EUVIMEDEUVIMED entdecken
Crossref

Effect of Rain on Road Surface Deterioration by Deep Learning

Amarsinh B. Landage, Samruddhi S. Berde, Pooja R. Jangam, Akanksha P. Bhatkar

IOSR Journal of Mechanical and Civil Engineering · 2026-03 · 23 (3) · 13-20

DOI: 10.9790/1684-2303011320 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IOSR Journal of Mechanical and Civil Engineering, 2026-03. Verfasst von Amarsinh B. Landage und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Road surface deterioration due to rainfall is one of the major challenges in transportation infrastructure management. Continuous exposure to water leads to surface cracks, potholes, rutting, and overall reduction in pavement life, increasing maintenance costs and compromising road safety. The unpredictable nature of rainfall and its varying impact on different pavement materials make deterioration modelling complex. Traditional analytical or empirical methods often fail to accurately predict such effects due to limited data handling capacity and nonlinear environmental interactions. In this study, deep learning techniques are employed to analyze and predict the impact of rainfall on road surface deterioration. A comprehensive dataset comprising rainfall intensity, frequency, pavement age, traffic load, and surface distress images was collected from multiple sources. Convolutional Neural Networks were utilized to identify and classify different types of surface damage, while Recurrent Neural Networks were applied to understand temporal patterns in deterioration progression under varying rainfall conditions. The integration of meteorological and image-based data enhanced the accuracy and robustness of the predictive model. The developed deep learning model demonstrates superior performance compared to traditional regression-based and statistical methods. It effectively captures complex relationships between rainfall parameters and surface distress levels, enabling early detection of deterioration trends. The model’s ability to process high-dimensional data allows for adaptive learning and continuous improvement as new data becomes available. This predictive capability supports timely maintenance interventions and minimizes unexpected road failures.

Zitieren

APA

Landage, A. B., Berde, S. S., Jangam, P. R., & Bhatkar, A. P. (2026). Effect of Rain on Road Surface Deterioration by Deep Learning. IOSR Journal of Mechanical and Civil Engineering, 23(3), 13-20. https://doi.org/10.9790/1684-2303011320

Vancouver

Landage AB, Berde SS, Jangam PR, Bhatkar AP. Effect of Rain on Road Surface Deterioration by Deep Learning. IOSR Journal of Mechanical and Civil Engineering. 2026;23(3):13-20. doi:10.9790/1684-2303011320

BibTeX
@article{Landage2026,
  author = {Landage, Amarsinh B. and Berde, Samruddhi S. and Jangam, Pooja R. and Bhatkar, Akanksha P.},
  title = {Effect of Rain on Road Surface Deterioration by Deep Learning},
  journal = {IOSR Journal of Mechanical and Civil Engineering},
  year = {2026},
  volume = {23},
  number = {3},
  pages = {13--20},
  doi = {10.9790/1684-2303011320}
}
Kostenlos starten →