Abstract
Under the influence of complex environmental conditions, the spatial heterogeneity of soil organic matter (SOM) is inevitable, and the relationship between SOM and visible and near-infrared (VNIR) spectra has the potential to be nonlinear. However, conventional VNIR-based methods for soil organic matter estimation cannot simultaneously consider the potential nonlinear relationship between the explanatory variables and predictors and the spatial heterogeneity of the relationship. Thus, the regional application of existing VNIR spectra-based SOM estimation methods is limited. This study combines the proposed partial least squares–based multivariate adaptive regression spline (PLS–MARS) method and a regional multi-variable associate rule mining and Rank–Kennard-Stone method (MVARC-R-KS) to construct a nonlinear prediction model to realize local optimality considering spatial heterogeneity. First, the MVARC-R-KS method is utilized to select representative samples and alleviate the sample global underrepresentation caused by spatial heterogeneity. Second, the PLS–MARS method is proposed to construct a nonlinear VNIR spectra-based estimation model with local optimization based on selected representative samples. PLS–MARS combined with the MVARC-R-KS method is illustrated and validated through a case study of Jianghan Plain in Hubei Province, China. Results showed that the proposed method far outweighs some available methods in terms of accuracy and robustness, suggesting the reliability of the proposed prediction model.
Highlights
Soil organic matter (SOM) content is significantly relevant to soil fertility, biological productivity, and agricultural sustainable development [1,2]
The formation, variation, and decomposition of SOM are generally influenced by various factors, and the visible and near-infrared (VNIR) spectra are comprehensively related to various soil properties; the relation of SOM content to VNIR spectra is complex with high nonlinearity [6,7]
The calibration set obtained utilizing the Rank–KS method was both SOM content and spectral information representative. These results indicated that the component concentrations and spectrographic information should be simultaneously taken into account to obtain the representative calibration set to accurately build a VNIR-spectrum–based SOM prediction model
Summary
Soil organic matter (SOM) content is significantly relevant to soil fertility, biological productivity, and agricultural sustainable development [1,2]. Accurate prediction of SOM content is of great significance for land management [1,3]. Extensive studies have fully affirmed the capability of SOM prediction methods based on visible and near-infrared (VNIR) spectra [4,5]. The function relation between SOM content and VNIR spectra should be established because of the strong soil spatial heterogeneity under the influence of complex environmental conditions. The formation, variation, and decomposition of SOM are generally influenced by various factors, and the VNIR spectra are comprehensively related to various soil properties; the relation of SOM content to VNIR spectra is complex with high nonlinearity [6,7]. Further exploration of VNIR spectra-based SOM prediction models is needed to improve simulation and prediction accuracies
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
