Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation

Time resolution is one of the limiting factors when using Ground Penetrating Radar (GPR) techniques to characterize thin layers in the subsurface, such as the tack coat in pavements. To evaluate this residual bituminous emulsion at the interface between the wearing course and the binder course, we h...

Full description

Saved in:
Bibliographic Details
Main Authors: Grégory Andreoli, Amine Ihamouten, Franziska Schmidt, Mai Lan Nguyen, David Souriou, Xavier Dérobert
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Transportation Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666691X25000399
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321658425278464
author Grégory Andreoli
Amine Ihamouten
Franziska Schmidt
Mai Lan Nguyen
David Souriou
Xavier Dérobert
author_facet Grégory Andreoli
Amine Ihamouten
Franziska Schmidt
Mai Lan Nguyen
David Souriou
Xavier Dérobert
author_sort Grégory Andreoli
collection DOAJ
description Time resolution is one of the limiting factors when using Ground Penetrating Radar (GPR) techniques to characterize thin layers in the subsurface, such as the tack coat in pavements. To evaluate this residual bituminous emulsion at the interface between the wearing course and the binder course, we have developed an inverse method based on a hybrid data processing approach that combines machine learning (ML) algorithms with Full-Waveform Inversion (FWI). Adding the dielectric permittivity of the wearing course (extracted via FWI) as a structural a priori input into the SVM/SVR models has demonstrated the strong potential of this methodology on synthetic time domain signals. This research, proposes extending such a methodology through experimental campaigns. To carry out this study, three distinct campaigns have been planned, namely on: Hot-Mix Asphalt (HMA)-controlled slabs manufactured in the laboratory; a controlled full-scale structure using the Gustave Eiffel University fatigue carousel (Nantes, France); and a new, yet-to-be-used, road in France. These experiments serve to validate the performance improvements of various classification and regression SVM/SVR algorithms when adding the dielectric permittivity of the wearing course. Herein will be compared the results of the global approach, without preprocessing raw time domain signals, with the developed hybrid model.
format Article
id doaj-art-ed123c90944f41f78f2a71f9c0ce3490
institution Kabale University
issn 2666-691X
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Transportation Engineering
spelling doaj-art-ed123c90944f41f78f2a71f9c0ce34902025-08-20T03:49:41ZengElsevierTransportation Engineering2666-691X2025-06-012010033910.1016/j.treng.2025.100339Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validationGrégory Andreoli0Amine Ihamouten1Franziska Schmidt2Mai Lan Nguyen3David Souriou4Xavier Dérobert5MAST/MIT Research Group, Gustave Eiffel University, Nantes, France; Corresponding author.MAST/LAMES Research Group, Gustave Eiffel University, Nantes, FranceMAST/EMGCU, Research Group, Gustave Eiffel University, Marne-la-Vallée, FranceMAST/LAMES Research Group, Gustave Eiffel University, Nantes, FranceFI-NDT, Nantes, FranceGERS/GeoEND Research Group, Gustave Eiffel University - FI-NDT, Nantes, FranceTime resolution is one of the limiting factors when using Ground Penetrating Radar (GPR) techniques to characterize thin layers in the subsurface, such as the tack coat in pavements. To evaluate this residual bituminous emulsion at the interface between the wearing course and the binder course, we have developed an inverse method based on a hybrid data processing approach that combines machine learning (ML) algorithms with Full-Waveform Inversion (FWI). Adding the dielectric permittivity of the wearing course (extracted via FWI) as a structural a priori input into the SVM/SVR models has demonstrated the strong potential of this methodology on synthetic time domain signals. This research, proposes extending such a methodology through experimental campaigns. To carry out this study, three distinct campaigns have been planned, namely on: Hot-Mix Asphalt (HMA)-controlled slabs manufactured in the laboratory; a controlled full-scale structure using the Gustave Eiffel University fatigue carousel (Nantes, France); and a new, yet-to-be-used, road in France. These experiments serve to validate the performance improvements of various classification and regression SVM/SVR algorithms when adding the dielectric permittivity of the wearing course. Herein will be compared the results of the global approach, without preprocessing raw time domain signals, with the developed hybrid model.http://www.sciencedirect.com/science/article/pii/S2666691X25000399Tack coatGPRMachine learningFWIHybridization
spellingShingle Grégory Andreoli
Amine Ihamouten
Franziska Schmidt
Mai Lan Nguyen
David Souriou
Xavier Dérobert
Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
Transportation Engineering
Tack coat
GPR
Machine learning
FWI
Hybridization
title Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
title_full Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
title_fullStr Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
title_full_unstemmed Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
title_short Hybrid ML/FWI method using GPR data to evaluate the tack coat characteristics in pavements: Experimental validation
title_sort hybrid ml fwi method using gpr data to evaluate the tack coat characteristics in pavements experimental validation
topic Tack coat
GPR
Machine learning
FWI
Hybridization
url http://www.sciencedirect.com/science/article/pii/S2666691X25000399
work_keys_str_mv AT gregoryandreoli hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation
AT amineihamouten hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation
AT franziskaschmidt hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation
AT mailannguyen hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation
AT davidsouriou hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation
AT xavierderobert hybridmlfwimethodusinggprdatatoevaluatethetackcoatcharacteristicsinpavementsexperimentalvalidation