Reflections on Artificial Intelligence applications: physical models and datadriven models as research paradigms in road infrastructure
DOI:
https://doi.org/10.58922/transportes.v32i3.3045Keywords:
Artificial Intelligence. Machine learning. Data science. Pavements.Abstract
This paper reflects on applications of Artificial Intelligence in pavement research, whose increasing use represents an epistemological turn in the area, mostly built on top of physical models. In the search for solutions, data-driven models can produce satisfactory results without explaining the underlying physical processes that led to these results. Applications such as automated distress surveying and smart cities are exemplified, and some of the associated risks are recognized, such as ethical issues and data bias. It highlights how innovations should not only improve immediate performance, but contribute to a more complete and sustainable understanding of road infrastructure. AI tools have a transformative potential, as well as the ability to attract students and young researchers, which is essential for the advancement of any area of knowledge. It is hoped that the type of reflection and thinking provided herein will encourage discussions and collaborations necessary to navigating the challenges posed and maximizing the benefits of emerging technologies.
Downloads
References
Abdelaziz, N.; R.T.A. El-Hakim; S.M. El-Badawy et al. (2020) International Roughness Index prediction model for flexible pavements. The International Journal of Pavement Engineering, v. 21, n. 1, p. 88-99. DOI: 10.1080/10298436.2018.1441414. DOI: https://doi.org/10.1080/10298436.2018.1441414
Alnedawi, A.; R. Al-Ameri e K.P. Nepal (2019) Neural network-based model for prediction of permanent deformation of unbound granular materials. Journal of Rock Mechanics and Geotechnical Engineering, v. 11, n. 6, p. 1231-1242. DOI: 10.1016/j. jrmge.2019.03.005. DOI: https://doi.org/10.1016/j.jrmge.2019.03.005
Araújo, C. B. C.; F.A. Souza Filho; J.B. Soares et al. (2023) The effects of climate change on the performance of asphaltic pavement structures. International Journal of Advances in Engineering and Technology, v. 16, n. 3, p. 66.
Brega, J.R.F. (1997) Utilização de Redes Neurais Artificiais em um Sistema de Gerência de Pavimentos. Tese (doutorado). Escola de Engenharia de São Carlos, Universidade de São Paulo. São Carlos.
Coutinho Neto, B. (2000) Redes Neurais Artificiais Como Procedimento para Retroanálise de Pavimentos Flexíveis. Dissertação (mestrado). Escola de Engenharia de São Carlos, Universidade de São Paulo. São Carlos.
Cranmer, M. (2024) The Next Great Scientific Theory is Hiding Inside a Neural Network. New York: Simons Foundation.
Eidgahee, D.R.; H. Jahangir; N. Solatifar et al. (2022) Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches. Neural Computing & Applications, v. 34, n. 20, p. 17289-17314. DOI: 10.1007/ s00521-022-07382-3. DOI: https://doi.org/10.1007/s00521-022-07382-3
Furtado, L.S.; J.B. Soares e V. Furtado (2024a) A task-oriented framework for generative AI in design. Journal of Creativity, v. 34, n. 2, p. 100086. DOI: 10.1016/j.yjoc.2024.100086. DOI: https://doi.org/10.1016/j.yjoc.2024.100086
Furtado, L.S.; H. Busgaib; L. Babadopulos et al. (2024b) Prompts para análise de dados espaciais sobre defeitos de pavimentos com o ChatGPT-4. In XXII Congreso Ibero Latinoamericano del Asfalto. Madrid: ASEFMA.
