Artificial neural network modelling to predict international roughness index of rigid pavements

  • Mohammad HossainEmail author
  • Leela Sai Praveen Gopisetti
  • Md. Suruz Miah
Article in Press


This research focuses on predicting the International Roughness Index (IRI) of rigid pavements using the Artificial Neural Network (ANN) model that uses climate and traffic parameters as inputs. A Long-Term Pavement Performance (LTPP) database is used to extract data from wet-freeze, wet no-freeze, dry-freeze, and dry no-freeze climatic zones. The climate and traffic parameters are Mean Annual Air Temperature, Annual Average Freezing Index, Annual Average Maximum and Minimum Humidity, Annual Average Precipitation, Annual Average Daily Traffic, and Annual Average Daily Truck Traffic. The ANN model is trained with 70% of climate, traffic and IRI data, rest 15% data is used to test the model, and remaining 15% data is used to validate the model. The trained and the validated models are compared by calculating Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Among many results, the datasets that are tested with 7–9–9–1 ANN structure with hyperbolic tangent sigmoidal transfer function generated the best prediction models with an RMSE value of 0.01 and MAPE value of 0.01 (1% error) for a rigid pavement located in the wet no-freeze climatic zone.


Artificial Neural Network (ANN) International Roughness Index (IRI) Long-Term Pavement Performance (LTPP) Rigid pavements Climate Traffic 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    B. Saghafi., A. Hassani., R. Noori., M. G. Bustos, Artificial Neural Networks and Regression Analysis for Predicting Faulting in Jointed Concrete Pavements Considering Base Condition, Int. J. Pavement Res. Technol. 2 (1) (2009) 20–25.Google Scholar
  2. [2]
    K. Ksaibati., R. McNamara., W. Miley., J. M. Armaghani, Evaluating the ride number as a pavement management roughness index, Florida Department of Transportation, Gainesville, FL, USA, 1998.Google Scholar
  3. [3]
    T. Wang., J. Harvey., J. Lea., C. Kim., Impact of Pavement Roughness on Vehicle Free-Flow Speed, J. Transp. Eng. 140 (9) (2014) 1–11. doi:10.1061/(ASCE)TE.1943–5436.0000689.Google Scholar
  4. [4]
    J. Lin., J.-T. Yau., L.-H. Hsiao., Correlation Analysis Between International Roughness Index (IRI) and Pavement Distress by Neural Network, in: 82nd Transp. Res. Board Annu. Meet., Transportation Research Board, Washington, D.C., USA, 2003.Google Scholar
  5. [5]
    A. Bin., A. Latif., Relationship Between International Roughness Index (IRI) and Present Serviceability Index (PSI), (Master of Science Thesis), Universiti Teknologi Malaysia, Malaysia, 2009.Google Scholar
  6. [6]
    K. Park., N. E. Thomas, K. Wayne Lee, Applicability of the International Roughness Index as a Predictor of Asphalt Pavement Condition, J. Transp. Eng. 133 (12) (2007) 706–709. doi:10.1061/(ASCE)0733–947X(2007)133:12(706).CrossRefGoogle Scholar
  7. [7]
    S. A. Arhin, L. N. Williams, A. Ribbiso., M. F. Anderson, Predicting Pavement Condition Index Using International Roughness Index in a Dense Urban Area, J. Civ. Eng. Res. 5 (1) (2015) 10–17. doi:10.5923/j.jce.20150501.02.Google Scholar
  8. [8]
    Y. Du., C. Liu., D. Wu., S. Jiang., Measurement of International Roughness Index by Using Z-Axis Accelerometers and GPS, Math. Probl. Eng. 2014 (2014) 1–10. doi:10.1155/2014/928980.Google Scholar
  9. [9]
    M. W. Sayers, S. M. Karamihas, Interpretation of Road Roughness Profile Data—Final Report, Federal Highway Administration, McLean, VA, USA, 1996.Google Scholar
  10. [10]
    J. Chang., Y. Su., T. Huang., S. Kang., S. Hsieh., Measurement of the International Roughness Index (IRI) using an Autonomous Robot (P3-AT), in: 26th Int. Symp. Autom. Robot. Constr., International Association for Automation and Robotics in Construction, Austin, Texas, USA, 2009, pp. 325–331.Google Scholar
