Improving Spectral Estimation of Soil Organic Carbon Content through Semi-Supervised Regression

Visible and near infrared (VIS-NIR) spectroscopy has been applied to estimate soil organic carbon (SOC) content with many modeling strategies and techniques, in which a crucial and challenging problem is to obtain accurate estimations using a limited number of samples with reference values (labeled samples). To solve such a challenging problem, this study, with Honghu City (Hubei Province, China) as a study area, aimed to apply semi-supervised regression (SSR) to estimate SOC contents from VIS-NIR spectroscopy. A total of 252 soil samples were collected in four field campaigns for laboratory-based SOC content determinations and spectral measurements. Semi-supervised regression with co-training based on least squares support vector machine regression (Co-LSSVMR) was applied for spectral estimations of SOC contents, and it was further compared with LSSVMR. Results showed that Co-LSSVMR could improve the estimations of SOC contents by exploiting samples without reference values (unlabeled samples) when the number of labeled samples was not excessively small and produce better estimations than LSSVMR. Therefore, SSR could reduce the number of labeled samples required in calibration given an accuracy threshold, and it holds advantages in SOC estimations from VIS-NIR spectroscopy with a limited number of labeled samples. Considering the increasing popularity of airborne platforms and sensors, SSR might be a promising modeling technique for SOC estimations from remotely sensed hyperspectral images.

[1]  S. K. Alavipanah,et al.  Estimating soil organic carbon from soil reflectance: a review , 2010, Precision Agriculture.

[2]  T. Behrens,et al.  New approaches of soil similarity analysis using manifold-based metric learning from proximal vis – NIR sensing data , 2011 .

[3]  Dimitri P. Bertsekas,et al.  Constrained Optimization and Lagrange Multiplier Methods , 1982 .

[4]  Rodnei Rizzo,et al.  Spectral regionalization of tropical soils in the estimation of soil attributes , 2016 .

[5]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[6]  Sabine Chabrillat,et al.  Prediction of Common Surface Soil Properties Based on Vis-NIR Airborne and Simulated EnMAP Imaging Spectroscopy Data: Prediction Accuracy and Influence of Spatial Resolution , 2016, Remote. Sens..

[7]  A. Ashworth,et al.  Organic substrate, clay type, texture, and water influence on NIR carbon measurements , 2016 .

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

[9]  Xiaojun Wan,et al.  Co-Training for Cross-Lingual Sentiment Classification , 2009, ACL.

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

[11]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

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

[13]  Liang Xiaocui.  Characteristics of organic carbon and nutrient content in five soil types in Honghu wetland ecosystems , 2011 .

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

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

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

[17]  Farid Melgani,et al.  Semisupervised PSO-SVM Regression for Biophysical Parameter Estimation , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[18]  Chein-I Chang,et al.  Semi-Supervised Linear Spectral Unmixing Using a Hierarchical Bayesian Model for Hyperspectral Imagery , 2008, IEEE Transactions on Signal Processing.

[19]  Zhi-Hua Zhou,et al.  Analyzing Co-training Style Algorithms , 2007, ECML.

[20]  Alexander J. Smola,et al.  Support Vector Regression Machines , 1996, NIPS.

[21]  Michael E. Schaepman,et al.  Creating Multi-Temporal Composites of Airborne Imaging Spectroscopy Data in Support of Digital Soil Mapping , 2016, Remote. Sens..

[22]  R. Casa,et al.  Evaluation of the potential of the current and forthcoming multispectral and hyperspectral imagers to estimate soil texture and organic carbon , 2016 .

[23]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[24]  Kacem Chehdi,et al.  Regional prediction of soil organic carbon content over temperate croplands using visible near-infrared airborne hyperspectral imagery and synchronous field spectra , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[25]  D. Mulla.  Twenty five years of remote sensing in precision agriculture: Key advances and remaining knowledge gaps , 2013 .

