Academic Journal of Computing & Information Science, 2024, 7(1); doi: 10.25236/AJCIS.2024.070114.
Qiao Sun1,2, Ideris Zakaria1
1Department of Civil Engineering, Infrastructure University, Kuala Lumpur, 430000, Malaysia
2College of Civil Engineering, Guangxi Electrical Polytechnic Institute, Nanning, 530000, China
With the widespread application of asphalt pavement in highway construction in China, especially in hot and humid areas like Guangdong and Guangxi, this type of pavement faces challenges such as softening, rutting, and accelerated aging under high temperatures and moist conditions. Traditional evaluation models have limitations in these specific environments. This study proposes a new asphalt pavement performance evaluation model using Self-Organizing Map (SOM) and Random Forest (RF) algorithms, re-evaluating and optimizing the weight of pavement performance evaluation indicators based on actual data from 14 highways in hot and humid areas. Through cross-validation and case analysis, the new model not only excels in accurately reflecting the actual performance of asphalt pavement in hot and humid areas but also provides more effective decision support for local asphalt pavement maintenance and management.
Humid and Hot Areas, Asphalt Pavement, Evaluation Model, SOM, RF
Qiao Sun, Ideris Zakaria. Comprehensive Evaluation of Asphalt Pavement Performance in Hot and Humid Areas Based on Self-Organizing Map and Random Forest Algorithms. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 1: 93-101. https://doi.org/10.25236/AJCIS.2024.070114.
[1] Xiao F, Xu L, Zhao Z, et al. Recent applications and developments of reclaimed asphalt pavement in China, 2010–2021. Sustainable Materials and Technologies, 2023: e00697.
[2] Li Z, Zhang Y, Fa C, et al. Investigation on the temperature distribution of asphalt overlay on the existing cement concrete pavement in hot-humid climate in southern China. Advances in Civil Engineering, 2021, 2021: 1-12.
[3] Wu C, Yang Y, Wang W, Cai Y, Yang H. Research on evaluation of asphalt pavement damage condition in humid and hot regions based on disease characteristics. Journal of Transportation Science and Engineering, 2023, (04): 9-16.
[4] Jia G, Yang B, Wang J, Luo D. Comparative study on pavement technical condition evaluation index systems between China and developed countries. Transportation Research, 2021, (04): 105-113.
[5] Dickinson E J. The hardening of Middle East petroleum asphalts in pavement surfacings. Association of Asphalt Paving Technologists Proceedings. 1980, 49: 30-63.
[6] Gong Z, Zhang L, Wu J, et al. Review of regulation techniques of asphalt pavement high temperature for climate change adaptation. Journal of Infrastructure Preservation and Resilience, 2022, 3(1): 1-18.
[7] Luo Y, Wu H, Song W, et al. Thermal fatigue and cracking behaviors of asphalt mixtures under different temperature variations. Construction and Building Materials, 2023, 369: 130623.
[8] Li Y, Wang Y H, Wu Q H, et al. The Quality Assessment of Pavement Performance Using the Entropy Weight-Variable Fuzzy Sets Model. Mathematical Problems in Engineering, 2022, 2022: 1-9.
[9] Knott J F, Jacobs J M, Sias J E, et al. A framework for introducing climate-change adaptation in pavement management. Sustainability, 2019, 11(16): 4382.
[10] Liu T, Yang S, Jiang X, et al. Adaptation measures for asphalt pavements to climate change in China. Journal of Cleaner Production, 2023, 415: 137861.
[11] Chen C, Deng Y, Li M, et al. Investigation of key climatic factors affecting asphalt pavement roughness in different climate regions. Transportation Research Part D: Transport and Environment, 2023, 122: 103877.
[12] Swarna S T, Hossain K, Mehta Y A, Bernier A. Climate change adaptation strategies for Canadian asphalt pavements; Part 1: Adaptation strategies. Journal of Cleaner Production, 2022, 363: 132313.
[13] Zeiada W, Dabous S A, Hamad K, Al-Ruzouq R, Khalil M A. Machine learning for pavement performance modelling in warm climate regions. Arabian Journal for Science and Engineering, 2020, 45(5): 4091-4109.
[14] Issa A, Samaneh H, Ghanim M. Predicting pavement condition index using artificial neural networks approach. Ain Shams Engineering Journal, 2022, 13(1): 101490.
[15] Philip B, Xu Z, Aljassmi H, et al. ASENN: attention-based selective embedding neural networks for road distress prediction. Journal of Big Data, 2023, 10(1): 1-19.
[16] Sari Y, Prakoso P B, Baskara A R. Road crack detection using support vector machine (SVM) and OTSU algorithm. 2019 6th International Conference on Electric Vehicular Technology (ICEVT). IEEE, 2019: 349-354.
[17] Hu M J, Ge R H, Qiu Q F, et al. Asphalt pavement performance evaluation based on SOM neural network. Applied Mechanics and Materials, 2012, 188: 219-225.
[18] Attoh‐Okine N O. Grouping Pavement Condition Variables for Performance Modeling Using Self‐Organizing Maps. Computer‐Aided Civil and Infrastructure Engineering, 2001, 16(2): 112-125.
[19] Zhang J, Guo W, Song B, Zhuo Y, Zhang Y. Prediction of asphalt pavement performance based on random forest. Journal of Beijing University of Technology, 2021, 47(11).
[20] Gong H, Sun Y, Shu X, et al. Use of random forests regression for predicting IRI of asphalt pavements. Construction and Building Materials, 2018, 189: 890-897.
[21] Kang J. Pavement Performance Prediction Using Machine Learning and Instrumentation in Smart Pavement. University of Waterloo, 2022.
[22] Zhou W, Shi X, Shi Z, Sun L. Investigation of cement concrete pavements and network-level service performance prediction model. Journal of Tongji University (Natural Science), 2006, 34(5): 624-628.