Neural Network Solution of an Inverse Problem in Raman Spectroscopy of Multi-component Solutions of Inorganic Salts

The paper presents a study into several aspects of solution of the inverse problem on determination of concentrations of components in a multi-component water solution of inorganic salts by processing Raman spectra of the solutions by perceptron type artificial neural networks. The studied aspects are: (1) determination of the optimal architecture of a multi-layer perceptron, (2) influence of the input dimensionality reduction by aggregation of adjacent spectral channels on the error of problem solution. The results are compared for two data arrays including spectra of solutions of: (1) 5 salts composed of 10 different ions (salt determination problem), and (2) 10 salts composed of 10 different ions (ion determination problem).

[1]  R. Sabesan,et al.  Polarization of the CO bond in H-bonded complexes: an infrared study , 1970 .

[2]  Chris W. Brown,et al.  Detection of ionic water pollutants by laser excited raman spectroscopy , 1972 .

[3]  Svetlana V. Patsaeva,et al.  The regularities of change of the 3100-3700 cm-1 band of water raman-scattering in salt aqueous-solutions , 1986 .

[4]  D. Combes,et al.  Effect of salts on dynamics of water: A Raman spectroscopy study , 1990 .

[5]  K. Furic,et al.  Raman spectroscopic study of sodium chloride water solutions , 2000 .

[6]  Tatiana A. Dolenko,et al.  Valence band of liquid water Raman scattering: some peculiarities and applications in the diagnostics of water media , 2000 .

[7]  J. Pulliainen,et al.  Application of an empirical neural network to surface water quality estimation in the Gulf of Finland using combined optical data and microwave data , 2002 .

[8]  I. G. Persiantsev,et al.  New opportunity solutions to inverse problems in laser spectroscopy involving artificial neural networks , 2002 .

[9]  Antonio Plaza,et al.  Nonlinear neural-network-based mixture model for estimating the concentration of nitrogen salts in turbid inland waters using hyperspectral imagery , 2004, SPIE Optics East.

[10]  W. Rudolph,et al.  Raman and Infrared Spectroscopic Investigations on Aqueous Alkali Metal Phosphate Solutions and Density Functional Theory Calculations of Phosphate—Water Clusters , 2007, Applied spectroscopy.

[11]  Xiao-yun Zhang,et al.  Application of Artificial Neural Networks to Classify Water Quality of the Yellow River , 2008, ACFIE.

[12]  Hongwei Ji,et al.  Simultaneous determination of calcium and magnesium in water using artificial neural network spectro-photometric method , 2010 .

[13]  Hongwei Ji,et al.  Simultaneous determination of iron and manganese in water using artificial neural network catalytic spectrophotometric method , 2012, Journal of Ocean University of China.

[14]  Xiangnan Liu,et al.  Artificial Neural Network and Random Forest Approaches for Modeling of Sea Surface Salinity , 2013 .

[15]  I. G. Persiantsev,et al.  Neural Network Approaches to Solution of the Inverse Problem of Identification and Determination of Partial Concentrations of Salts in Multi-сomponent Water Solutions , 2014, ICANN.

[16]  I. G. Persiantsev,et al.  Comparison of the quality of solving the inverse problems of spectroscopy of multi-component solutions with neural network methods and with the method of projection to latent structures , 2015, Optical Memory and Neural Networks.

[17]  I. G. Persiantsev,et al.  Neural Network Approaches to Solution of the Inverse Problem of Identification and Determination of the Ionic Composition of Multi-component Water Solutions , 2015, EANN.

[18]  Alexander Efitorov,et al.  Significant Feature Selection in Neural Network Solution of an Inverse Problem in Spectroscopy , 2015 .