zhpsЖурнал прикладной спектроскопииZhurnal Prikladnoii Spektroskopii0514-7506B. I. Stepanov Institute of Physics of the National Academy of Scienceszhps-1869Research ArticleАННОТАЦИИ АНГЛОЯЗЫЧНЫХ СТАТЕЙABSTRACTS ENGLISH-LANGUAGE ARTICLESАдаптивная оптимизация метода роя частиц на основе нейронной сети на радиальном базисе для классификации почв с помощью лазерно-искровой эмиссионной спектроскопииAdaptive Particle Swarm Optimization Radial Basis Neural Network (APSO-RBF)-Based Method for Classifying Soils by Laser-Induced Breakdown SpectroscopyChenJ.ChenJ.

Тайюань, Шаньси

Taiyuan, Shanxi

haoxiaojian@nuc.edu.cnHaoX.HaoX.

Тайюань, Шаньси

Taiyuan, Shanxi

haoxiaojian@nuc.edu.cnJiaR.JiaR.

Тайюань, Шаньси

Taiyuan, Shanxi

MoB.MoB.

Тайюань, Шаньси

Taiyuan, Shanxi

LiS.LiS.

Тайюань, Шаньси

Taiyuan, Shanxi

WeiH.WeiH.

Тайюань, Шаньси

Taiyuan, Shanxi

Национальная лаборатория фотоэлектрических динамических технологий и испытаний приборов в экстремальных условиях Северного университета Китая; Школа приборостроения и электроники Северного университета КитаяState Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, North University of China; School of Instrument and Electronics, North University of China202520052025923409409Copyright © Chen J., Hao X., Jia R., Mo B., Li S., Wei H., 20252025Chen J., Hao X., Jia R., Mo B., Li S., Wei H.Chen J., Hao X., Jia R., Mo B., Li S., Wei H.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://zhps.ejournal.by/jour/article/view/1869

Для классификации и идентификации стандартных образцов почвы использовано сочетание лазерно-искровой эмиссионной спектроскопии (LIBS) с адаптивной оптимизацией метода роя частиц на основе нейронной сети на радиальном базисе (APSO-RBF). Вычислительную сложность и избыточность исходных данных можно уменьшить путем выбора главных компонент спектральных данных LIBS в качестве входных, при этом образцы классифицировать быстро и точно. Для идентификации образцов почвы из 10 регионов в качестве входных данных модели APSO-RBF использованы шесть первых главных компонент, точность классификации тестового набора 98.81%. Производительность предлагаемой модели выше по сравнению с алгоритмами обратного распространения, APSO-RBF и RBF. Показано, что сочетание LIBS с моделью APSO-RBF значительно повышает точность идентификации почвы.

As soil is an important natural resource on the earth’s surface, the composition and characterization of soil have a significant impact on agricultural production, the ecological environment, and human health. Traditional soil identification methods need to deal with a large number of samples and complex chemical analysis, which requires a lot of time and effort. In this paper, a method combining laser-induced breakdown spectroscopy (LIBS) and adaptive particle swarm optimization radial basis neural network (APSO-RBF) is proposed to classify and identify soil standard samples from different geographical regions. By selecting the appropriate principal component of LIBS spectral data as input, the computational complexity can be reduced, the redundancy of the original spectral data can be reduced, and the samples can be classified quickly and accurately. For the soil from 10 different regions, the first 6 principal components with the highest contribution rate in principal component analysis were used as the input of APSO-RBF classification model, and the classification accuracy of the test set could reach 98.81%. In comparison with the back propagation (BP) algorithm, back propagation based on adaptive particle swarm optimization (APSO-RBF) algorithm and radial basis function neural network (RBF) algorithm, the powerful classification performance of the model is verified. The results show that LIBS technology greatly improved the accuracy of soil identification in different regions with the help of APSO-RBF model.

