Comparisons of spatial and non-spatial models for predicting soil carbon content based on visible and near-infrared spectral technology

Abstract Visible and near-infrared (VNIR) reflectance spectroscopy is a rapid, non-destructive, and cost-effective method for predicting soil properties. Partial least squares regression (PLSR) is a common method used to predict soil properties based on VNIR reflectance spectra. However, PLSR ignores the spatial autocorrelation of soil properties and the assumption of linear regression models, in which explanatory variables and model residuals should be independently and identically distributed. In this study, PLSR, partial least squares–geographically weighted regression (PLS–GWR), partial least squares regression Kriging (PLSRK), and partial least squares–geographically weighted regression Kriging (PLS–GWRK) were constructed to predict soil organic matter (SOM) based on soil spectral reflectance. In addition, this study explores the influence of the spatial non-stationarity of explanatory variables on prediction accuracy. Among the aforementioned models, PLSR was used as a reference model; PLS–GWR considered the spatial autocorrelation of SOM and its auxiliary variables; PLSRK and PLS–GWRK considered the spatial dependence of the model residuals to ensure the usability of PLSR and PLS–GWR. A total of 256 topsoil samples (0–30 cm) were collected from Chahe Town, located in Jianghan Plain, China, and the reflectance spectra (400–2350 nm) of soil were used. The prediction capabilities of the models were evaluated using the coefficient of determination ( R 2 ), the root-mean-square error (RMSE), and the ratio of performance to inter-quartile range (RPIQ). The evaluation indices showed that PLS–GWRK was the optimal model for predicting SOM using VNIR spectra. PLS–GWRK has the lowest values of RMSE C [0.109 ln (g·kg − 1 )] and RMSE P [0.223 ln (g·kg − 1 )] and the highest values of R 2 C (0.933), R 2 P (0.653), and RPIQ (3.015). PLS–GWR result showed that the spatial dependence of SOM and principal components could improve prediction accuracy compared with the PLSR result. The result of PLSRK showed that the spatial dependence of the model residuals could influence the prediction accuracy of PLSR. The PLS–GWRK approach explicitly addressed the spatial dependency and spatial non-stationarity issues for interpolating SOM at regional scale.

[1]  S. Fotheringham,et al.  Geographically Weighted Regression , 1998 .

[2]  Yunqiang Zhu,et al.  Mapping the mean annual precipitation of China using local interpolation techniques , 2014, Theoretical and Applied Climatology.

[3]  L. Wilding,et al.  Spatial variability: its documentation, accommodation and implication to soil surveys , 1985 .

[4]  T. G. Orton,et al.  Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale , 2014, 1502.02513.

[5]  G. Kiely,et al.  Towards spatial geochemical modelling: Use of geographically weighted regression for mapping soil organic carbon contents in Ireland , 2011 .

[6]  R. Lal,et al.  Mapping the organic carbon stocks of surface soils using local spatial interpolator. , 2011, Journal of environmental monitoring : JEM.

[7]  A. McBratney,et al.  Critical review of chemometric indicators commonly used for assessing the quality of the prediction of soil attributes by NIR spectroscopy , 2010 .

[8]  H. Jenny,et al.  Factors of Soil Formation , 1941 .

[9]  Junhong Bai,et al.  Spatial distribution characteristics of organic matter and total nitrogen of marsh soils in river marginal wetlands , 2005 .

[10]  G. Matheron.  Principles of geostatistics , 1963 .

[11]  Guofeng Wu,et al.  Soil Organic Carbon Content Estimation with Laboratory-Based Visible–Near-Infrared Reflectance Spectroscopy: Feature Selection , 2014, Applied spectroscopy.

[12]  Rattan Lal,et al.  A geographically weighted regression kriging approach for mapping soil organic carbon stock , 2012 .

[13]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[14]  Annamaria Castrignanò,et al.  Laboratory-based Vis–NIR spectroscopy and partial least square regression with spatially correlated errors for predicting spatial variation of soil organic matter content , 2015 .

[15]  Rattan Lal,et al.  Assessing spatial variability in soil characteristics with geographically weighted principal components analysis , 2012, Computational Geosciences.

[16]  Guofeng Wu,et al.  Monitoring arsenic contamination in agricultural soils with reflectance spectroscopy of rice plants. , 2014, Environmental science & technology.

[17]  Charlie Chen,et al.  Digitally mapping the information content of visible–near infrared spectra of surficial Australian soils , 2011 .

[18]  Tao Chen,et al.  [Study of spatial interpolation of soil Cd contents in sewage irrigated area based on soil spectral information assistance]. , 2013, Guang pu xue yu guang pu fen xi = Guang pu.

[19]  Changkun Wang,et al.  Prediction of Soil Organic Matter Content Under Moist Conditions Using VIS-NIR Diffuse Reflectance Spectroscopy , 2013 .

[20]  E. Ben-Dor.  The reflectance spectra of organic matter in the visible near-infrared and short wave infrared region (400-2500 nm) during a controlled decomposition process , 1997 .

[21]  Shi Zhou,et al.  In Situ Measurement of Some Soil Properties in Paddy Soil Using Visible and Near-Infrared Spectroscopy , 2014, PloS one.

