Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement

Ramon Botella; Davide Lo Presti; Kamilla Vasconcelos; Kinga Bernatowicz; Adriana H. Martínez; Rodrigo Miró; Luciano Specht; Edith Arámbula Mercado; Gustavo Menegusso Pires; Emiliano Pasquini; Chibuike Ogbo; Francesco Preti; Marco Pasetto; Ana Jiménez del Barco Carrión; Antonio Roberto; Marko Orešković; Kranthi K. Kuna; Gurunath Guduru; Amy Epps Martin; Alan Carter; Gaspare Giancontieri; Ahmed Abed; Eshan Dave; Gabrielle Tebaldi

doi:10.1617/s11527-022-01933-9

Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement

Ramon Botella
, Davide Lo Presti^*
, Kamilla Vasconcelos
, Kinga Bernatowicz
, Adriana H. Martínez
, Rodrigo Miró
, Luciano Specht
, Edith Arámbula Mercado
, Gustavo Menegusso Pires
, Emiliano Pasquini
, Chibuike Ogbo
, Francesco Preti
, Marco Pasetto
, Ana Jiménez del Barco Carrión
, Antonio Roberto
, Marko Orešković
, Kranthi K. Kuna
, Gurunath Guduru
, Amy Epps Martin
, Alan Carter

Gaspare Giancontieri, Ahmed Abed, Eshan Dave, Gabrielle Tebaldi

^*Corresponding author for this work

Engineering Systems & Supply Chain Management

Universitat Politècnica de Catalunya
Università degli Studi di Palermo
University of Nottingham
Universidade de São Paulo
Vall d’Hebron Institute of Oncology (VHIO)
Federal University of Santa Maria
Texas A&M University System
Dynatest Latam
Università degli Studi di Padova
University of New Hampshire Durham
University of Parma
Universidad de Granada
University of Belgrade
Indian Institute of Technology Kharagpur
Ecole de Technologie Superieure and Cmind

Research output: Contribution to journal › Article › peer-review

14 Citations (SciVal)

26 Downloads (Pure)

Abstract

This paper describes the development of novel/state-of-art computational framework to accurately predict the degree of binder activity of a reclaimed asphalt pavement sample as a percentage of the indirect tensile strength (ITS) using a reduced number of input variables that are relatively easy to obtain, namely compaction temperature, air voids and ITS. Different machine learning (ML) techniques were applied to obtain the most accurate data representation model. Specifically, three ML techniques were applied: 6th-degree multivariate polynomial regression with regularization, artificial neural network and random forest regression. The three techniques produced models with very similar precision, reporting a mean absolute error ranging from 12.2 to 12.8% of maximum ITS on the test data set. The work presented in this paper is an evolution in terms of data analysis of the results obtained within the interlaboratory tests conducted by Task Group 5 of the RILEM Technical Committee 264 on Reclaimed Asphalt Pavement. Hence, despite it has strong bonds with this framework, this work was developed independently and can be considered as a natural follow-up.

Original language	English
Article number	112
Journal	Materials and Structures/Materiaux et Constructions
Volume	55
Issue number	4
Early online date	16 Apr 2022
DOIs	https://doi.org/10.1617/s11527-022-01933-9
Publication status	Published - May 2022

Bibliographical note

This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

Funding Information:
Part of this research was funded by the project RTI2018-096224-J-I00 that has been cofounded by the Spanish Ministry of Science and Innovation, inside the National Program for Fostering Excellence in Scientific and Technical Research, National Subprogram of Knowledge Generation, 2018 call, in the framework of the Spanish National Plan for Scientific and Technical Research and Innovation 2017–2020, and by the European Union, through the European Regional Development Fund, with the main objective of Promoting technological development, innovation and quality research. Part of this work was financially supported by the Italian Ministry of University and Research with the research Grant PRIN 2017 USR342 Urban Safety, Sustainability and Resilience.

Funding

Part of this research was funded by the project RTI2018-096224-J-I00 that has been cofounded by the Spanish Ministry of Science and Innovation, inside the National Program for Fostering Excellence in Scientific and Technical Research, National Subprogram of Knowledge Generation, 2018 call, in the framework of the Spanish National Plan for Scientific and Technical Research and Innovation 2017–2020, and by the European Union, through the European Regional Development Fund, with the main objective of Promoting technological development, innovation and quality research. Part of this work was financially supported by the Italian Ministry of University and Research with the research Grant PRIN 2017 USR342 Urban Safety, Sustainability and Resilience. The data used in this paper was generated by a project led by the TG-5 of the Technical Committee 264 Reclaimed Asphalt Pavement of the RILEM association. Especially, the authors would like to acknowledge Ahmed Abed (University of Nottingham, UK), Gustavo dos Santos Pinheiro (University of S?o Paulo ? Polytechnic School - Brazil), Gaspare Giancontieri (University of Palermo, Italy), Alexandros Margaritis (Universiteit Antwerpen, Belgium), Wim Van den Bergh (Universiteit Antwerpen, Belgium), Xavier Carbonneau (Colas), Shanin Eskandarsefatand and Loretta Venturini (Iterchimica S.r.A., Italy), Gordon Airey (University of Nottingham, UK), Nunzio Viscioneand Francesca Russo (University of Naples Federico II, Italy), Leda Christiane Lucena (Federal University of Campina Grande, Brazil), Timothy Sobieski (Texas Transportation Institute/Texas A&M University, USA), Luis Miguel Guti?rrez Klinsky (CCR NovaDutra, Brazil), Marco Salles Chamouton (CCR NovaDutra, Brazil) and Pedro Orlando Borges Junior (Federal University of Santa Mar?a, Brazil).