лазерно-искровая эмиссионная спектроскопияадаптивная оптимизация метода роя частицметод главных компонентклассификация почвыlaser-induced breakdown spectroscopyadaptive particle swarm optimizationprincipal componentSoil classificationThis research work has been awarded grants by the National Natural Science Foundation of China (No. 52475575), Shanxi Province Key R&D Program Projects (No. 202302150101016), the State Key Laboratory of Quantum Optics and Optical Quantum Devices (Shanxi University) Open project (No. KF202301), and Central Guided Local Science and Technology Development Funding Program (YDZJSX2024D033)This research work has been awarded grants by the National Natural Science Foundation of China (No. 52475575), Shanxi Province Key R&D Program Projects (No. 202302150101016), the State Key Laboratory of Quantum Optics and Optical Quantum Devices (Shanxi University) Open project (No. KF202301), and Central Guided Local Science and Technology Development Funding Program (YDZJSX2024D033)ReferencesJ. R. Bacon, O. T. Butler, W. R. L. Cairns, O. Cavoura, J. M. Cook, C. M. Davidson, R. Mertz-Kraus, J. Anal. At. Spectrometry, 39, No. 1, 11–65 (2024), doi: 10.1039/d3ja90044d.J. R. Bacon, O. T. Butler, W. R. L. Cairns, O. Cavoura, J. M. Cook, C. M. Davidson, R. Mertz-Kraus, J. Anal. At. Spectrometry, 39, No. 1, 11–65 (2024), doi: 10.1039/d3ja90044d.W. Yang, F. Li, S. Lyu, Q. Zhang, Y. Zhao, J. Anal. At. Spectrometry, 38, No. 9, 1830–1840 (2023), doi: 10.1039/d3ja00120b.W. Yang, F. Li, S. Lyu, Q. Zhang, Y. Zhao, J. Anal. At. Spectrometry, 38, No. 9, 1830–1840 (2023), doi: 10.1039/d3ja00120b.B. M. Butler, J. Palarea-Albaladejo, K. D. Shepherd, K. M. Nyambura, E. K. Towett, A. M. Sila, S. Hillier, Geoderma, 375 (2020), doi: 10.1016/j.geoderma.2020.114474.B. M. Butler, J. Palarea-Albaladejo, K. D. Shepherd, K. M. Nyambura, E. K. Towett, A. M. Sila, S. Hillier, Geoderma, 375 (2020), doi: 10.1016/j.geoderma.2020.114474.A. L. Sikora, L. W. Maguire, R. W. Nairn, R. C. Knox, Environ. Monitoring and Asses., 193, No. 8 (2021), doi: 10.1007/s10661-021-09275-9.A. L. Sikora, L. W. Maguire, R. W. Nairn, R. C. Knox, Environ. Monitoring and Asses., 193, No. 8 (2021), doi: 10.1007/s10661-021-09275-9.S. Krzebietke, M. Daszykowski, H. Czarnik-Matusewicz, I. Stanimirova, L. Pieszczek, S. Sienkiewicz, J. Wierzbowska, Talanta, 251 (2023), doi: 10.1016/j.talanta.2022.123749.S. Krzebietke, M. Daszykowski, H. Czarnik-Matusewicz, I. Stanimirova, L. Pieszczek, S. Sienkiewicz, J. Wierzbowska, Talanta, 251 (2023), doi: 