[22]  Guofeng Wu,et al.  Visible and near-infrared reflectance spectroscopy-an alternative for monitoring soil contamination by heavy metals. , 2014, Journal of hazardous materials.

[23]  Hanbin Kwak,et al.  Small-scale spatial variability of soil properties in a Korean swamp , 2013, Landscape and Ecological Engineering.

[24]  Claudy Jolivet,et al.  Which strategy is best to predict soil properties of a local site from a national Vis–NIR database? , 2014 .

[25]  R. Henry,et al.  Simultaneous Determination of Moisture, Organic Carbon, and Total Nitrogen by Near Infrared Reflectance Spectrophotometry , 1986 .

[26]  Sabine Grunwald,et al.  Comparison of multivariate methods for inferential modeling of soil carbon using visible/near-infrared spectra , 2008 .

[27]  S. Ustin,et al.  Predicting water content using Gaussian model on soil spectra , 2004 .

[28]  Y. Wan,et al.  Modeling the impact of climate change on soil organic carbon stock in upland soils in the 21st century in China , 2011 .

[29]  Zhongke Bai,et al.  Spatial variability and sampling optimization of soil organic carbon and total nitrogen for Minesoils of the Loess Plateau using geostatistics , 2015 .

[30]  Panos Panagos,et al.  Prediction of soil organic carbon content by diffuse reflectance spectroscopy using a local partial least square regression approach , 2014 .

[31]  Junjie Wang,et al.  Transferability of a Visible and Near-Infrared Model for Soil Organic Matter Estimation in Riparian Landscapes , 2014, Remote. Sens..

[32]  A. Stewart Fotheringham,et al.  Trends in quantitative methods I: stressing the local , 1997 .

[33]  G. McCarty,et al.  Mid-Infrared and Near-Infrared Diffuse Reflectance Spectroscopy for Soil Carbon Measurement , 2002 .

[34]  Edward B. Rastetter,et al.  Global Change and the Carbon Balance of Arctic EcosystemsCarbon/nutrient interactions should act as major constraints on changes in global terrestrial carbon cycling , 1992 .

[35]  Yaolin Liu,et al.  Comparing geospatial techniques to predict SOC stocks , 2015 .

[36]  R. V. Rossel,et al.  Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties , 2006 .

[37]  Yiyun Chen,et al.  Estimating Soil Organic Carbon Using VIS/NIR Spectroscopy with SVMR and SPA Methods , 2014, Remote. Sens..

[38]  Ming Xu,et al.  Spatial variability of soil microbial biomass and its relationships with edaphic, vegetational and climatic factors in the Three-River Headwaters region on Qinghai-Tibetan Plateau , 2015 .

[39]  W. Parton,et al.  Analysis of factors controlling soil organic matter levels in Great Plains grasslands , 1987 .

[40]  J. Deckers,et al.  World Reference Base for Soil Resources , 1998 .

[41]  D. W. Nelson,et al.  A Rapid and Accurate Procedure for Estimation of Organic Carbon in Soils , 1974 .

[42]  K. Shepherd,et al.  Global soil characterization with VNIR diffuse reflectance spectroscopy , 2006 .

[43]  Jacques Rivoirard.  On the Structural Link Between Variables in Kriging with External Drift , 2002 .

[44]  Harold M. van Es,et al.  Combined use of hyperspectral VNIR reflectance spectroscopy and kriging to predict soil variables spatially , 2011, Precision Agriculture.

[45]  Martin Charlton,et al.  The Use of Geographically Weighted Regression for Spatial Prediction: An Evaluation of Models Using Simulated Data Sets , 2010 .

[46]  Clifford M. Hurvich,et al.  Smoothing parameter selection in nonparametric regression using an improved Akaike information criterion , 1998 .

[47]  C. Hurburgh,et al.  Near-Infrared Reflectance Spectroscopy–Principal Components Regression Analyses of Soil Properties , 2001 .

[48]  De-Cheng Li,et al.  Mapping soil organic carbon content by geographically weighted regression: A case study in the Heihe River Basin, China , 2016 .

[49]  J. Granjeiro,et al.  Nanometer Scale Titanium Surface Texturing Are Detected by Signaling Pathways Involving Transient FAK and Src Activations , 2014, PloS one.

[50]  Yufeng Ge,et al.  VNIR DIFFUSE REFLECTANCE SPECTROSCOPY FOR AGRICULTURAL SOIL PROPERTY DETERMINATION BASED ON REGRESSION-KRIGING , 2007 .

[51]  Chuanrong Zhang,et al.  Predictive mapping of soil total nitrogen at a regional scale: A comparison between geographically weighted regression and cokriging , 2013 .

[52]  Frans van den Berg,et al.  Review of the most common pre-processing techniques for near-infrared spectra , 2009 .

[53]  Michael Vohland,et al.  Determination of soil properties with visible to near- and mid-infrared spectroscopy: Effects of spectral variable selection , 2014 .

[54]  Rattan Lal,et al.  Estimating the spatial distribution of organic carbon density for the soils of Ohio, USA , 2013, Journal of Geographical Sciences.