Near infrared spectroscopic determination of soil organic matter based on dung beetle optimizer and support vector machine regression

D Yun and L Chang and SX Chen and YY Shi, JOURNAL OF NEAR INFRARED SPECTROSCOPY, 33, 93-106 (2025).

DOI: 10.1177/09670335251383685

Learning performance and generalization ability of support vector machines regression (SVR) models used to predict soil organic matter (SOM) largely depend on the selection of correlation coefficients. Soil sample data from the state-owned Huangmian Forest Farm and Yachang Forest Farm in Guangxi Zhuang Autonomous Region, were used to compare competitive adaptive reweighted sampling (CARS) with principal component analysis (PCA) and support vector regression (SVR) based on full spectrual data. In addition, the SVR model optimized by multi-strategy improved dung beetle optimizer (MSDBO) and grey wolf optimizer (GWO) were compared. The experiment result shows two spectral feature wavelength selection algorithms and two optimization algorithms could improve the determination coefficient and reduced the root mean square error of prediction (RMSEP). The SVR model optimized by PCA and MSDBO illustrates the best generalization performance among all the evaluated models, the determination coefficient and RMSEP were 0.94 and 2.9 gkg-1 respectively. Mean relative error and mean absolute error were 10.0% and 2.2 respectively. The results show that the content of organic matter in soil can be accurately detected by SVR model optimized by input characteristics and parameters based on near infrared spectral data.

Return to Publications page