  11. [11]
    F. Bayomy., H. Salem., L. Vosti., Analysis of the Long-Term Pavement Performance Data for the Idaho GPS and SPS Sections, Idaho Transportation Department, Boise, Idaho, USA, 2007.Google Scholar
  12. [12]
    N. J. Santero, A. Horvath., Global Warming Potential of Pavements, Environ. Res. Lett. 4 (3) (2009) 4–11. doi:10.1088/1748–9326/4/3/034011.CrossRefGoogle Scholar
  13. [13]
    N. Yadav., A. Yadav., M. Kumar., History of Neural Networks, in: An Introd. to Neural Netw. Methods Differ. Equations., Springer, Dordrecht, 2015: pp. 13–15. doi:10.1007/978–94–017–9816–7.Google Scholar
  14. [14]
    J. A. Bullinaria, Introduction to Neural Networks and Their History, University of Birmingham, UK, 2004. doi:10.1108/eb007822.Google Scholar
  15. [15]
    Y. LeCun., A Theoretical Framework for Back-Propagation, Proc. 1988 Connect. Model. Summer Sch., Carnegie-Mellon University, Pittsburgh, PA, USA, 1988, pp. 21–28. doi:10.1007/978–3–642–35289–8.Google Scholar
  16. [16]
    M. B. Bayrak, E. Teomete., M. Agarwal., Use of Artificial Neural Networks for Predicting Rigid Pavement Roughness, in: Midwest Transp. Consort., Ames, Iowa, USA, 2004: pp. 1–18.Google Scholar
  17. [17]
    J. Yang., J. J. Lu, M. Gunaratne., Application of Neural Network Models for Forecasting of Pavement Crack Index and Pavement Condition Rating, Tallahassee, FL, 2003.Google Scholar
  18. [18]
    J. S. Miller, W. Y. Bellinger, Distress Identification Manual for the Long-Term Pavement Performance Program, McLean, Virginia, USA, 2003.Google Scholar
  19. [19]
    G. E. Elkins, T. Thomson., A. Simpson., B. Ostrom., Long-Term Pavement Performance Information Management System: Pavement Performance Database User Reference Guide, McLean, Virginia, USA, 2012.Google Scholar
  20. [20]
    G. E. Elkins, Ba. Ostrom., B. Visintine., J. Groeger., Long-Term Pavement Performance Ancillary Information Management System (AIMS) Reference Guide, Federal Highway Administration, McLean, VA, USA, 2012.Google Scholar
  21. [21]
    A. N. Hanna, S. D. Tayabji, J. S. Miller, SHRP-LTPP Specific Pavement Studies: Five-Year Report, Washington, D.C., USA, 1994.Google Scholar
  22. [22]
    K. K. Mantravadi, LTPP-Distress Due to Environment, in: MTC Transp. Sch. Conf., Ames, Iowa, USA, 2000: pp. 83–90.Google Scholar
  23. [23]
    M. B. Bayrak, Analysis of Jointed Plain Concrete Pavement Systems with Nondestructive Test Results using Artificial Neural Networks, Iowa State University, 2008.Google Scholar
  24. [24]
    S. K. Suman, S. Sinha., Pavement Condition Forecasting Through Artificial Neural Network Modelling, Int. J. Emerg. Technol. Adv. Eng. 2 (11) (2012) 474–478.Google Scholar
  25. [25]
    D. T. Thube, Artificial Neural Network (ANN) based pavement deterioration models for low volume roads in India, Int. J. Pavement Res. Technol. 5 (2) (2012) 115–120.Google Scholar
  26. [26]
    R.A. El-Hakim, S. El-Badawy, International Roughness Index Prediction for Rigid Pavements: An Artificial Neural Network Application, Adv. Mater. Res. 723 (2013) 854–860. doi:10.4028/ Scholar
  27. [27]
    Z. Wu., S. Hu., F. Zhou., Expert Systems with Applications Prediction of Stress Intensity Factors in Pavement Cracking with Neural Networks Based on Semi-Analytical FEA, Expert Syst. Appl. 41 (4) (2014) 1021–1030. doi:10.1016/j.eswa.2013.07.063.Google Scholar
  28. [28]
    F. Gu., X. Luo., Y. Zhang., Y. Chen., R. Luo., R. L. Lytton, Prediction of Geogrid-Reinforced Flexible Pavement Performance using Artificial Neural Network Approach, Road Mater. Pavement Des. Des. 19 (5) (2018) 1147–1163. doi:10.1080/14680629.2017.1302357.Google Scholar
  29. [29]
    J. S. Daniel, J. M. Jacobs, E. Douglas., R. B. Mallick, K. Hayhoe., Impact of Climate Change on Pavement Performance: Preliminary Lessons Learned through the Infrastructure and Climate Network (ICNet), in: Int. Symp. Clim. Eff. Pavement Geotech. Infrastruct., ASCE, 2013: pp. 1–9.Google Scholar
