using different mining algorithms to predict soil organic matter based on visible‐near infrared spectroscopy, Spectroscopy & Spectral Analysis, 32, 2393

10.3724/SP.J.1010.2012.00277

10.1201/b12728-79

10.1016/B978-0-12-394275-3.00003-1

10.1155/2012/294121

10.18637/jss.v018.i02

10.1016/j.soilbio.2013.10.022

10.1255/jnirs.1053

10.1016/j.geoderma.2012.12.014

10.1016/j.geoderma.2012.08.035

R Core Development Team, 2012, R: A Language and Environment for Statistical Computing

10.1255/jnirs.115

10.1007/s11427-013-4594-x

10.1016/S0065-2113(10)07005-7

10.1016/j.geoderma.2009.11.032

10.2136/sssaj1981.03615995004500060031x

Stroganova M.N., 2007, Environment Structure and Function: Earth System

10.1023/A:1023008322682

10.2134/jeq2009.0314

Viscarra Rossel R.A., 2009, The soil spectroscopy group and the development of a global soil spectral library, NIR New, 20, 17

10.1016/j.geoderma.2009.12.025

10.1111/j.1365-2389.2012.01495.x

10.1111/j.1365-2389.2011.01372.x

10.1111/j.1365-2389.2010.01283.x

Wold S., 1983, Proceedings of the Conference on Matrix Pencils: Lectures Notes in Mathematics, 286, 10.1007/BFb0062108

Xi C., 1982, The basis and regionalization of China's soil, Acta Pedological Sinica, 19, 97

Thông tin
Thông tin xuất bản

European Journal of Soil Science

Tập 66 Số 4

679-687

Thông tin tác giả