Gonçalves, H.B.B.; K.B. Paz; L.F.A.L. Babadopulos et al. (2024) Continuous visual survey of road pavement using convolutional neural networks and smartphone technology: a data-driven approach. In Proceedings of the International Conference on Maintenance and Rehabilitation of Pavements. Cham: Springer, p. 203-213. Vol. 523. DOI: 10.1007/978-3-031-63584-7_21. DOI: https://doi.org/10.1007/978-3-031-63584-7_21
Ghorbani, B.; A. Arulrajah; G. Narsilio; S. Horpibulsuk; M.W. Bo (2020) Development of genetic-based models for predicting the resilient modulus of cohesive pavement subgrade soils. Soils and Foundations, v. 60, n. 2, p. 398-412. DOI: 10.1016/j.sandf.2020.02.010. DOI: https://doi.org/10.1016/j.sandf.2020.02.010
Kaloop, M.R.; D. Kumar; P. Samui et al. (2019) Particle Swarm Optimization Algorithm-Extreme Learning Machine (PSO-ELM) model for predicting resilient modulus of stabilized aggregate bases. Applied Sciences, v. 9, n. 16, p. 3221. DOI: 10.3390/app9163221. DOI: https://doi.org/10.3390/app9163221
Kissinger, H. A., E. Schmidt e D. Huttenlocher (2024) ChatGPT Heralds an intellectual revolution. WSJ.
Lucas Jr., J.L.O.; L.F.A.L. Babadopulos e J.B. Soares. (2019) Aggregate-binder adhesiveness assessment and investigation of the influence of morphological and physico-chemical properties of mineral aggregates. Road Materials and Pavement Design, v. 20, n. sup1, p. S79-S94. DOI: 10.1080/14680629.2019.1588773. DOI: https://doi.org/10.1080/14680629.2019.1588773
Majidifard, H.; B. Jahangiri; P. Rath et al. (2021) Developing a prediction model for rutting depth of asphalt mixtures using gene expression programming. Construction & Building Materials, v. 267, p. 120543. DOI: 10.1016/j.conbuildmat.2020.120543. DOI: https://doi.org/10.1016/j.conbuildmat.2020.120543
Mariano, A.L.G. (2023) Uso de Aprendizado de Máquina Interpretável para Avaliação da Deformação Permanente em Misturas Asfálticas. Dissertação (mestrado). Programa de Pós-graduação em Engenharia de Transportes, Universidade Federal do Ceará. Fortaleza.
Melo, C. D. R., Soares, J. B., Parente Jr., E., & Silva, J. C. T. (2024) Gaussian process-based estimation of asphalt mixture master stiffness curve under data scarcity. No prelo.
Ministério da Ciência e Tecnologia (2024) IA para o Bem de Todos: Proposta de Plano Brasileiro de Inteligência Artificial 2024-2028. Brasília.
Mota, B.C.; B.P. Ignez; G.V. Silva et al. (2023) Construção e análise de banco de dados de misturas asfálticas com ferramentas de inteligência artificial. In Anais do 37º Congresso de Pesquisa e Ensino em Transportes. Santos, SP.
Naderpour, H.; A.H. Rafiean e P. Fakharian (2018) Compressive strength prediction of environmentally friendly concrete using artificial neural networks. Journal of Building Engineering, v. 16, p. 213-219. DOI: 10.1016/j.jobe.2018.01.007. DOI: https://doi.org/10.1016/j.jobe.2018.01.007
Nunes, D.E. e V.F.S. Mota (2019) A participatory sensing framework to classify road surface quality. Journal of Internet Services and Applications, v. 10, n. 1, p. 13. DOI: 10.1186/s13174-019-0111-1. DOI: https://doi.org/10.1186/s13174-019-0111-1
Piryonesi, S.M. e T. El-Diraby (2021) Climate change impact on infrastructure: a machine learning solution for predicting pavement condition index. Construction & Building Materials, v. 306, p. 124905. DOI: 10.1016/j.conbuildmat.2021.124905. DOI: https://doi.org/10.1016/j.conbuildmat.2021.124905
Prince, S.J.D. (2023) Understanding Deep Learning. Cambridge: The MIT Press.