10.1016/j.talanta.2022.123749.J. G. Decaillon, M. Bickel, C. Hill, T. Altzitzoglou, Appl. Rad. and Isotopes, 61, No. 2-3, 409–413 (2004), doi: 10.1016/j.apradiso.2004.03.016.J. G. Decaillon, M. Bickel, C. Hill, T. Altzitzoglou, Appl. Rad. and Isotopes, 61, No. 2-3, 409–413 (2004), doi: 10.1016/j.apradiso.2004.03.016.S. Zhu, L. Gao, M. Zheng, H. Liu, B. Zhang, L. Liu, Y. Wang, Talanta, 118, 210–216 (2014), doi: 10.1016/j.talanta.2013.09.044.S. Zhu, L. Gao, M. Zheng, H. Liu, B. Zhang, L. Liu, Y. Wang, Talanta, 118, 210–216 (2014), doi: 10.1016/j.talanta.2013.09.044.J. Ning, J. Zhao, L. Meng, Y. Yang, Anal. Lett., 48, No. 6, 1021–1029 (2015), doi: 10.1080/00032719.2014.966375.J. Ning, J. Zhao, L. Meng, Y. Yang, Anal. Lett., 48, No. 6, 1021–1029 (2015), doi: 10.1080/00032719.2014.966375.D. Zhang, J. Nie, H. Ma, X. Niu, S. Shi, F. Chen, L. Guo, X. Ji, Anal. Chim. Acta, 1236 (2022), doi: 10.1016/j.aca.2022.340552.D. Zhang, J. Nie, H. Ma, X. Niu, S. Shi, F. Chen, L. Guo, X. Ji, Anal. Chim. Acta, 1236 (2022), doi: 10.1016/j.aca.2022.340552.J. Wang, X. Hao, B. Pan, X. Huang, H. Sun, P. Pei, Opt. Express, 31, No. 5 (2023), doi: 10.1364/oe.481822.J. Wang, X. Hao, B. Pan, X. Huang, H. Sun, P. Pei, Opt. Express, 31, No. 5 (2023), doi: 10.1364/oe.481822.X. Zhang, Y. Ge, E. Wan, Y. Liu, J. Yao, Plasma Sci. Technol., 24, No. 8 (2022), doi: 10.1088/20586272/ac639b.X. Zhang, Y. Ge, E. Wan, Y. Liu, J. Yao, Plasma Sci. Technol., 24, No. 8 (2022), doi: 10.1088/20586272/ac639b.R. Gaudiuso, E. Ewusi-Annan, W. Xia, N. Melikechi, Spectrochim. Acta B: At. Spectrosc., 171 (2020), doi: 10.1016/j.sab.2020.105931.R. Gaudiuso, E. Ewusi-Annan, W. Xia, N. Melikechi, Spectrochim. Acta B: At. Spectrosc., 171 (2020), doi: 10.1016/j.sab.2020.105931.W. Zhao, C. Li, C. Yan, H. Min, Y. An, S. Liu, Anal. Chim. Acta, 1166 (2021), doi: 10.1016/j.aca.2021.338574.W. Zhao, C. Li, C. Yan, H. Min, Y. An, S. Liu, Anal. Chim. Acta, 1166 (2021), doi: 10.1016/j.aca.2021.338574.J. Qi, T. Zhang, H. Tang, H. Li, Spectrochim. Acta B: At. Spectrosc., 149, 288–293 (2018), doi: 10.1016/j.sab.2018.09.006.J. Qi, T. Zhang, H. Tang, H. Li, Spectrochim. Acta B: At. Spectrosc., 149, 288–293 (2018), doi: 10.1016/j.sab.2018.09.006.J. Moros, L. M. Cabalín, J. J. Laserna, Anal. Chim. Acta, 1191 (2022), doi: 10.1016/j.aca.2021.339294.J. Moros, L. M. Cabalín, J. J. Laserna, Anal. Chim. Acta, 1191 (2022), doi: 10.1016/j.aca.2021.339294.D. Zhang, J. Ding, Z. Feng, R. Yang, Y. Yang, S. Yu, B. Xie, J. Zhu, Spectrochim. Acta B: At. Spectrosc., 180 (2021), doi: 10.1016/j.sab.2021.106192.D. Zhang, J. Ding, Z. Feng, R. Yang, Y. Yang, S. Yu, B. Xie, J. Zhu, Spectrochim. Acta