Abstract
Soil spectral libraries were established all over the world to help build the base for predicting soil properties by proximal soil sensing. Previous studies indicated that it was important to select optimum subsets when predicting soil properties of a local site from a large spectral library. Thus, how to determine optimum subsets from the spectral library becomes crucial. This study compared different strategies for predicting soil organic matter of a local site from a regional Vis–NIR soil spectral library. Different calibration subsets and two calibration models [local and global partial least squares regression (PLSR)] were assessed for prediction of the target set: (1) different calibration subsets were compared (Pro_cali, samples in the province; Hb_cali, samples in Huaibei area, geographically close, and with similar parent material compared to the target set; Local_cali, samples located in the same county of the target set); (2) the spiking effects were investigated by selecting different numbers of local samples from Local_cali using Kennard–Stone algorithm to be spiked with different calibration sets (Pro_cali and Hb_cali); (3) local PLSR and global PLSR calibrations were compared for prediction accuracy. Model performances were assessed in terms of coefficient determination between observed and predicted values (R2), root-mean-squared error for prediction (RMSEP), and the ratio of percentage deviation (RPD). In general, this study concluded that (1) prediction performances of different calibration subsets indicated that Hb_cali can be a good alternative to replace Local_cali for prediction, when local samples are not available; (2) the spiking effects depended on the number of spectra spiked, also it did not always lead to higher prediction accuracy; and (3) global PLSR and local PLSR exhibited similar prediction accuracy in this case study, more research were needed to compare the performances of these two models.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Araujo SR, Wetterlind J, Dematte JAM, Stenberg B (2014) Improving the prediction performance of a large tropical vis-NIR spectroscopic soil library from Brazil by clustering into smaller subsets or use of data mining calibration techniques. European Journal of Soil Science 65(5): 718–729.
Brown DJ (2007) Using a global VNIR soil-spectral library for local soil characterization and landscape modeling in a 2nd-order Uganda watershed. Geoderma 140(4): 444–453.
Brown DJ, Shepherd KD, Walsh MG, Mays MD, Reinsch TG (2006) Global soil characterization with VNIR diffuse reflectance spectroscopy. Geoderma 132(3–4): 273–290.
Fearn T, Davies A (2003) Locally-biased regression. Journal of Near Infrared Spectroscopy 11(6): 467–478.
Gogé F, Gomez C, Jolivet C, Joffre R (2014) Which strategy is best to predict soil properties of a local site from a national Vis–NIR database? Geoderma 213(0): 1–9.
Gogé F, Joffre R, Jolivet C, Ross I, Ranjard L (2012) Optimization criteria in sample selection step of local regression for quantitative analysis of large soil NIRS database. Chemometrics and Intelligent Laboratory Systems 110(1): 168–176.
Guerrero C, Stenberg B, Wetterlind J, Rossel RAV, Maestre FT, Mouazen AM, Zornoza R, Ruiz-Sinoga JD, Kuang B (2014) Assessment of soil organic carbon at local scale with spiked NIR calibrations: effects of selection and extra-weighting on the spiking subset. European Journal of Soil Science 65(2): 248–263.
Guerrero C, Zornoza R, Gómez I, Mataix-Beneyto J (2010) Spiking of NIR regional models using samples from target sites: Effect of model size on prediction accuracy. Geoderma 158(1–2): 66–77.
Kuang, B, Mouazen AM (2013) Effect of spiking strategy and ratio on calibration of on-line visible and near infrared soil sensor for measurement in European farms. Soil and Tillage Research 128(0): 125–136.
Naes, T, Isaksson T, Fearn T, Davies T (2002) A user friendly guide to multivariate calibration and classification. NIR publications.
Nocita M, Stevens A, Toth G, Panagos P, van Wesemael B, Montanarella L (2014) Prediction of soil organic carbon content by diffuse reflectance spectroscopy using a local partial least square regression approach. Soil Biology & Biochemistry 68: 337–347.
Rossel RAV, Jeon YS, Odeh IOA, McBratney AB (2008) Using a legacy soil sample to develop a mid-IR spectral library. Soil Research 46(1): 1–16.
Sankey JB, Brown DJ, Bernard ML, Lawrence RL (2008) 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. Geoderma 148(2): 149–158.
Shepherd KD, Walsh MG (2002) Development of Reflectance Spectral Libraries for Characterization of Soil Properties. Soil Science Society of American Journal 66(3): 988–998.
Shi Z, Wang Q, Peng J, Ji W, Liu H, Li X, Rossel RAV (2014) Development of a national VNIR soil-spectral library for soil classification and prediction of organic matter concentrations. Science China Earth Sciences 57(7): 1671–1680.
Rossel RAV (2009) The Soil Spectroscopy Group and the development of a global soil spectral library. NIR news 20(4): 14–15.
Rossel RAV, Walvoort DJJ, McBratney AB, Janik LJ, Skjemstad JO (2006) Visible, near infrared, mid infrared or combined diffuse reflectance spectroscopy for simultaneous assessment of various soil properties. Geoderma 131(1–2): 59–75.
Wetterlind J, Stenberg B (2010) Near-infrared spectroscopy for within-field soil characterization: small local calibrations compared with national libraries spiked with local samples. European Journal of Soil Science 61(6): 823–843.
Acknowledgements
The study was supported by the National Science Foundation of China (41130530, 91325301). The authors are grateful to Dr. David Rossiter for his comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this chapter
Cite this chapter
Zeng, R., Zhao, YG., Wu, DW., Wei, CL., Zhang, GL. (2016). Comparison of Different Strategies for Predicting Soil Organic Matter of a Local Site from a Regional Vis–NIR Soil Spectral Library. In: Zhang, GL., Brus, D., Liu, F., Song, XD., Lagacherie, P. (eds) Digital Soil Mapping Across Paradigms, Scales and Boundaries. Springer Environmental Science and Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-10-0415-5_26
Download citation
DOI: https://doi.org/10.1007/978-981-10-0415-5_26
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0414-8
Online ISBN: 978-981-10-0415-5
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)