Quantitative Analysis of Major Metals in Agricultural Biochar Using Laser-Induced Breakdown Spectroscopy with an Adaboost Artificial Neural Network Algorithm

Abstract

To promote the green development of agriculture by returning biochar to farmland, it is of great significance to simultaneously detect heavy and nutritional metals in agricultural biochar. This work aimed first to apply laser-induced breakdown spectroscopy (LIBS) for the determination of heavy (Pb, Cr) and nutritional (K, Na, Ca, Mg, Cu, and Zn) metals in agricultural biochar. Each batch of collected biochar was prepared to a standardized sample using the separating and milling method. Two types of univariate analysis model were developed using peak intensity and integration area of the sensitive emission lines, but the performance did not satisfy the requirements of practical application because of the poor correlations between the measured values and predicted values, as well as large relative standard deviation of the prediction (RSDP) values. An ensemble learning algorithm, adaboost backpropagation artificial neural network (BP-Adaboost), was then used to develop the multivariate analysis models, which had a more robust performance than traditional univariate analysis, partial least squares regression (PLSR), and backpropagation artificial neural network (BP-ANN). The optimized RSDP values for K, Ca, Mg, and Cu were less than 10%, while the RSDP values for Pb, Cr, Zn, and Na were in the range of 10–20%. Moreover, the pairwise t-test of its prediction set showed that there was no significant difference between the measurements of LIBS and ICP-MS. The promising results indicate that rapid and simultaneous detection of major heavy and nutritional metals in agricultural biochar can be achieved using LIBS and reasonable chemometric algorithms.

Quantitative Detection of Chromium Pollution in Biochar Based on Matrix Effect Classification Regression Model

“…However, the complex matrix effect present in these samples cannot be reduced by these sensitive variable extraction algorithms, resulting in the high degree of noise in the LIBS analytical spectra of Cr. Moreover, the ARSDP value of the developed 3 classification regression model decreased by 9.28% in comparison with our previous work [ 34 ] at similar concentrations. The reason for this may be that the unsupervised/supervised classification methods can successfully divide the tested samples into different classifications, which can obviously weaken the influence of matrix effect on the analytical spectra of Cr.…”

Laser Spectroscopic Characterization for the Rapid Detection of Nutrients along with CN Molecular Emission Band in Plant-Biochar

“…PCA test remodels the dataset from high-ranking dimensions to significant low-dimension correlated variables known as principal components (PCs). PCA can be applied for sample classification and high dimension reduction using a scoring matrix [ 20 , 49 , 50 ].…”

“…PCA is an unsupervised machine learning and the statistical algorithm technique used to lower the high dimensional data to a set of low dimensional correlated variables. These low-dimensional correlated variables are known as principal components (PCs) [ 20 ]. In the present study, PCs were constructed using the maximum covariance in the spectral data.…”

“…In addition, it was also reported that PCA of FTIR spectra indicated similarities and dissimilarities of biochar samples prepared at different pyrolysis temperatures. Most recently, Duan et al [ 20 ] employed a calibrated LIBS technique on agriculture biochar for the quantitative studies of heavy elements, including Cr, and Pb, along with major nutritional metals, including Cu, Zn, Ca, Na, K, and Mg.…”

Application of laser-induced breakdown spectroscopy with a generalized regression neural network and LASSO-type methods for estimation of arsenic and chromium in soil

“…22 Zhang et al proposed LIBS and random forest (RF) for the quantitative analysis of 14 steel samples containing Cr, Cu Mn, Ni, and Si elements, 23 while Duan et al successfully employed a backpropagation neural network (BPNN) combined with AdaBoost to detect heavy metals in agricultural biochar and obtained the determination coefficients of prediction of 0.9584, 0.9463, 0.8497, and 0.9798 for Cu, Cr, Pb, and Zn elements, respectively. 24 In soil analysis, Jantzi et al analyzed soil for forensic reasons using a 266 nm laser and the LIBS technology. Cu, Fe, Cr, Mg, Ba, Pb, Ti, Ca, Li, V, Mn, and Sr concentrations were estimated with a precision of less than 10%.…”