Abstract
This study is devoted to inverse problems of optical spectroscopy that include qualitative and quantitative analysis of sample composition by its spectra. We consider the methods of optical absorption, IR absorption, and Raman spectroscopy for determining the concentrations of heavy metal ions in water. Since this problem has neither an analytical nor a direct numerical solution, practically the only way to solve it is by using approximation methods, including machine learning methods based on experimental data. Obtaining spectra is a laborious and expensive process, which makes it difficult to obtain a training sample of sufficient size. At the same time, experimental spectra are sensitive to impurities contained in water, including those of organic origin which are specific to each source. Therefore, it is not possible to create a universal training dataset with good representativity and providing a stable solution on any sample. Thus, in this paper, it is proposed to use the transfer learning approach to improve the quality of the neural network solution. The neural networks are pretrained on a basic dataset containing the spectra of solutions prepared in distilled water. Then, fine tuning and testing of the networks are carried out on specific datasets containing the spectra of solutions prepared in river water taken from different rivers. It is demonstrated that the transfer learning approach consistently provides the best results on the river water data.
REFERENCES
M. Jaishankar, T. Tseten, N. Anbalagan, et al., Interdiscip. Toxicol. 7, 60 (2014). https://doi.org/10.2478/intox-2014-0009
X. Wu, S. J. Cobbina, G. Mao, et al., Environ. Sci. Pollut. Res. 23, 8244 (2016). https://doi.org/10.1007/s11356-016-6333-x
C. H. Pitot and P. Y. Dragan, Casarett and Doull’s Toxicology, 5th ed. (McGraw-Hill, New York, 1996), pp. 201–260.
P. Koedrith, H. Kim, J. I. Weon, and Y. R. Seo, Int. J. Hyg. Environ. Health 216, 587 (2013). https://doi.org/10.1016/j.ijheh.2013.02.010
H. Brandl, Heavy Metals in the Environment: Origin, Interaction and Remediation (Elsevier, London, 2005). https://doi.org/10.1016/j.jcis.2005.05.069
Z. L. He, X. E. Yang, and P. J. Stoffella, J. Trace Elem. Med. Biol. 19 (2–3), 125 (2005). https://doi.org/10.1016/j.jtemb.2005.02.010
P. Lochyński, M. Szymańska, S. Charazińska, et al., J. Water Resour. Ind. 30, 100216 (2023). https://doi.org/10.1016/j.wri.2023.100216
T. H. Kauffmann and M. D. Fontana, J. Sens. Actuators, B 209, 154 (2015). https://doi.org/10.1016/j.snb.2014.11.108
T. R. Crompton, Determination of Anions in Natural and Treated Waters (CRC Press, London, 2002). https://doi.org/10.1201/9781482289190
S. Kulkarni, S. Dhokpande, and J. Kaware, Int. J. Adv. Eng. Res. Sci. 2(9), 35 (2015).
H. M. M. P. D. H. A. Aziz, Doctoral Dissertation in Philosophy (Brunel Univ., London, 2005).
S. A. Burikov, S. A. Dolenko, T. A. Dolenko, and I. G. Persiantsev, J. Opt. Mem. Neural Networks 19, 140 (2010). https://doi.org/10.3103/S1060992X10020049
I. V. Isaev, N. D. Trifonov, O. E. Sarmanova, et al., Proc. SPIE 11458, 171 (2020).https://doi.org/10.1117/12.2564398
X. Zhang, F. Zhang, H. T. Kung, et al., Int. J. Environ. Res. Public Health 15, 2390 (2018). https://doi.org/10.3390/ijerph15112390
X. Qin, F. Gao, and G. Chen, J. Water Res. 46(4), 1133 (2012). https://doi.org/10.1016/j.watres.2011.12.005
T. A. Dolenko, S. A. Burikov, A. O. Efitorov, and S. A. Dolenko, Int. J. Comput. Inf. Eng. 8, 1345 (2014). https://doi.org/10.5281/zenodo.1096475
S. A. Burikov, T. A. Dolenko, V. V. Fadeev, and A. V. Sugonyaev, Pattern Recognit. Image Anal. 17, 554 (2007). https://doi.org/10.1134/S1054661807040141
Keras, Deep learning for humans, https://keras.io/. Cited June 19, 2023.
Funding
This study has been conducted at the expense of the grant of the Russian Science Foundation no. 19-11-00333, https://rscf.ru/en/project/19-11-00333/.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Guskov, A.A., Isaev, I.V., Burikov, S.A. et al. Transfer Learning for Neural Network Solution of an Inverse Problem in Optical Spectroscopy. Moscow Univ. Phys. 78 (Suppl 1), S115–S121 (2023). https://doi.org/10.3103/S0027134923070111
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0027134923070111