rs‐local data‐mines information from spectral libraries to improve local calibrations

&NA; Diffuse reflectance spectroscopy in the visible‐near infrared (vis‐NIR) and mid infrared (mid‐IR) can be used to estimate soil properties, such as organic carbon (C) content. Compared with conventional laboratory methods, it enables practical and inexpensive measurements at finer spatial and temporal resolutions, which are needed to improve the assessment and management of soil and the environment. Measurements of soil properties with spectra require empirical calibration and soil spectral libraries (SSL) have been developed for this purpose at the regional, continental and global scales. Calibrations derived with these SSLs, however, are often shown to predict poorly at local sites. Here we present a new method, rs‐local, that uses a small representative set of site‐specific (or ‘local’) data and re‐sampling techniques to select a subset of data from a large vis‐NIR SSL to improve calibrations at the site. We demonstrate the implementation of rs‐local by estimating soil organic C in two fields with different soil types, one in Australia and one in New Zealand. We found that with as few as 12 to 20 site‐specific samples and the SSL, training datasets derived with rs‐local could accurately predict soil organic C concentrations. Predictions with the rs‐local data were comparable to, or better than those made with site‐specific calibrations with up to 300 samples. Our method outperformed other published ‘local’ spectroscopic techniques that we tested. Thus, rs‐local can effectively improve both the accuracy and financial viability of soil spectroscopy. HighlightsWe describe a new algorithm (rs‐local) for site‐specific calibration using existing spectral libraries.rs‐local is a data driven method that makes no assumptions on spectral or sample similarities.rs‐local improved the accuracy of soil organic carbon estimates using spectroscopy.rs‐local improves the economic viability of soil spectroscopy.

[1]  Keith D. Shepherd,et al.  Soil Spectroscopy: An Alternative to Wet Chemistry for Soil Monitoring , 2015 .

[2]  Zhou Shi,et al.  Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations , 2014, Science China Earth Sciences.

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

[4]  Abdul Mounem Mouazen,et al.  Assessment of soil organic carbon at local scale with spiked NIR calibrations: effects of selection and extra-weighting on the spiking subset , 2013 .

[5]  R. Lal.  Soil carbon sequestration to mitigate climate change , 2004 .

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

[7]  David Clifford,et al.  The Australian three-dimensional soil grid: Australia’s contribution to the GlobalSoilMap project , 2015 .

[8]  Rick L. Lawrence,et al.  Comparing local vs. global visible and near-infrared (VisNIR) diffuse reflectance spectroscopy (DRS) calibrations for the prediction of soil clay, organic C and inorganic C , 2008 .

[9]  R. V. Rossel,et al.  Visible and near infrared spectroscopy in soil science , 2010 .

[10]  Sabine Grunwald,et al.  Spectroscopic models of soil organic carbon in Florida, USA. , 2010, Journal of environmental quality.

[11]  J. R. Quinlan.  Learning With Continuous Classes , 1992 .

[12]  Paolo Berzaghi,et al.  Investigation of a LOCAL Calibration Procedure for near Infrared Instruments , 1997 .

[13]  Tormod Næs,et al.  Multivariate calibration. I. Concepts and distinctions , 1984 .

[14]  Richard Webster,et al.  Predicting soil properties from the Australian soil visible–near infrared spectroscopic database , 2012 .

[15]  A. Hewitt.  New Zealand soil classification. , 1993 .

[16]  R. A. Viscarra Rossel,et al.  Soil organic carbon and its fractions estimated by visible–near infrared transfer functions , 2015 .

[17]  Thorsten Behrens,et al.  Distance and similarity-search metrics for use with soil vis-NIR spectra , 2013 .

[18]  Zhou Shi,et al.  Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis–NIR spectral library , 2015 .

[19]  Thomas Scholten,et al.  The spectrum-based learner: A new local approach for modeling soil vis–NIR spectra of complex datasets , 2013 .

[20]  William J. Welch,et al.  Computer-aided design of experiments , 1981 .

[21]  Meiyan Wang,et al.  Effects of Subsetting by Parent Materials on Prediction of Soil Organic Matter Content in a Hilly Area Using Vis–NIR Spectroscopy , 2016, PloS one.

[22]  César Guerrero,et al.  Spiking of NIR regional models using samples from target sites: effect of model size on prediction accuracy. , 2010 .

[23]  Martial Bernoux,et al.  National calibration of soil organic carbon concentration using diffuse infrared reflectance spectroscopy , 2016 .

[24]  Ronald D. Snee,et al.  Validation of Regression Models: Methods and Examples , 1977 .

[25]  R. Isbell.  Australian Soil Classification , 1996 .

[26]  Neil McKenzie,et al.  Proximal Soil Sensing: An Effective Approach for Soil Measurements in Space and Time , 2011 .

[27]  S. Wold,et al.  The multivariate calibration problem in chemistry solved by the PLS method , 1983 .

[28]  T. Næs,et al.  Locally weighted regression and scatter correction for near-infrared reflectance data , 1990 .

[29]  Viacheslav I. Adamchuk,et al.  A global spectral library to characterize the world’s soil , 2016 .

[30]  Zhou Shi,et al.  Baseline estimates of soil organic carbon by proximal sensing : Comparing design-based, model-assisted and model-based inference , 2016 .

[31]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[32]  Luca Montanarella,et al.  Prediction of Soil Organic Carbon at the European Scale by Visible and Near InfraRed Reflectance Spectroscopy , 2013, PloS one.

[33]  R. V. Rossel,et al.  In situ measurements of soil colour, mineral composition and clay content by vis–NIR spectroscopy , 2009 .