Keywords

Artificial neural networks
Degree of binder activity
Hot mix asphalt
Indirect tensile strength
Machine learning
Random forest
Reclaimed asphalt pavement
Recycling

Access to Document

10.1617/s11527-022-01933-9Licence: CC BY 4.0

Machine learning techniques to estimate the degree of binder activity
This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
Final published version, 967 KBLicence: CC BY 4.0

Cite this

Botella, R., Lo Presti, D., Vasconcelos, K., Bernatowicz, K., Martínez, A. H., Miró, R., Specht, L., Mercado, E. A., Pires, G. M., Pasquini, E., Ogbo, C., Preti, F., Pasetto, M., del Barco Carrión, A. J., Roberto, A., Orešković, M., Kuna, K. K., Guduru, G., Martin, A. E., ... Tebaldi, G. (2022). Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement. Materials and Structures/Materiaux et Constructions, 55(4), Article 112. https://doi.org/10.1617/s11527-022-01933-9

@article{3b4af9ca924943b79f799f197dd9e2ae,

title = "Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement",

abstract = "This paper describes the development of novel/state-of-art computational framework to accurately predict the degree of binder activity of a reclaimed asphalt pavement sample as a percentage of the indirect tensile strength (ITS) using a reduced number of input variables that are relatively easy to obtain, namely compaction temperature, air voids and ITS. Different machine learning (ML) techniques were applied to obtain the most accurate data representation model. Specifically, three ML techniques were applied: 6th-degree multivariate polynomial regression with regularization, artificial neural network and random forest regression. The three techniques produced models with very similar precision, reporting a mean absolute error ranging from 12.2 to 12.8\% of maximum ITS on the test data set. The work presented in this paper is an evolution in terms of data analysis of the results obtained within the interlaboratory tests conducted by Task Group 5 of the RILEM Technical Committee 264 on Reclaimed Asphalt Pavement. Hence, despite it has strong bonds with this framework, this work was developed independently and can be considered as a natural follow-up.",

keywords = "Artificial neural networks, Degree of binder activity, Hot mix asphalt, Indirect tensile strength, Machine learning, Random forest, Reclaimed asphalt pavement, Recycling",

author = "Ramon Botella and \{Lo Presti\}, Davide and Kamilla Vasconcelos and Kinga Bernatowicz and Mart{\'i}nez, \{Adriana H.\} and Rodrigo Mir{\'o} and Luciano Specht and Mercado, \{Edith Ar{\'a}mbula\} and Pires, \{Gustavo Menegusso\} and Emiliano Pasquini and Chibuike Ogbo and Francesco Preti and Marco Pasetto and \{del Barco Carri{\'o}n\}, \{Ana Jim{\'e}nez\} and Antonio Roberto and Marko Ore{\v s}kovi{\'c} and Kuna, \{Kranthi K.\} and Gurunath Guduru and Martin, \{Amy Epps\} and Alan Carter and Gaspare Giancontieri and Ahmed Abed and Eshan Dave and Gabrielle Tebaldi",

note = "This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Funding Information: Part of this research was funded by the project RTI2018-096224-J-I00 that has been cofounded by the Spanish Ministry of Science and Innovation, inside the National Program for Fostering Excellence in Scientific and Technical Research, National Subprogram of Knowledge Generation, 2018 call, in the framework of the Spanish National Plan for Scientific and Technical Research and Innovation 2017–2020, and by the European Union, through the European Regional Development Fund, with the main objective of Promoting technological development, innovation and quality research. Part of this work was financially supported by the Italian Ministry of University and Research with the research Grant PRIN 2017 USR342 Urban Safety, Sustainability and Resilience. ",

year = "2022",

month = may,

doi = "10.1617/s11527-022-01933-9",

language = "English",

volume = "55",

journal = "Materials and Structures/Materiaux et Constructions",

issn = "1359-5997",

publisher = "Springer Science and Business Media B.V.",

number = "4",

}

Botella, R, Lo Presti, D, Vasconcelos, K, Bernatowicz, K, Martínez, AH, Miró, R, Specht, L, Mercado, EA, Pires, GM, Pasquini, E, Ogbo, C, Preti, F, Pasetto, M, del Barco Carrión, AJ, Roberto, A, Orešković, M, Kuna, KK, Guduru, G, Martin, AE, Carter, A, Giancontieri, G, Abed, A, Dave, E & Tebaldi, G 2022, 'Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement', Materials and Structures/Materiaux et Constructions, vol. 55, no. 4, 112. https://doi.org/10.1617/s11527-022-01933-9