  30. [30]
    M. W. Sayers, S. M. Karamihas, The little book of profiling, Basic Inf. about Meas. Interpret. Road Profiles. (1998) 100.Google Scholar
  31. [31]
    R. Machemehl., C. E. Lee, Dynamic Traffic Loading of Pavements, Austin, Texas, USA, 1974.Google Scholar
  32. [32]
    M. Cilimkovic., Neural Networks and Back Propagation Algorithm, Institute of Technology Blanchardstown, Dublin, Ireland, 2010.Google Scholar
  33. [33]
    T. P. Vogl, J. K. Mangis, A. K. Rigler, W. T. Zink, D. L. Alkon, Biological Cybernetics Accelerating the Convergence of the Back-Propagation Method, Biol. Cybern. 59 (4–5) (1988) 257–263.CrossRefGoogle Scholar
  34. [34]
    M. I. Hossain, L.S. P. Gopisetti, M. S. Miah, Prediction of International Roughness Index of Flexible Pavements from Climatic and Traffic Data Using Artificial Neural Network Modeling, in: I.L. Al-Qadi (Ed.), Proc. Int. Conf. Highw. Pavements Airf. Technol. Airf. Highw. Pavements 2017, ASCE, Philadelphia, Pennsylvania, USA, 2017: pp. 256–267. doi:10.1061/9780784410059.CrossRefGoogle Scholar
  35. [35]
    C. Chang., C. Liao., Parameter Sensitivity Analysis of Artificial Neural Network for Predicting Water Turbidity, Transfer. 3 (3) (2012) 4–5.Google Scholar
  36. [36]
    Y.-S. Hwang., S.-Y. Bang., Determination of the Weights of an RBF Network using Linear Discriminant Analysis, Pohang University of Science and Technology, Pohang, Korea, 2007.Google Scholar
  37. [37]
    J. Kaur., Techniques Used in Hypothesis Testing in Research Methodology–A Review, 4 (2) (2015) 2013–2016.Google Scholar
  38. [38]
    A. U. Stata, H. M. Park, Comparing Group Means: The T-test and One-way, Indiana University, Bloomington, IN, USA, 2005.Google Scholar
  39. [39]
    R. H. Walpole, R. H. Myers, S. L. Myers, K. Ye., Probability & Statistics for Engineers & Scientists, Eight Edit, Pearson Prentice Hall, NY, USA, 2007. doi:10.2307/2288012.zbMATHGoogle Scholar
  40. [40]
    M. I. Hossain, L.S. P. Gopisetti, M. S. Miah, International Roughness Index Prediction of Flexible Pavements using Neural Networks, J. Transp. Eng. Part B Pavement. 145 (1) (2018). doi:10.1061/JPEODX.0000088.Google Scholar
  41. [41]
    T. Shaikhina., N. A. Khovanova, Handling Limited Datasets with Neural Networks in Medical Applications: A Small-Data Approach, Artif. Intell. Med. 75 (2017) 51–63. doi:10.1016/j.artmed.2016.12.003.CrossRefGoogle Scholar
  42. [42]
    Alharbi, Fawaz, Predicting pavement performance utilizing artificial neural network (ANN) models, (Graduate Theses and Dissertations), Iowa State University, Ames, IA, USA, 2018.Google Scholar
  43. [43]
    H. Ceylan., O. Kaya., A. R. Tarahomi., K. Gopalakrishnan., S. Kim., D. R. Brill., Developing Rigid Airport Pavement Multiple-Slab Response Models for Top-Down Cracking Mode using Artificial Neural Networks, Civil, Construction and Environmental Engineering Conference Presentations and Proceedings, Iowa State University, Ames, IA, USA, 37, 2017.Google Scholar
  44. [44]
    O. Kaya., N. Garg; H. Ceylan., S. Kim., Development of Artificial Neural Networks Based Predictive Models for Dynamic Modulus of Airfield Pavement Asphalt Mixtures, International Conference on Transportation and Development 2018: Airfield and Highway Pavements, American Society of Civil Engineers, Reston, VA, 2018.Google Scholar

Copyright information

© Higher Education Press Limited Company 2020

Authors and Affiliations

  • Mohammad Hossain
    • 1
    Email author
  • Leela Sai Praveen Gopisetti
    • 2
  • Md. Suruz Miah
    • 3
  1. 1.Department of Civil Engineering and ConstructionBradley UniversityPeoriaUSA
  2. 2.Department of Civil, Construction and Environmental EngineeringIowa State UniversityAmesUSA
  3. 3.Department of Electrical and Computer EngineeringBradley UniversityPeoriaUSA

Personalised recommendations