B: At. Spectrosc., 180 (2021), doi: 10.1016/j.sab.2021.106192.X. Jin, G. Yang, X. Sun, D. Qu, S. Li, G. Chen, C. Li, D. Tian, L. Yao, J. Anal. Atom. Spectrometry, 38, No. 1, 243–252 (2023), doi: 10.1039/d2ja00290f.X. Jin, G. Yang, X. Sun, D. Qu, S. Li, G. Chen, C. Li, D. Tian, L. Yao, J. Anal. Atom. Spectrometry, 38, No. 1, 243–252 (2023), doi: 10.1039/d2ja00290f.M. Yao, G. Fu, T. Chen, M. Liu, J. Xu, H. Zhou, X. He, L. Huang, J. Anal. At. Spectrometry, 36, No. 2, 361–367 (2021), doi: 10.1039/d0ja00317d.M. Yao, G. Fu, T. Chen, M. Liu, J. Xu, H. Zhou, X. He, L. Huang, J. Anal. At. Spectrometry, 36, No. 2, 361–367 (2021), doi: 10.1039/d0ja00317d.D. Stefas, N. Gyftokostas, S. Couris, Spectrochim. Acta B: At. Spectroscopy, 172 (2020), doi: 10.1016/j.sab.2020.105969.D. Stefas, N. Gyftokostas, S. Couris, Spectrochim. Acta B: At. Spectroscopy, 172 (2020), doi: 10.1016/j.sab.2020.105969.H. Li, T. Liu, Y. Fu, W. Li, M. Zhang, X. Yang, D. Song, J. Wang, Y. Wang, M. Huang, Chin. Opt. Lett., 21, No. 4 (2023), doi: 10.3788/col202321.043001.H. Li, T. Liu, Y. Fu, W. Li, M. Zhang, X. Yang, D. Song, J. Wang, Y. Wang, M. Huang, Chin. Opt. Lett., 21, No. 4 (2023), doi: 10.3788/col202321.043001.G. Song, S. Zhu, W. Zhang, B. Hu, F. Zhu, H. Zhang, T. Sun, K. T. V. Grattan, Appl. Optics, 61, No. 35 (2022), doi: 10.1364/ao.472220.G. Song, S. Zhu, W. Zhang, B. Hu, F. Zhu, H. Zhang, T. Sun, K. T. V. Grattan, Appl. Optics, 61, No. 35 (2022), doi: 10.1364/ao.472220.W. Hao, X. Hao, Y. Yang, X. Liu, Y. Liu, P. Sun, R. Sun, J. Anal. At. Spectrometry, 36, No. 11, 2509–2518 (2021), doi: 10.1039/d1ja00078k.W. Hao, X. Hao, Y. Yang, X. Liu, Y. Liu, P. Sun, R. Sun, J. Anal. At. Spectrometry, 36, No. 11, 2509–2518 (2021), doi: 10.1039/d1ja00078k.Q. Li, Q. Xiong, S. Ji, Y. Yu, C. Wu, H. Yi, Neurocomputing, 431, 7–22 (2021), doi: 10.1016/j.neucom.2020.12.032.Q. Li, Q. Xiong, S. Ji, Y. Yu, C. Wu, H. Yi, Neurocomputing, 431, 7–22 (2021), doi: 10.1016/j.neucom.2020.12.032.Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, M. Yao, Appl. Optics, 58, No. 7 (2019), doi: 10.1364/ao.58.001631.Z. Luo, L. Zhang, T. Chen, M. Liu, J. Chen, H. Zhou, M. Yao, Appl. Optics, 58, No. 7 (2019), doi: 10.1364/ao.58.001631.S. Vijh, P. Gaurav, H. M. Pandey, Neural Comp. Appl., 35, No. 33, 23711–23724 (2020), doi: 10.1007/s00521-020-05362-z.S. Vijh, P. Gaurav, H. M. Pandey, Neural Comp. Appl., 35, No. 33, 23711–23724 (2020), doi: 10.1007/s00521-020-05362-z.A. A. Yahya, A. Osman, M. S. El-Bashir, Swarm and Evolutionary Comp., 34, 18–32 (2017), doi: 