TY - JOUR

T1 - Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement

AU - Botella, Ramon

AU - Lo Presti, Davide

AU - Vasconcelos, Kamilla

AU - Bernatowicz, Kinga

AU - Martínez, Adriana H.

AU - Miró, Rodrigo

AU - Specht, Luciano

AU - Mercado, Edith Arámbula

AU - Pires, Gustavo Menegusso

AU - Pasquini, Emiliano

AU - Ogbo, Chibuike

AU - Preti, Francesco

AU - Pasetto, Marco

AU - del Barco Carrión, Ana Jiménez

AU - Roberto, Antonio

AU - Orešković, Marko

AU - Kuna, Kranthi K.

AU - Guduru, Gurunath

AU - Martin, Amy Epps

AU - Carter, Alan

AU - Giancontieri, Gaspare

AU - Abed, Ahmed

AU - Dave, Eshan

AU - Tebaldi, Gabrielle

N1 - This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. Funding Information: Part of this research was funded by the project RTI2018-096224-J-I00 that has been cofounded by the Spanish Ministry of Science and Innovation, inside the National Program for Fostering Excellence in Scientific and Technical Research, National Subprogram of Knowledge Generation, 2018 call, in the framework of the Spanish National Plan for Scientific and Technical Research and Innovation 2017–2020, and by the European Union, through the European Regional Development Fund, with the main objective of Promoting technological development, innovation and quality research. Part of this work was financially supported by the Italian Ministry of University and Research with the research Grant PRIN 2017 USR342 Urban Safety, Sustainability and Resilience.

PY - 2022/5

Y1 - 2022/5

N2 - This paper describes the development of novel/state-of-art computational framework to accurately predict the degree of binder activity of a reclaimed asphalt pavement sample as a percentage of the indirect tensile strength (ITS) using a reduced number of input variables that are relatively easy to obtain, namely compaction temperature, air voids and ITS. Different machine learning (ML) techniques were applied to obtain the most accurate data representation model. Specifically, three ML techniques were applied: 6th-degree multivariate polynomial regression with regularization, artificial neural network and random forest regression. The three techniques produced models with very similar precision, reporting a mean absolute error ranging from 12.2 to 12.8% of maximum ITS on the test data set. The work presented in this paper is an evolution in terms of data analysis of the results obtained within the interlaboratory tests conducted by Task Group 5 of the RILEM Technical Committee 264 on Reclaimed Asphalt Pavement. Hence, despite it has strong bonds with this framework, this work was developed independently and can be considered as a natural follow-up.

AB - This paper describes the development of novel/state-of-art computational framework to accurately predict the degree of binder activity of a reclaimed asphalt pavement sample as a percentage of the indirect tensile strength (ITS) using a reduced number of input variables that are relatively easy to obtain, namely compaction temperature, air voids and ITS. Different machine learning (ML) techniques were applied to obtain the most accurate data representation model. Specifically, three ML techniques were applied: 6th-degree multivariate polynomial regression with regularization, artificial neural network and random forest regression. The three techniques produced models with very similar precision, reporting a mean absolute error ranging from 12.2 to 12.8% of maximum ITS on the test data set. The work presented in this paper is an evolution in terms of data analysis of the results obtained within the interlaboratory tests conducted by Task Group 5 of the RILEM Technical Committee 264 on Reclaimed Asphalt Pavement. Hence, despite it has strong bonds with this framework, this work was developed independently and can be considered as a natural follow-up.

KW - Artificial neural networks

KW - Degree of binder activity

KW - Hot mix asphalt

KW - Indirect tensile strength

KW - Machine learning

KW - Random forest

KW - Reclaimed asphalt pavement

KW - Recycling

UR - https://www.scopus.com/pages/publications/85128307771

UR - https://link.springer.com/article/10.1617/s11527-022-01933-9

U2 - 10.1617/s11527-022-01933-9

DO - 10.1617/s11527-022-01933-9

M3 - Article

AN - SCOPUS:85128307771

SN - 1359-5997

VL - 55

JO - Materials and Structures/Materiaux et Constructions

JF - Materials and Structures/Materiaux et Constructions

IS - 4

M1 - 112

ER -

Machine learning techniques to estimate the degree of binder activity of reclaimed asphalt pavement

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this