Quantitative Analysis of Lead and Cadmium Heavy Metal Elements in Soil Based on Principal Component Analysis and Broad Learning System
LÜ Shu-bin1, 2, YANG Wan-qi1, 2, LI Fu-sheng1, 2*
1. School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2. Yangtze River Delta Research Institute, University of Electronic Science and Technology of China (Huzhou), Huzhou 313001, China
Abstract：X-ray fluorescence analysis (XRF) is a remarkably effective analytical technique for quantitatively studying heavy metal elements in soils. Due to matrix effects and elemental interferences, existing machine-learning methods suffer from inadequate performance and instability in predicting lead (Pb) and cadmium (Cd) concentrations using soil XRF spectra. Therefore, this paper proposes a PCA-BLS method for the XRF quantitative analysis of heavy metals in soil based on principal component analysis (PCA) combined with the broad learning system (BLS). It can accurately, efficiently, and stably determine concentrations of Pb and Cd in soil. First, the 56 standard soil data are feature-reduced using PCA. The first three principal components of Pb and Cd are selected as features. Then, the optimal principal component features are fed into the width learning system for calibration and testing. Using the grid search determine the optimal network structure. The three optimum parameters for the BLS corresponding to the Pb and Cd elements are 2, 11, 11 and 3, 19, 15, respectively. Using support vector regression (SVR), BP neural network, and the original BLS compared with the PCA-BLS. PCA-BLS achieved performances of 0.954, 1.433, and 1.014 in the R2, RMSE, and MAPE corresponding to Pb. In the quantitative Cd, PCA-BLS obtains the R2 of 0.982, RMSE of 1.215, and MAPE of 1.059. Grid search visualization demonstrates the stable performance of PCA-BLS in predicting two heavy metal elements. The experimental results show that PCA-BLS can effectively correct for matrix effects and interferences in soil XRF. The PCA-BLS is a promising method for quantitative XRF spectroscopy that accurately predicts Pb and Cd elemental concentrations while maintaining model stability.
Key words：Soil heavy metals; XRF quantitative analysis; Broad learning system; Principal component analysis
吕树彬，杨婉琪，李福生. 基于主成分分析和宽度学习系统的土壤铅镉重金属元素定量分析[J]. 光谱学与光谱分析, 2024, 44(07): 1852-1857.
LÜ Shu-bin, YANG Wan-qi, LI Fu-sheng. Quantitative Analysis of Lead and Cadmium Heavy Metal Elements in Soil Based on Principal Component Analysis and Broad Learning System. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 1852-1857.
[1] Li F, Yang W, Ma Q, et al. Measurement Science and Technology, 2021, 32(10): 105501.
[2] Bai B, Xu T, Nie Q, et al. International Journal of Heat and Mass Transfer, 2020, 153: 119573.
[3] Sergeev A P, Buevich A G, Baglaeva E M, et al. Catena, 2019, 174: 425.
[4] Zhou W, Yang H, Xie L, et al. Catena, 2021, 202: 105222.
[5] Pessanha S, Guilherme A, Carvalho M L. Applied Physics A, 2009, 97(2): 497.
[6] Marini F, Walczak B. Chemometrics and Intelligent Laboratory Systems, 2015, 149: 153.
[7] JIANG Xiao-yu, LI Fu-sheng, WANG Qing-ya, et al(江晓宇, 李福生, 王清亚, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(5): 1535.
[8] Abdi H, Williams L J. Wiley Interdisciplinary Reviews: Computational Statistics, 2010, 2(4): 433.
[9] Chen C L P, Liu Z. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(1): 10.
[10] Chen C L P, Liu Z, Feng S. IEEE Transactions on Neural Networks and Learning Systems, 2018, 30(4): 1191.
[11] Wang J, Lyu S, Chen C L, et al. Journal of Intelligent Manufacturing, 2023, 34(4): 1779.
[12] Yang W, Li F, Zhao Y, et al. Analytical Methods, 2022, 14(40)：3944.
[13] QIAO Ji-hong, YUAN Xi-yan, WU Jing-zhu, et al(乔继红, 苑希岩, 吴静珠, 等). Journal of Food Safety & Quality(食品安全质量检测学报), 2023, 14(5): 9.
[14] Cheng J, Yu D, Yang Y. Mechanical Systems and Signal Processing, 2007, 21(3): 1197.
[15] Goh A T C. Artificial Intelligence in Engineering, 1995, 9(3): 143.
