Machine learning-driven identification and predictive mapping of clogging regimes in porous media

<p>Clogging in porous media critically limits the performance of subsurface and filtration systems, yet conventional models often rely on oversimplified, single-parameter thresholds to predict its behavior. This study develops a unified, machine learning–based framework to identify, characteri...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ahmed Elrahmani (17128837) (author)
مؤلفون آخرون: Riyadh I. Al-Raoush (2366107) (author), Harris Sajjad Rabbani (14489205) (author), Thomas D. Seers (8759187) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513541025824768
author Ahmed Elrahmani (17128837)
author2 Riyadh I. Al-Raoush (2366107)
Harris Sajjad Rabbani (14489205)
Thomas D. Seers (8759187)
author2_role author
author
author
author_facet Ahmed Elrahmani (17128837)
Riyadh I. Al-Raoush (2366107)
Harris Sajjad Rabbani (14489205)
Thomas D. Seers (8759187)
author_role author
dc.creator.none.fl_str_mv Ahmed Elrahmani (17128837)
Riyadh I. Al-Raoush (2366107)
Harris Sajjad Rabbani (14489205)
Thomas D. Seers (8759187)
dc.date.none.fl_str_mv 2025-08-20T15:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.jhydrol.2025.134106
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Machine_learning-driven_identification_and_predictive_mapping_of_clogging_regimes_in_porous_media/30018754
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Chemical engineering
Environmental engineering
Information and computing sciences
Machine learning
Fine particle migration
Permeability reduction
Clogging regimes
Machine learning
Dimensionless analysis
Predictive mapping
dc.title.none.fl_str_mv Machine learning-driven identification and predictive mapping of clogging regimes in porous media
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Clogging in porous media critically limits the performance of subsurface and filtration systems, yet conventional models often rely on oversimplified, single-parameter thresholds to predict its behavior. This study develops a unified, machine learning–based framework to identify, characterize, and predict clogging behavior using dimensionless parameters representing pore structure, hydrodynamics, and particle–surface interactions. A total of 2,500 pore-scale realizations, generated with a pre-trained model informed by CFD-DEM simulations, were analyzed using four key metrics: permeability reduction, clogged fraction of throats, clogging zone length, and critical throat size of clogging. Three distinct clogging regimes emerged statistically (namely, surface, deep distributed, and sparse) each with its distinguished features. The framework further introduces high-resolution Phase Diagram and Clogging Diagnostic Maps that link input conditions to spatial clogging patterns and severity. These tools provide a scalable, interpretable foundation for optimizing system performance in managed aquifer recharge, enhanced oil recovery, groundwater remediation, and filtration system design.</p><h2>Other Information</h2> <p> Published in: Journal of Hydrology<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jhydrol.2025.134106" target="_blank">https://dx.doi.org/10.1016/j.jhydrol.2025.134106</a></p>
eu_rights_str_mv openAccess
id Manara2_ef9ebdff7d9fd7fd8cd86b49284e512a
identifier_str_mv 10.1016/j.jhydrol.2025.134106
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30018754
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Machine learning-driven identification and predictive mapping of clogging regimes in porous mediaAhmed Elrahmani (17128837)Riyadh I. Al-Raoush (2366107)Harris Sajjad Rabbani (14489205)Thomas D. Seers (8759187)EngineeringChemical engineeringEnvironmental engineeringInformation and computing sciencesMachine learningFine particle migrationPermeability reductionClogging regimesMachine learningDimensionless analysisPredictive mapping<p>Clogging in porous media critically limits the performance of subsurface and filtration systems, yet conventional models often rely on oversimplified, single-parameter thresholds to predict its behavior. This study develops a unified, machine learning–based framework to identify, characterize, and predict clogging behavior using dimensionless parameters representing pore structure, hydrodynamics, and particle–surface interactions. A total of 2,500 pore-scale realizations, generated with a pre-trained model informed by CFD-DEM simulations, were analyzed using four key metrics: permeability reduction, clogged fraction of throats, clogging zone length, and critical throat size of clogging. Three distinct clogging regimes emerged statistically (namely, surface, deep distributed, and sparse) each with its distinguished features. The framework further introduces high-resolution Phase Diagram and Clogging Diagnostic Maps that link input conditions to spatial clogging patterns and severity. These tools provide a scalable, interpretable foundation for optimizing system performance in managed aquifer recharge, enhanced oil recovery, groundwater remediation, and filtration system design.</p><h2>Other Information</h2> <p> Published in: Journal of Hydrology<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.jhydrol.2025.134106" target="_blank">https://dx.doi.org/10.1016/j.jhydrol.2025.134106</a></p>2025-08-20T15:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.jhydrol.2025.134106https://figshare.com/articles/journal_contribution/Machine_learning-driven_identification_and_predictive_mapping_of_clogging_regimes_in_porous_media/30018754CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300187542025-08-20T15:00:00Z
spellingShingle Machine learning-driven identification and predictive mapping of clogging regimes in porous media
Ahmed Elrahmani (17128837)
Engineering
Chemical engineering
Environmental engineering
Information and computing sciences
Machine learning
Fine particle migration
Permeability reduction
Clogging regimes
Machine learning
Dimensionless analysis
Predictive mapping
status_str publishedVersion
title Machine learning-driven identification and predictive mapping of clogging regimes in porous media
title_full Machine learning-driven identification and predictive mapping of clogging regimes in porous media
title_fullStr Machine learning-driven identification and predictive mapping of clogging regimes in porous media
title_full_unstemmed Machine learning-driven identification and predictive mapping of clogging regimes in porous media
title_short Machine learning-driven identification and predictive mapping of clogging regimes in porous media
title_sort Machine learning-driven identification and predictive mapping of clogging regimes in porous media
topic Engineering
Chemical engineering
Environmental engineering
Information and computing sciences
Machine learning
Fine particle migration
Permeability reduction
Clogging regimes
Machine learning
Dimensionless analysis
Predictive mapping