Stochastic machine learning modeling for the estimation of some uncertain parameters. Case study: Retardation factor in a radionuclide transport model

: pp. 311–317
Received: October 13, 2021
Accepted: February 07, 2022

Mathematical Modeling and Computing, Vol. 9, No. 2, pp. 311–317 (2022)

Mathematics, Computer Sciences and Applications Team (ERMIA), University of AbdelMalek Essaadi, ENSA of Tangier, Morocco
Mathematics, Computer Sciences and Applications Team (ERMIA), University of AbdelMalek Essaadi, ENSA of Tangier, Morocco

In the present work, we define a stochastic model using machine learning techniques to generate random fields of some uncertain parameters.  The proposed stochastic model is based on Bayesian inference and aims at reconstituting the parameters of interest and their credible intervals.  The main goal of this work is to define a model that estimates the values of the uncertain parameters known only by their distribution probability functions and some observed spatial measurements.  We note that this type of parameters may be associated with some mathematical models usually traduced by non-linear differential equations.  In our case, we study the uncertainty of the retardation factor in a radionuclide transport model.  To achieve a more realistic parameter estimation, Markov сhain Monte Carlo (MCMC) algorithms are applied.  We demonstrate that the obtained results confirm the feasibility of our proposed model and lead to a new understanding of contaminants' behavior.

  1. Ndaїrou F., Area I., Nieto J. J., Torres D. F. M.  Mathematical modeling of COVID-19 transmission dynamics with a case study of Wuhan.  Chaos, Solitons and Fractals. 135, 109846 (2020).
  2. Ma Y., Xiao X., Yu W., Shang W., Tan P., Wu Z., Ni M.  Mathematical modeling and numerical analysis of the discharge process of an alkaline zinc-cobalt battery.  Journal of Energy Storage. 30, 101432 (2020).
  3. Kareem W. A., Izawa S., Klein M., Fukunishi Y.  A hyperbolic partial differential equation model for filtering turbulent flows.  Computers & Fluids. 190, 156–167 (2019).
  4. Locatelli L., Binning P. J., Sanchez-Vila X., Søndergaard G. L., Rosenberg L., Bjerg P. L.  A simple contaminant fate and transport modelling tool for management and risk assessment of groundwater pollution from contaminated sites.  Journal of Contaminant Hydrology. 221, 35–49 (2019).
  5. Majee S., Shit G. C.  Modeling and simulation of blood flow with magnetic nanoparticles as carrier for targeted drug delivery in the stenosed artery.  European Journal of Mechanics – B/Fluids. 83, 42–57 (2020).
  6. Stadlbauer B., Cossettini A., Morales J. A., Pasterk E. D., Scarbolo P., Taghizadeh L., Heitzinger C., Selmi L.  Bayesian estimation of physical and geometrical parameters for nanocapacitor array biosensors.  Journal of Computational Physics. 397, 108874 (2019).
  7. Choi W., Kikumoto H., Choudhary R., Ooka R.  Bayesian inference for thermal response test parameter estimation and uncertainty assessment.  Applied Energy. 209, 306–321 (2018).
  8. Khan A. I., Liu J., Dutta P.  Bayesian inference for parameter estimation in lactoferrin-mediated iron transport across blood-brain barrier.  Biochimica et Biophysica Acta (BBA) – General Subjects. 1864 (3), 129459 (2020).
  9. Fang T., Mackillop W., Jiang W., Hildesheim A., Wacholder S., Chen B. E.  A Bayesian method for risk window estimation with application to HPV vaccine trial.  Computational Statistics & Data Analysis. 112, 53–62 (2017).
  10. Ji Y., Jiang X., Wan L.  Hierarchical least squares parameter estimation algorithm for two-input Hammerstein finite impulse response systems.  Journal of the Franklin Institute. 357 (8), 5019–5032 (2020).
  11. Li M., Liu X.  The least squares based iterative algorithms for parameter estimation of a bilinear system with autoregressive noise using the data filtering technique.  Signal Processing. 147, 23–34 (2018).
  12. Patmanidis S., Chignola R., Charalampidis A. C., Papavassilopoulos G. P.  A comparison between Nonlinear Least Squares and Maximum Likelihood estimation for the prediction of tumor growth on experimental data of human and rat origin.  Biomedical Signal Processing and Control. 54, 101639 (2019).
  13. El Yamani M. A., Lazaar S.  Conditional Assessment of Uncertain Parameters Using Palm Probabilistic Approach and Kriging Interpolation.  AI2SD 2019: Advanced Intelligent Systems for Sustainable Development (AI2SD’2019). 27–33 (2020).
  14. Mikhailov G. A.  Monte Carlo methods for solving problems with stochastic parameters.  Russian Journal of Numerical Analysis and Mathematical Modelling. 2 (2), 137–157 (1987).
  15. Lazaar S.  Random fields for uncertain parameters related to a transport model – Monte Carlo method.  Seminar at "Service de Métrologie Nucléaire". University Libre of Brussels, Belgium (2000).
  16. Díaz M. J. M., Lazaar S., Ortegón G. F.  On the numerical simulation of uncertain parameters in a radionuclide transport model.  Comptes Rendus Mathematique. 345 (7), 415–420 (2007).
  17. Lazaar S.  A numerical simulation of some uncertain parameters related to a radionuclide transport model.  Seminar at Departamento de ecuaciones diferenciales y análisis numérico of Seville University, Spain (2010).