10.1016/j.swevo.2016.11.005.A. A. Yahya, A. Osman, M. S. El-Bashir, Swarm and Evolutionary Comp., 34, 18–32 (2017), doi: 10.1016/j.swevo.2016.11.005.O. Hamdy, Z. Abdel-Salam, M. Abdel-Harith, Appl. Opt., 61, No. 34 (2022), doi: 10.1364/ao.470835.O. Hamdy, Z. Abdel-Salam, M. Abdel-Harith, Appl. Opt., 61, No. 34 (2022), doi: 10.1364/ao.470835.J. Wang, X. Hao, B. Pan, X. Huang, H. Sun, P. Pei, Opt. Lett., 48, No. 2 (2023), doi: 10.1364/ol.478629.J. Wang, X. Hao, B. Pan, X. Huang, H. Sun, P. Pei, Opt. Lett., 48, No. 2 (2023), doi: 10.1364/ol.478629.J. Chen, X. Hao, B. Mo, S. Li, J. Ma, X. Liang, Z. Wang, H. Zhang, J. Anal. At. Spectrometry, 39, No. 10, 2382–2394 (2024), doi: 10.1039/d4ja00143e.J. Chen, X. Hao, B. Mo, S. Li, J. Ma, X. Liang, Z. Wang, H. Zhang, J. Anal. At. Spectrometry, 39, No. 10, 2382–2394 (2024), doi: 10.1039/d4ja00143e.J. Chen, J. Pisonero, S. Chen, X. Wang, Q. Fan, Y. Duan, Spectrochim. Acta B: At. Spectroscopy, 166 (2020), doi: 10.1016/j.sab.2020.105801.J. Chen, J. Pisonero, S. Chen, X. Wang, Q. Fan, Y. Duan, Spectrochim. Acta B: At. Spectroscopy, 166 (2020), doi: 10.1016/j.sab.2020.105801.H. Jin, X. Hao, B. Mo, J. Anal. At. Spectrometry, 38, No. 11, 2280–2290 (2023), doi: 10.1039/d3ja00254c.H. Jin, X. Hao, B. Mo, J. Anal. At. Spectrometry, 38, No. 11, 2280–2290 (2023), doi: 10.1039/d3ja00254c.C. Wang, J. Wang, J. Wang, H. Du, J. Wang, Laser Phys., 31, No. 3 (2021), doi:10.1088/15556611/abdfc8.C. Wang, J. Wang, J. Wang, H. Du, J. Wang, Laser Phys., 31, No. 3 (2021), doi:10.1088/15556611/abdfc8.H. Jin, X. Hao, N. Li, Y. Han, B. Mo, S. Zhang, J. Anal. At. Spectrometry, 39, No. 7 (2024), doi: 10.1039/d4ja00062e.H. Jin, X. Hao, N. Li, Y. Han, B. Mo, S. Zhang, J. Anal. At. Spectrometry, 39, No. 7 (2024), doi: 10.1039/d4ja00062e.Q. Zeng, G. Chen, W. Li, Z. Li, J. Tong, M. Yuan, B. Wang, H. Ma, Y. Liu, L. Guo, H. Yu. Plasma Sci. Technol., 24, No. 8 (2022), doi: 10.1088/2058-6272/ac72e3.Q. Zeng, G. Chen, W. Li, Z. Li, J. Tong, M. Yuan, B. Wang, H. Ma, Y. Liu, L. Guo, H. Yu. Plasma Sci. Technol., 24, No. 8 (2022), doi: 10.1088/2058-6272/ac72e3.N. d. A. Porto, J. V. Roque, C. A. Wartha, W. Cardoso, L. A. Peternelli, M. H. P. Barbosa, R. F. Teófilo, Spectrochim. Acta A: Mol. Biomolec. Spectrosc., 218, 69–75 (2019), doi: 10.1016/j.saa.2019.03.114.N. d. A. Porto, J. V. Roque, C. A. Wartha, W. Cardoso, L. A. Peternelli, M. H. P. Barbosa, R. F. Teófilo, Spectrochim. Acta A: Mol. Biomolec. Spectrosc., 218, 69–75 (2019), doi: 10.1016/j.saa.2019.03.114.

The authors declare that there are no conflicts of interest present.