TY  - JOUR
T1  - OPTIMIZED MACHINE LEARNING METHODS FOR PREDICTION OF MARSHALL STABILITY VALUES
TT  - OPTIMIZED MACHINE LEARNING METHODS FOR PREDICTION OF MARSHALL STABILITY VALUES
AU  - Gürfidan, Remzi
AU  - Erten, Kemal
PY  - 2025
DA  - August
Y2  - 2025
DO  - 10.46519/ij3dptdi.1660315
JF  - International Journal of 3D Printing Technologies and Digital Industry
JO  - IJ3DPTDI
PB  - Kerim ÇETİNKAYA
WT  - DergiPark
SN  - 2602-3350
SP  - 220
EP  - 228
VL  - 9
IS  - 2
LA  - en
AB  - This study evaluates the performance of machine learning algorithms in predicting Marshall stability values to improve quality control processes in highway pavements. Coring is a costly, time-consuming and destructive method, which increases the need for alternative prediction models. In this context, Extra Trees, Random Forest, Gradient Boosting, K-Nearest Neighbours (KNN) and AdaBoost algorithms were used to predict the stability values obtained from core samples and error metrics were analyzed. In the study, the effects of hyperparameter optimization on model performance were examined in detail. The results show that the Extra Trees algorithm has the best prediction performance with an R² of 97.62% and an accuracy of 99.71%. Random Forest and Gradient Boosting algorithms also showed improvements after optimization, but their error rates remained higher compared to the Extra Trees model. The KNN model showed moderate success, while the AdaBoost model showed the lowest performance with an R² value of 58.87%. The findings reveal that machine learning algorithms can be used effectively in the prediction of stability values obtained from core samples and model performance can be improved by optimizing the right hyperparameters. The study shows that data-driven approaches can be less costly and time efficient in quality control processes.
KW  - Machine Learning
KW  - Marshall Stability
KW  - Core Sample
KW  - Hyperparameter Optimization
N2  - This study evaluates the performance of machine learning algorithms in predicting Marshall stability values to improve quality control processes in highway pavements. Coring is a costly, time-consuming and destructive method, which increases the need for alternative prediction models. In this context, Extra Trees, Random Forest, Gradient Boosting, K-Nearest Neighbours (KNN) and AdaBoost algorithms were used to predict the stability values obtained from core samples and error metrics were analyzed. In the study, the effects of hyperparameter optimization on model performance were examined in detail. The results show that the Extra Trees algorithm has the best prediction performance with an R² of 97.62% and an accuracy of 99.71%. Random Forest and Gradient Boosting algorithms also showed improvements after optimization, but their error rates remained higher compared to the Extra Trees model. The KNN model showed moderate success, while the AdaBoost model showed the lowest performance with an R² value of 58.87%. The findings reveal that machine learning algorithms can be used effectively in the prediction of stability values obtained from core samples and model performance can be improved by optimizing the right hyperparameters. The study shows that data-driven approaches can be less costly and time efficient in quality control processes.
CR  - 1. Llopis-Castelló, D., García-Segura, T., Montalbán-Domingo, L., Sanz-Benlloch, A., and Pellicer, E., “Influence of pavement structure, traffic, and weather on urban flexible pavement deterioration”, Sustainability, Vol. 12, Issue 22, Pages 9717, 2020.
CR  - 2. Haslett, K.E., Knott, J.F., Stoner, A.M., Sias, J.E., Dave, E.V., Jacobs, J.M., and Hayhoe, K., “Climate change impacts on flexible pavement design and rehabilitation practices”, Road Materials and Pavement Design, Vol. 22, Issue 9, Pages 2098-2112, 2021.
CR  - 3. Bhandari, S., Luo, X., and Wang, F., “Understanding the effects of structural factors and traffic loading on flexible pavement performance”, International Journal of Transportation Science and Technology, Vol. 12, Issue 1, Pages 258-272, 2023.
CR  - 4. Raffaniello, A., Bauer, M., Safiuddin, M., and El-Hakim, M., “Traffic and climate impacts on rutting and thermal cracking in flexible and composite pavements”, Infrastructures, Vol. 7, Issue 8, Pages 100, 2022.
CR  - 5. Deng, Y., Luo, X., Zhang, Y., and Lytton, R.L., “Evaluation of flexible pavement deterioration conditions using deflection profiles under moving loads”, Transportation Geotechnics, Vol. 26, Pages 100434, 2021.
CR  - 6. Özgan, E., “Determining the Stability of Asphalt Concrete at Varying Temperatures and Exposure Times Using Destructive and Non-Destructive Methods”, Journal of Applied Sciences, Vol. 7, Issue 24, Pages 3870-3879, 2007.