Ribeiro, T.R. e F.H.L. Oliveira (2023) Desenvolvimento de modelos de previsão de coeficiente de atrito em pistas de pouso e decolagem brasileiras com Redes Neurais Artificiais. Revista Transportes, v. 31, n. 2, e2792. DOI: 10.58922/transportes.v31i2.2792. DOI: https://doi.org/10.58922/transportes.v31i2.2792
Saha, S.; F. Gu; X. Luo et al. (2018) Use of an artificial neural network approach for the prediction of resilient modulus for unbound granular material. Soil and Foundation, v. 2672, n. 52, p. 23-33. DOI: https://doi.org/10.1177/0361198118756881
Serafim, M.O.; C.A. Sousa; L.C. Almeida et al. (2023) Automated detection of defects and vertical signs on roadways using images produced by drivers. Journal of Testing and Evaluation, v. 51, n. 4, p. 1897. DOI: 10.1520/JTE20220298. DOI: https://doi.org/10.1520/JTE20220298
Soares, J.B. (2020) Reflexões sobre um programa de pesquisa científica para a infraestrutura viária do Brasil. Revista Transportes, v. 28, n. 5, p. 154-168. DOI: 10.14295/transportes.v28i5.2174. DOI: https://doi.org/10.14295/transportes.v28i5.2174
Soares, J. B. (2024) Physics-Inspired vs. Data-Driven: Paradigms in Pavement Infrastructure Research (Keynote Lecture). In 14th ISAP Conference, International Society for Asphalt Pavements. Montreal, Canadá: ÉTS.
Souza, W.M.; A.J.A. Ribeiro e C.A.U. Silva (2022a) Use of ANN and visual-manual classification for prediction of soil properties for paving purposes. The International Journal of Pavement Engineering, v. 23, n. 8, p. 1482-1490. DOI: 10.1080/10298436.2020.1807546. DOI: https://doi.org/10.1080/10298436.2020.1807546
Souza, W.M.; A.J.A. Ribeiro e S.H.A. Barroso (2022b) Estimating the resilient modulus of subgrade materials using visual inspection. Transportes, v. 30, n. 3, p. 2738. DOI: 10.14295/transportes.v30i3.2738. DOI: https://doi.org/10.14295/transportes.v30i3.2738
Specht, L.P. e O. Khatchatourian (2014) Application of artificial intelligence to modelling asphalt-rubber viscosity. The International Journal of Pavement Engineering, v. 15, n. 9, p. 1-11. DOI: 10.1080/10298436.2014.893316. DOI: https://doi.org/10.1080/10298436.2014.893316
Specht, L.P.; O. Khatchatourian; L.A.T. Brito et al. (2007) Modeling of asphalt-rubber rotational viscosity by statistical analysis and neural networks. Materials Research, v. 10, n. 1, p. 69-74. DOI: https://doi.org/10.1590/S1516-14392007000100015
Tong, Z.; J. Gao e H. Zhang (2017) Recognition, location, measurement, and 3D reconstruction of concealed cracks using convolutional neural networks. Construction & Building Materials, v. 146, p. 775-787. DOI: 10.1016/j.conbuildmat.2017.04.097. DOI: https://doi.org/10.1016/j.conbuildmat.2017.04.097
Xu, Y.; Z. Xie; Y. Feng et al. (2018) Road extraction from high-resolution remote sensing imagery using deep learning. Remote Sensing, v. 10, n. 9, p. 1461. DOI: 10.3390/rs10091461. DOI: https://doi.org/10.3390/rs10091461
Zhang, A.; K.C.P. Wang; B. Li et al. (2017) Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network. Computer-Aided Civil and Infrastructure Engineering, v. 32, n. 10, p. 805-819. DOI: 10.1111/mice.12297. DOI: https://doi.org/10.1111/mice.12297
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Jorge Barbosa Soares
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who submit papers for publication by TRANSPORTES agree to the following terms:
- Authors retain copyright and grant TRANSPORTES the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of this journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in TRANSPORTES.
- Authors are allowed and encouraged to post their work online (e.g., in institutional repositories or on their website) after publication of the article. Authors are encouraged to use links to TRANSPORTES (e.g., DOIs or direct links) when posting the article online, as TRANSPORTES is freely available to all readers.
- Authors have secured all necessary clearances and written permissions to published the work and grant copyright under the terms of this agreement. Furthermore, the authors assume full responsibility for any copyright infringements related to the article, exonerating ANPET and TRANSPORTES of any responsibility regarding copyright infringement.
- Authors assume full responsibility for the contents of the article submitted for review, including all necessary clearances for divulgation of data and results, exonerating ANPET and TRANSPORTES of any responsibility regarding to this aspect.
