Skip to main content

Advertisement

SpringerLink
Log in

Artificial neural network-based roughness prediction models for gravel roads considering land use

  • Technical paper
  • Published:
Innovative Infrastructure Solutions Aims and scope Submit manuscript

Abstract

The Wyoming Technology Transfer Center (WYT2/LTAP) is in the process of developing a holistic and integrated Gravel Road Management System (GRMS). As a part of this effort, gravel roads condition prediction models have been developed. The developed models aim to predict the roughness of gravel roads in terms of International Roughness Index (IRI) considering the land use and the traffic volume levels. Approximately 700 miles of gravel roads in Laramie County, Wyoming were tested and evaluated. The land use of each road was classified into three groups: residential, agricultural, and industrial. While the traffic volume, for the purpose of this study, was categorized into three levels: low, moderate, and high. Both land use and traffic volume levels were found to have significant effect on the IRI deterioration over time. Initially, multiple linear regression was used to develop IRI prediction models. The developed multiple linear regression models represented the data with accepted coefficient of determination (R2) level. Also, Artificial Neural Network (ANN) was used to develop prediction models for the IRI. ANN process started by using 70% of the data to train the model, then the remaining 30% were used for validation and testing. One ANN prediction model was developed for each land use. ANN prediction models showed significantly more ability to represent the data than multiple linear regression. The developed prediction models can be an essential part for developing a holistic GRMS and improving better understanding for gravel roads deterioration behavior.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Huntington G, Ksaibati K (2009) Annualized road works cost estimates for unpaved roads. J Transp Eng 135(10):702–710

    Article  Google Scholar 

  2. Aleadelat W, Wulff S, Ksaibati K (2019) Development of performance prediction models for gravel roads using Markov chains. Am J Civ Eng 7(3):73–81

    Article  Google Scholar 

  3. Transportation Information Center at University of Wisconsin-Madison (2002) Pavement Surface Evaluation and Rating-PASER Manual Gravel roads

  4. Al-Suleiman (Obaidat), Turki I, and Abu Daoud O (2021) Evaluation of pavement condition of the primary roads in Jordan using SHRP procedure. Jordan J Civ Eng 15(2):305–317

  5. Abu Daoud O, Albatayneh O, Forslöf L, Ksaibati K (2021) Validating the practicality of utilising an image classifer developed using TensorFlow framework in collecting corrugation data from gravel roads. Int J Pavement Eng. https://doi.org/10.1080/10298436.2021.1921773

    Article  Google Scholar 

  6. Zhang Q (2019) Recent advances in convolutional neural network acceleration. Neuro-Comput 323:37–51

    Google Scholar 

  7. Alharbi F, and Smadi O (2019) Predicting pavement performance utilizing artificial neural network (ANN). Int J Adv Eng Manag Sci (IJAEMS). https://doi.org/10.22161/ijaems.58.4

  8. Huntington G, Ksaibati K (2011) Implementation guide for the management of unsealed gravel roads. Transp Res Record J Transp Res Board 2205:189–197

    Article  Google Scholar 

  9. Huntington G, Ksaibati K (2015) Visual assessment system for rating unsealed roads. Transp Res Record J Transp Res Board 2474:116–122

    Article  Google Scholar 

  10. Costello SB (2005) Stochastic model for strategic assessment of road maintenance. Proc Inst Civ Eng Transp 158(TR4):203–211

    Google Scholar 

  11. Eaton RA, Beaucham RE (1992) Unsurfaced road maintenance management. Hanover, NH: United States Army Corps of Engineers Cold Regions Research and Engineering Laboratory, special report 92–26

  12. Jones D, and Paige-Green P (2000) DRAFT TMH12 Pavement management systems: standard visual assessment manual for unsealed roads version 1. Contract Report CR2000/66."Pretoria, South Africa

  13. Brown M, Mercier S, Provencher Y (2003) Road maintenance with opti-grade®: maintaining road networks to achieve the best value. Transp Res Record J Transp Res Board. https://doi.org/10.3141/1819a-41

    Article  Google Scholar 

  14. Gong H (2019) Neural networks for fatigue cracking prediction using outputs from pavement mechanistic-empirical design. Int J Pavement Eng 22(2):162–172

    Article  Google Scholar 

  15. Gu J (2018) Recent advances in convolutional neural networks. Pattern Recogn 77:354–377

    Article  Google Scholar 

  16. Yousaf MH (2018) Visual analysis of asphalt pavement for detection and localization of potholes. Adv Eng Inform 38:527–537

    Article  Google Scholar 

  17. Steyn WJvdM, Bean WL, and Monismith CL (2008) The potential costs of bad roads in South Africa. In: Fifth Annual State of logistics survey for South Africa. CSIR, Pretoria, South Africa, pp. 49–52. 4

  18. Skorseth K and Selim AA (2000) Gravel roads maintenance and design manual, Report No. LTAP-02–002, South Dakota Local Transportation Assistance Program

  19. Kargah-Ostadi N, Stoffels SM (2015) Framework for development and comprehensive comparison of empirical pavement performance models. J Transp Eng. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000779