CR  - 7. İskender, E., “Asfalt kaplama kalınlığının karışım homojenitesi üzerindeki etkisi”, Gümüşhane Üniversitesi Fen Bilimleri Dergisi, Vol. 9, Issue 4, Pages 681-690, 2019.
CR  - 8. Köfteci, S., “Bitümlü sıcak karışımlardan geri dönüşüm yolu ile elde edilen agregaların performanslarının değerlendirilmesi: Deneysel bir çalışma”, Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Vol. 6, Issue 2, Pages 535-545, 2017.
CR  - 9. Shaffie, E., Jaya, R.P., Ahmad, J., Arshad, A.K., Zihan, M.A., and Shiong, F., “Prediction model of the coring asphalt pavement performance through response surface methodology”, Advances in Materials Science and Engineering, Vol. 2022, Issue 1, Pages 6723396, 2022.
CR  - 10. Dan, H.C., Huang, Z., Lu, B., and Li, M., “Image-driven prediction system: Automatic extraction of aggregate gradation of pavement core samples integrating deep learning and interactive image processing framework”, Construction and Building Materials, Vol. 453, Pages 139056, 2024.
CR  - 11. Braham, A., Hossain, Z., Yang, S., and Chowdhury, N., “Evaluating performance of asphalt pavement based on data collected during IRP”, Final Report for Arkansas State Highway and Transportation Department, TRC, Report No. 1404, Pages 1404, 2015.
CR  - 12. Kıyıldı, R.K., “Yapay sinir ağları ile Marshall stabilite değerinin tahmini”, Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Vol. 10, Issue 2, Pages 627-633, 2021.
CR  - 13. Yıldırım, Z.B., Karacasu, M., and Okur, V., “Optimisation of Marshall Design criteria with central composite design in asphalt concrete”, International Journal of Pavement Engineering, Vol. 21, Issue 5, Pages 666-676, 2020.
CR  - 14. Chen, H., Xu, Q., Chen, S., and Zhang, Z., “Evaluation and design of fiber-reinforced asphalt mixtures”, Materials & Design, Vol. 30, Issue 7, Pages 2595-2603, 2009.
CR  - 15. Xu, B., Chen, J., Zhou, C., and Wang, W., “Study on Marshall Design parameters of porous asphalt mixture using limestone as coarse aggregate”, Construction and Building Materials, Vol. 124, Pages 846-854, 2016.
CR  - 16. Heydari, S., Hajimohammadi, A., Javadi, N.H.S., and Khalili, N., “The use of plastic waste in asphalt: A critical review on asphalt mix design and Marshall properties”, Construction and Building Materials, Vol. 309, Pages 125185, 2021.
17. Duran Aşkar, D., “Yapay Zeka Destekli Asfalt Performans Tahmini”, Yüksek Lisans Tezi, İskenderun Teknik Üniversitesi, Fen Bilimleri Enstitüsü, Hatay, 2018.
CR  - 18. Aljassar, A.H., Metwali, S., and Ali, M.A., “Effect of filler types on Marshall stability and retained strength of asphalt concrete”, International Journal of Pavement Engineering, Vol. 5, Issue 1, Pages 47-51, 2004.
CR  - 19. Changra, A., and Singh, E.G., “Comparison of Marshall Stability values of the different bitumen mixes with crumb rubber”, IOP Conference Series: Earth and Environmental Science, Vol. 1110, No. 1, Pages 012034, 2023.
CR  - 20. Phung, B.N., Le, T.H., Nguyen, M.K., Nguyen, T.A., and Ly, H.B., “Practical numerical tool for Marshall stability prediction based on machine learning: An application for asphalt concrete containing basalt fiber”, Journal of Science and Transport Technology, Pages 26-43, 2023.
CR  - 21. Erten, K.M., and Terzi, S., “Technical Investigation of the Usability for Foamed Bitumen Stabilized Materials in Asphalt Pavements”, Journal of Engineering Research, Vol. 11, Issue 3, Pages 1-10, 2023.
CR  - 22. Breiman, L., and Cutler, R.A., “Random forests machine learning”, Journal of Clinical Microbiology, Vol. 2, Pages 199-228, 2001.
CR  - 23. Geurts, P., Ernst, D., and Wehenkel, L., “Extremely randomized trees”, Machine Learning, Vol. 63, Pages 3-42, 2006.
CR  - 24. Hammed, M.M., AlOmar, M.K., Khaleel, F., and Al-Ansari, N., “An extra tree regression model for discharge coefficient prediction: Novel, practical applications in the hydraulic sector and future research directions”, Mathematical Problems in Engineering, Vol. 2021, Pages 1-19, 2021.
CR  - 25. Willmott, C., and Matsuura, K., “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance”, Climate Research, Vol. 30, Pages 79–82, 2005.
UR  - https://doi.org/10.46519/ij3dptdi.1660315
L1  - https://dergipark.org.tr/tr/download/article-file/4701566
ER  -