Determination of soil pH from Vis-NIR spectroscopy by extreme learning machine and variable selection: A case study in lime concretion black soil

Abstract

Variable selection is widely accepted as an important step in the quantitative analysis of visible and near-infrared (Vis-NIR) spectroscopy, as it tends to improve the model's robustness and predictive ability. In this study, a total of 140 lime concretion black soil samples were collected from two towns in Guoyang County, China. The Vis-NIR spectra measured in the laboratory were used to estimate soil pH by an extreme learning machine (ELM). First, the soil spectra were treated by the optimized continuous wavelet transform (CWT), and then four spectral feature selection methods (competitive adaptive reweighted sampling, CARS; successive projections algorithm, SPA; Monte Carlo uninformative variable elimination, MCUVE; genetic algorithm, GA) were applied with ELM in the CWT domain to determine the techniques with most predictions. For comparison, The PLS and SVM models were also developed. The coefficient of determination (R²), root mean square error (RMSE), and residual prediction deviation (RPD) were used to evaluate the model performance. Based on the validation dataset, the performance of the ELM models was superior to that of the PLS and SVM models expect SPA and MCUVE. In the ELM models, the order of the prediction accuracy was GA-ELM (R²_p = 0.86; RMSE_p = 0.1484; RPD = 2.64), CARS-ELM (R²_p = 0.84; RMSE_p = 0.1565; RPD = 2.50), ELM (R²_p = 0.84; RMSE_p = 0.1572; RPD = 2.49), SPA-ELM (R²_p = 0.84; RMSE_p = 0.1589; RPD = 2.47) and MCUVE-ELM (R²_p = 0.83; RMSE_p = 0.1599; RPD = 2.45). The proposed method of CARS-ELM had a relatively strong ability for spectral variable selection while retaining excellent prediction accuracy and short computing time (0.39 s). In addition, the variables selected by the four methods (CARS, SPA, MCUVE and GA) indicated the prediction mechanism for pH in lime concretion black soil may be the relation between pH and iron oxides and organic matter. In conclusion, CARS-ELM has great potential to accurately determine the pH in lime concretion black soil using Vis-NIR spectroscopy.

Keywords: Extreme learning machine; Lime concretion black soil; Soil pH; VIS-NIR spectroscopy; Variable selection.