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

[27]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[28]  Mohamed Cheriet,et al.  Semi-supervised learning for weighted LS-SVM , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[29]  Zhi-Hua Zhou,et al.  Semi-Supervised Regression with Co-Training , 2005, IJCAI.

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

[31]  Mia Hubert,et al.  LIBRA: a MATLAB library for robust analysis , 2005 .

[32]  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 .

[33]  Guofeng Wu,et al.  Estimating Soil Organic Carbon Content with Visible–Near-Infrared (Vis-NIR) Spectroscopy , 2014, Applied spectroscopy.

[34]  Bernhard Schölkopf,et al.  Introduction to Semi-Supervised Learning , 2006, Semi-Supervised Learning.

[35]  Bernd Schilling,et al.  Soil organic carbon stocks in southeast Germany (Bavaria) as affected by land use, soil type and sampling depth , 2012 .

[36]  Kwoh Chee Keong,et al.  Fast leave-one-out evaluation and improvement on inference for LS-SVMs , 2004, ICPR 2004.

[37]  A. Walkley,et al.  AN EXAMINATION OF THE DEGTJAREFF METHOD FOR DETERMINING SOIL ORGANIC MATTER, AND A PROPOSED MODIFICATION OF THE CHROMIC ACID TITRATION METHOD , 1934 .

[38]  Naif Alajlan,et al.  Improved Estimation of Water Chlorophyll Concentration With Semisupervised Gaussian Process Regression , 2012, IEEE Transactions on Geoscience and Remote Sensing.

[39]  T. Udelhoven,et al.  Monitoring soil organic carbon in croplands using imaging spectroscopy (moca project) , 2008 .

[40]  L. Hoffmann,et al.  Measuring soil organic carbon in croplands at regional scale using airborne imaging spectroscopy , 2010 .

[41]  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 .

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

[43]  A. Gholizadeh,et al.  Visible, Near-Infrared, and Mid-Infrared Spectroscopy Applications for Soil Assessment with Emphasis on Soil Organic Matter Content and Quality: State-of-the-Art and Key Issues , 2013, Applied spectroscopy.

[44]  K. Moffett,et al.  Remote Sens , 2015 .

[45]  R. V. Rossel,et al.  Using data mining to model and interpret soil diffuse reflectance spectra. , 2010 .

[46]  Abhishek K Gupta,et al.  Numerical Methods using MATLAB , 2014, Apress.

[47]  Alex B. McBratney,et al.  Using a legacy soil sample to develop a mid-IR spectral library , 2008 .

[48]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[49]  Paulo Pereira,et al.  Soil mapping, classification, and pedologic modeling: History and future directions , 2016 .

[50]  Johan A. K. Suykens,et al.  Coupled Simulated Annealing , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[51]  Bastian Siegmann,et al.  Regionalization of Uncovered Agricultural Soils Based on Organic Carbon and Soil Texture Estimations , 2016, Remote. Sens..

[52]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .

[53]  R. Shah,et al.  Least Squares Support Vector Machines , 2022 .

[54]  Johan A. K. Suykens,et al.  LS-SVMlab : a MATLAB / C toolbox for Least Squares Support Vector Machines , 2007 .

[55]  F. Denis.  Classification and Co-training from Positive and Unlabeled Examples , 2003 .

[56]  Thorsten Behrens,et al.  Sampling optimal calibration sets in soil infrared spectroscopy , 2014 .

[57]  Ke Sun,et al.  Some concepts of soil organic carbon characteristics and mineral interaction from a review of literature , 2016 .

[58]  Yan Zhou,et al.  Enhancing Supervised Learning with Unlabeled Data , 2000, ICML.

[59]  Guofeng Wu,et al.  Comparison of multivariate methods for estimating soil total nitrogen with visible/near-infrared spectroscopy , 2012, Plant and Soil.

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

[61]  R. V. Rossel,et al.  Soil organic carbon prediction by hyperspectral remote sensing and field vis-NIR spectroscopy: An Australian case study , 2008 .