Extended artificial neural networks: incorporation of a priori chemical knowledge enables use of ion selective electrodes for in-situ measurement of ions at environmentally relevant levels.

A novel artificial neural network (ANN) architecture is proposed which explicitly incorporates a priori system knowledge, i.e., relationships between output signals, while preserving the unconstrained non-linear function estimator characteristics of the traditional ANN. A method is provided for architecture layout, disabling training on a subset of neurons, and encoding system knowledge into the neuron structure. The novel architecture is applied to raw readings from a chemical sensor multi-probe (electric tongue), comprised of off-the-shelf ion selective electrodes (ISEs), to estimate individual ion concentrations in solutions at environmentally relevant concentrations and containing environmentally representative ion mixtures. Conductivity measurements and the concept of charge balance are incorporated into the ANN structure, resulting in (1) removal of estimation bias typically seen with use of ISEs in mixtures of unknown composition and (2) improvement of signal estimation by an order of magnitude or more for both major and minor constituents relative to use of ISEs as stand-alone sensors and error reduction by 30-50% relative to use of standard ANN models. This method is suggested as an alternative to parameterization of traditional models (e.g., Nikolsky-Eisenman), for which parameters are strongly dependent on both analyte concentration and temperature, and to standard ANN models which have no mechanism for incorporation of system knowledge. Network architecture and weighting are presented for the base case where the dot product can be used to relate ion concentrations to both conductivity and charge balance as well as for an extension to log-normalized data where the model can no longer be represented in this manner. While parameterization in this case study is analyte-dependent, the architecture is generalizable, allowing application of this method to other environmental problems for which mathematical constraints can be explicitly stated.

[1]  P. Bühlmann,et al.  Selectivity of potentiometric ion sensors. , 2000, Analytical chemistry.

[2]  Lorenzo Leija,et al.  Determination of Ammonium Ion Employing an Electronic Tongue Based on Potentiometric Sensors , 2003 .

[3]  Conrad Bessant,et al.  Optimisation of a neural network model for calibration of voltammetric data , 2002 .

[4]  D L Massart,et al.  Application of neural network calibrations to an halide ISE array. , 2000, Talanta.

[5]  Conrad Bessant,et al.  A liquid handling system for the automated acquisition of data for training, validating and testing calibration models , 2003 .

[6]  Alisa Rudnitskaya,et al.  A flow injection system based on chalcogenide glass sensors for the determination of heavy metals , 2000 .

[7]  Xavier Muñoz-Berbel,et al.  EIS multianalyte sensing with an automated SIA system-An electronic tongue employing the impedimetric signal. , 2007, Talanta.

[8]  F Despagne,et al.  Neural networks in multivariate calibration. , 1998, The Analyst.

[9]  Antonella Macagnano,et al.  Multicomponent analysis on polluted waters by means of an electronic tongue , 1997 .

[10]  P. Hernández,et al.  An electronic tongue using potentiometric all-solid-state PVC-membrane sensors for the simultaneous quantification of ammonium and potassium ions in water , 2003, Analytical and bioanalytical chemistry.

[11]  S. Alegret,et al.  Sequential injection system with higher dimensional electrochemical sensor signals Part 2. Potentiometric e-tongue for the determination of alkaline ions. , 2005, Talanta.

[12]  H. Maier,et al.  The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters , 1996 .

[13]  C. Natale,et al.  Evaluation of Italian wine by the electronic tongue: recognition, quantitative analysis and correlation with human sensory perception , 2003 .

[14]  Indrajeet Chaubey,et al.  A simplified approach to quantifying predictive and parametric uncertainty in artificial neural network hydrologic models , 2007 .

[15]  W. M. Haynes.  CRC Handbook of Chemistry and Physics , 1990 .

[16]  Teresa Bernarda Ludermir,et al.  A multi-objective memetic and hybrid methodology for optimizing the parameters and performance of artificial neural networks , 2010, Neurocomputing.

[17]  Corrado Di Natale,et al.  Multicomponent analysis of heavy metal cations and inorganic anions in liquids by a non-selective chalcogenide glass sensor array , 1996 .

[18]  W. E. Morf.  The Principles of Ion-Selective Electrodes and of Membrane Transport , 2012 .

[19]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[20]  A. Petrović,et al.  Identifying dissolved phosphorus source areas and predicting transport from an urban watershed using distributed hydrologic modeling , 2007 .

[21]  Amy Mueller,et al.  DEVELOPMENT OF A COMBINED MULTI- SENSOR/SIGNAL PROCESSING ARCHITECTURE FOR IMPROVED IN-SITU QUANTIFICATION OF THE CHARGE BALANCE OF NATURAL WATERS , 2012 .

[22]  E. Mazzone,et al.  Application of Electronic Tongue for Quantitative Analysis of Mineral Water and Wine , 1999 .

[23]  L. Bachas,et al.  Can temperature be used to tune the selectivity of membrane ion-selective electrodes? , 2010, Analytical chemistry.

[24]  R. C. Weast.  CRC Handbook of Chemistry and Physics , 1973 .

[25]  Y. Vlasov,et al.  Multisensor system on the basis of an array of non-specific chemical sensors and artificial neural networks for determination of inorganic pollutants in a model groundwater. , 2001, Talanta.

[26]  M. Muir.  Physical Chemistry , 1888, Nature.

[27]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.