Skip to main content

ORIGINAL RESEARCH article

Front. Earth Sci.
Sec. Geoinformatics
Volume 12 - 2024 | doi: 10.3389/feart.2024.1474586

Geostatistics and artificial intelligence coupling: Advanced machine learning neural network regressor for experimental variogram modelling using Bayesian optimization

Provisionally accepted
Saâd Soulaimani Saâd Soulaimani 1,2*Ayoub Soulaimani Ayoub Soulaimani 3Kamal Abdelrahman Kamal Abdelrahman 4*Abdelhalim Miftah Abdelhalim Miftah 5*Mohammed S Fnais Mohammed S Fnais 4Biraj Kanti Mondal Biraj Kanti Mondal 6
  • 1 Resources Valorization, Environment and Sustainable Development Research Team (RVESD), Department of Mines, Rabat School of Mines, Rabat, Morocco
  • 2 Geology and Sustainable Mining Institute, Mohammed VI Polytechnic University, Ben Guerir, Morocco
  • 3 Natural resources and sustainable development Laboratory, Department of Earth Sciences, Faculty of Sciences, Ibn Tofail University, Kenitra, Morocco
  • 4 Department of Geology and Geophysics, College of Science, King Saud University, Riyadh, Saudi Arabia
  • 5 Faculty of Sciences and Techniques, Laboratory Physico-chemistry of Processes and Materials, Hassan Premier University, Settat, Beni Mellal-Khenifra, Morocco
  • 6 Department of Geography, Netaji Subhas Open University, Kolkata, West Bengal, India

The final, formatted version of the article will be published soon.

    Experimental variogram modelling is an essential process in geostatistics. The use of artificial intelligence (AI) is a new and advanced way of automating experimental variogram modelling. One part of this AI approach is the use of population search algorithms to fine-tune hyperparameters for better prediction performing. We use Bayesian optimization for the first time to find the optimal learning parameters for more precise neural network regressor for experimental variogram modelling. The goal is to leverage the capability of Bayesian optimization to consider previous regression results to improve the output of an experimental variogram using three experimental variograms as inputs and one as output for network training, calculated from ore grades of four orebodies, characterised by the same genetic aspect. In comparison of artificial neural network architectures, the Bayesian-optimized artificial neural network demonstrably achieved the superior Coefficient of determination in validation of 78.36%. This significantly outperformed a non-optimized wide, bilayer, and tri-layer network configurations, which yielded 32.94%, 14.00%, and -46.03%, respectively. The improved reliability of the Bayesian-optimized regressor demonstrates its superiority over traditional, non-optimized regressors, indicating that incorporating Bayesian optimization can significantly advance experimental variogram modelling, thus offering a more accurate and intelligent solution, combining geostatistics and artificial intelligence specifically machine learning for experimental variogram modelling.

    Keywords: geostatistics, Experimental variogram, machine learning, Neural Network, Bayesian optimization

    Received: 01 Aug 2024; Accepted: 27 Nov 2024.

    Copyright: © 2024 Soulaimani, Soulaimani, Abdelrahman, Miftah, Fnais and Mondal. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Saâd Soulaimani, Resources Valorization, Environment and Sustainable Development Research Team (RVESD), Department of Mines, Rabat School of Mines, Rabat, Morocco
    Kamal Abdelrahman, Department of Geology and Geophysics, College of Science, King Saud University, Riyadh, 11451, Saudi Arabia
    Abdelhalim Miftah, Faculty of Sciences and Techniques, Laboratory Physico-chemistry of Processes and Materials, Hassan Premier University, Settat, 26000, Beni Mellal-Khenifra, Morocco

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.