    Article  Google Scholar 

  20. Abu Daoud O, Ksaibati K (2021) Studying the effect of gravel roads geometric features on corrugation behavior. Int J Pavement Res Technol. https://doi.org/10.1007/s42947-021-00110-5

    Article  Google Scholar 

  21. Mehta A, Mehta H, Manjunath TC, Ardil C (2008) A multi-layer artificial neural network architecture design for load forecasting in power systems. Int J Appl Math Comput Sci 4(4):227–240

    Google Scholar 

  22. Rafiq MY, Bugmann G, Easterbrook DJ (2001) Neural network design for engineering applications. Comput Struct 79(17):1541–1552

    Article  Google Scholar 

  23. Basheer IA, Hajmeer M (2000) Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 43(1):3–31

    Article  Google Scholar 

  24. Zhang G, Patuwo BE, Hu MY (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14(1):35–62

    Article  Google Scholar 

  25. Karlaftis MG, Vlahogianni EI (2011) Statistical methods versus neural networks in transportation research: differences, similarities and some insights. Transp Res Part C 19(3):387–399

    Article  Google Scholar 

  26. Ling M, Luo X, Hu S, Gu F, Lytton RL (2017) Numerical modeling and artificial neural network for predicting J-integral of top-down cracking in asphalt concrete pavement. In: Transportation Research Board 96th Annual Meeting (No. 17–05318)

  27. Vlahogianni EI, Karlaftis MG (2013) Testing and comparing neural network and statistical approaches for predicting transportation time series. Transp Res Record J Transp Res Board 2399:9–22

    Article  Google Scholar 

  28. Golshani N, Shabanpour R, Mahmoudifard S, Derriblr S, Mohammadian A (2017) Comparison of artificial neural networks and statistical copula-based joint models (No. 17–-01202)

  29. Wu Z, Zhou F, Hu S (2014) Prediction of stress intensity factors in pavement cracking with neural networks based on semi-analytical FEA. Expert Syst Appl 41(4):1021–1030

    Article  Google Scholar 

  30. Felker V, Najjar YM, Hossain M (2004) Modeling the roughness progression on Kansas portland cement concrete (PCC) pavements (No. K-TRAN:KSU-00–6). Kansas Department of Transportation

  31. Lou Z, Gunaratne M, Lu JJ, Dietrich B (2001) Application of neural network model to forecast short-term pavement crack condition: Florida case study. J Infrastruct Syst 7(4):166–171

    Article  Google Scholar 

  32. Gencel O, Kocabas F, Gok MS, Koksal F (2011) Comparison of artificial neural networks and general linear model approaches for the analysis of abrasive wear of concrete. Constr Build Mater 25(8):3486–3494

    Article  Google Scholar 

  33. Attoh-Okine N (1994) Predicting roughness progression in flexible pavements using artificial neural networks. Transportation Research Board Conference Proceedings. (Vol. 1, No. 1)

  34. Attoh-Okine N, Adarkwa O (2013) Pavement condition surveys—Overview of current practices. Delaware Center for Transportation, University of Delaware, Newark, DE, USA

    Google Scholar 

  35. Islam S, Buttlar WG (2012) Effect of pavement roughness on user costs. Transp Res Record J Transp Res Board 2285:47–55

    Article  Google Scholar 

  36. Kargah-Ostadi N (2014) Comparison of machine learning techniques for developing performance prediction models. Computing in Civil and Building Engineering, 1222–1229

  37. Papagiannakis A, Raveendran B (1998) International standards organization-compatible index for pavement roughness. Transp Res Record J Transp Res Board 1643:110–115

    Article  Google Scholar 

  38. Huntington G and Ksaibati K (2016) Gravel roads surface performance modeling, Transportation Research Record. pp. 56–64

  39. Li M, Wang H (2017) Development of ANN-GA program for backcalculation of pavement moduli under FWD testing with viscoelastic and nonlinear parameters. Int J Pavement Eng. https://doi.org/10.1080/10298436.2017.1309197

    Article  Google Scholar 

  40. Varma S, Kutay E (2016) Back calculation of viscoelastic and nonlinear flexible pavement layer properties from falling weight deflections. Int J Pavement Eng 17:388–402

    Article  Google Scholar 

  41. Ceylan H, Gopalakrishnan K, and Guclu A (2005) Advanced approaches to characterizing nonlinear pavement system responses. Transportation Research Record, Washington, DC: TRB, National Research Council, 86–94

Download references

Acknowledgements

The authors would like to gratefully thank the Mountain Plains Consortium (MPC) for supporting this study.

Author information

Authors and Affiliations

  1. Department of Civil and Architectural Engineering, University of Wyoming, Laramie, Wyoming, 82070, USA

    Osama Abu Daoud & Khaled Ksaibati

Authors
  1. Osama Abu Daoud
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Khaled Ksaibati
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Osama Abu Daoud.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Daoud, O.A., Ksaibati, K. Artificial neural network-based roughness prediction models for gravel roads considering land use. Innov. Infrastruct. Solut. 7, 231 (2022). https://doi.org/10.1007/s41062-022-00793-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s41062-022-00793-0

Keywords

Search

Navigation