Tanvir Ahmed
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tanvir Ahmed has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Mayzan Isied
Department of Civil and Construction Engineering and Management, University of Texas at Tyler, Tyler, TX 75799, USA
4 shared publications - Mena I. Souliman
Department of Civil and Construction Engineering and Management, University of Texas at Tyler, Tyler, TX 75799, USA
4 shared publications - Gökhan Saygili
Univ. of Texas at Tyler
1 shared publication - Prashanta Kumar Acharjee
Department of Civil and Construction Engineering and Management, The University of Texas at Tyler, Tyler, USA
1 shared publication - Sameer Jung Karki
Department of Civil and Construction Engineering and Management, The University of Texas at Tyler, Tyler, USA
1 shared publication
Latest Publications
- Open Access
- 22 October 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (21) , 10445
Physics-Guided Machine Learning Approach for Roughness Prediction in Jointed Plain Concrete Pavements
The International Roughness Index (IRI) is a crucial indicator of rigid pavement performance and distress, and artificial neural networks (ANNs) have made pavement management system (PMS) forecasting more cost-effective. However, purely data-driven ANN models are not constrained to follow known physical trends and can behave unpredictably outside their training range. This study developed a physics-informed neural network (PINN) for predicting IRI in jointed plain concrete pavements (JPCPs) by incorporating an empirical equation from the Mechanistic-Empirical Pavement Design Guide (MEPDG) into the training loss, intended to bias predictions toward physically consistent trends. A total of 2705 observations from 394 U.S. and 6 Canadian pavement sections were used to train the model and compare it against a conventional ANN, standard regression, and the standalone MEPDG equation. The PINN achieved a coefficient of determination (R2) of 0.695 and a root mean square error (RMSE) of 11.79 in./mi. Its performance was comparable to the ANN (R2 = 0.698, RMSE = 11.71 in./mi), and both outperformed the MEPDG equation and conventional regression. A closed-form equation was extracted from the trained ANN weights and biases. While the physics constraint did not improve predictive accuracy in this study, it offers a transparent, interpretable tool that agencies can apply directly to prioritize JPCP maintenance and rehabilitation without proprietary model files.
- 22 October 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (21) , 10445
Open AccessPhysics-Guided Machine Learning Approach for Roughness Prediction in Jointed Plain Concrete Pavements
The International Roughness Index (IRI) is a crucial indicator of rigid pavement performance and distress, and artificial neural networks (ANNs) have made pavement management system (PMS) forecasting more cost-effective. However, purely data-driven ANN models are not constrained to follow known physical trends and can behave unpredictably outside their training range. This study developed a physics-informed neural network (PINN) for predicting IRI in jointed plain concrete pavements (JPCPs) by incorporating an empirical equation from the Mechanistic-Empirical Pavement Design Guide (MEPDG) into the training loss, intended to bias predictions toward physically consistent trends. A total of 2705 observations from 394 U.S. and 6 Canadian pavement sections were used to train the model and compare it against a conventional ANN, standard regression, and the standalone MEPDG equation. The PINN achieved a coefficient of determination (R2) of 0.695 and a root mean square error (RMSE) of 11.79 in./mi. Its performance was comparable to the ANN (R2 = 0.698, RMSE = 11.71 in./mi), and both outperformed the MEPDG equation and conventional regression. A closed-form equation was extracted from the trained ANN weights and biases. While the physics constraint did not improve predictive accuracy in this study, it offers a transparent, interpretable tool that agencies can apply directly to prioritize JPCP maintenance and rehabilitation without proprietary model files.
- Open Access
- 13 October 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Machine Learning–Driven Pavement Management System Framework for Bleeding Severity Classification Using Long-Term Pavement Performance Data
This study developed a machine learning–based framework to detect and classify bleeding severity in flexible pavements. It utilized nationally representative pavement performance data obtained from the Long-Term Pavement Performance program. Bleeding significantly reduces surface friction and increases crash risk, yet it remains difficult to detect through traditional inspection methods. The analysis was implemented on 3,781 observations from 658 pavement sections across 35 US states, incorporating structural, environmental, and traffic parameters. The methodology included feature selection, a new bleeding severity classification based on affected surface area, and comparative evaluation of seven classification models. Across all evaluated models, Light Gradient Boosting (LGB) and Extreme Gradient Boosting (XGB) demonstrated the strongest predictive performance. LGB achieved a Precision of 0.85, while XGB closely followed at 0.84; both models recorded a Recall of 0.83, with corresponding F1-scores of 0.83 and 0.82. The subsequent interpretability assessment, using feature importance, a representative decision tree, and partial dependence plots, confirmed that air voids, voids filled with asphalt, pavement age, and total annual precipitation consistently emerged as the dominant variables influencing bleeding severity. The results demonstrated the potential of machine learning to support Pavement Management Systems by enabling accurate identification of severe bleeding cases, thereby reducing inspection efforts and enabling targeted maintenance planning. Although some regions remained underrepresented in the available data, the framework provides a foundation for enhanced bleeding detection and classification. Future work should focus on expanding regional coverage, incorporating advanced sensor and imaging technologies, and developing predictive models for long-term maintenance planning and roadway safety.
- 13 October 2026
- Published by SAGE Publications in Transportation Research Record: Journal of the Transportation Research Board
Open AccessMachine Learning–Driven Pavement Management System Framework for Bleeding Severity Classification Using Long-Term Pavement Performance Data
This study developed a machine learning–based framework to detect and classify bleeding severity in flexible pavements. It utilized nationally representative pavement performance data obtained from the Long-Term Pavement Performance program. Bleeding significantly reduces surface friction and increases crash risk, yet it remains difficult to detect through traditional inspection methods. The analysis was implemented on 3,781 observations from 658 pavement sections across 35 US states, incorporating structural, environmental, and traffic parameters. The methodology included feature selection, a new bleeding severity classification based on affected surface area, and comparative evaluation of seven classification models. Across all evaluated models, Light Gradient Boosting (LGB) and Extreme Gradient Boosting (XGB) demonstrated the strongest predictive performance. LGB achieved a Precision of 0.85, while XGB closely followed at 0.84; both models recorded a Recall of 0.83, with corresponding F1-scores of 0.83 and 0.82. The subsequent interpretability assessment, using feature importance, a representative decision tree, and partial dependence plots, confirmed that air voids, voids filled with asphalt, pavement age, and total annual precipitation consistently emerged as the dominant variables influencing bleeding severity. The results demonstrated the potential of machine learning to support Pavement Management Systems by enabling accurate identification of severe bleeding cases, thereby reducing inspection efforts and enabling targeted maintenance planning. Although some regions remained underrepresented in the available data, the framework provides a foundation for enhanced bleeding detection and classification. Future work should focus on expanding regional coverage, incorporating advanced sensor and imaging technologies, and developing predictive models for long-term maintenance planning and roadway safety.
- 1 October 2025
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 52 (10) , 1885-1899
Leveraging physics with deep learning: physics-informed neural networks (PINN) for IRI prediction in flexible pavements
This study presents a physics-informed neural network (PINN) framework for predicting the international roughness index (IRI) of flexible pavements, utilizing the long-term pavement performance database. A total of 390 observations from 74 pavement sections across the United States were utilized. The architecture of the PINN combines a mean square error (MSE) loss function with a custom physics-informed MSE (PMSE) loss function. It integrates mechanistic IRI equations sourced from the mechanistic-empirical pavement design guide (MEPDG) into the training process. Comparative analysis was performed against standard regression models and the MEPDG IRI prediction equation. Results indicate that the PINN model significantly improves prediction accuracy, achieving a coefficient of determination ( R2) of 0.743 and a root mean squared error of 26.57, outperforming traditional methods. Furthermore, a closed-form equation from the model was derived. By utilizing this new simplified equation, transportation agencies can allocate resources and prioritize maintenance activities efficiently through the IRI forecast PINN Model for asphalt pavements.
- 1 October 2025
- Published by Canadian Science Publishing in Canadian Journal of Civil Engineering
- Vol. 52 (10) , 1885-1899
Leveraging physics with deep learning: physics-informed neural networks (PINN) for IRI prediction in flexible pavements
This study presents a physics-informed neural network (PINN) framework for predicting the international roughness index (IRI) of flexible pavements, utilizing the long-term pavement performance database. A total of 390 observations from 74 pavement sections across the United States were utilized. The architecture of the PINN combines a mean square error (MSE) loss function with a custom physics-informed MSE (PMSE) loss function. It integrates mechanistic IRI equations sourced from the mechanistic-empirical pavement design guide (MEPDG) into the training process. Comparative analysis was performed against standard regression models and the MEPDG IRI prediction equation. Results indicate that the PINN model significantly improves prediction accuracy, achieving a coefficient of determination ( R2) of 0.743 and a root mean squared error of 26.57, outperforming traditional methods. Furthermore, a closed-form equation from the model was derived. By utilizing this new simplified equation, transportation agencies can allocate resources and prioritize maintenance activities efficiently through the IRI forecast PINN Model for asphalt pavements.