Emerging Technologies of Deep Learning Models Development for Pavement Temperature Prediction

Abdalrhman Milad,Ibrahim Adwan,Sayf A Majeed,Zaher Mundher Yaseen,Nur Izzi Md Yusoff,Nadhir Al-Ansari

doi:10.1109/access.2021.3056568

Abstract

Air temperature is one of the critical factors influencing the bearing ability and performance of temperature-sensitive asphalt materials. This research investigates the relationship between air temperature at different depths and time to predict asphalt pavement temperature and evaluate asphalt performance. This paper discusses four deep learning-based regression models for calculating asphalt pavement temperature based on air temperature, depth from the asphalt surface, and time. Measurement of pavement temperature was made in the Gaza Strip. Monitoring stations were set up to measure asphalt pavement temperature and air temperature at different depths and times. The data were collected by hand measurement for the period from March 2012 to February 2013. The data is trained and validated using the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Gated Recurrent Unit (GRU). Bi-LSTM has an R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.9555 for the generated dataset and outperforms other algorithms because of its superiority in feature extraction and multidimensional data processing. Through deep learning techniques, Bi-LSTM has demonstrated outstanding robustness and promising potential in predicting asphalt pavement temperature.

Highlights

Temperature is a critical factor in the design and analysis of pavements
This study developed an empirical statistical model to predict the Asphalt Pavement Temperature (APT) for the typical Mediterranean weather condition in the Gaza Strip, which has specific climate characteristics
REMARKS This paper is the first paper to make a comprehensive comparison of the performances of four deep learning prediction methods, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Gated Recurrent Unit (GRU)

Summary

Introduction

Temperature is a critical factor in the design and analysis of pavements. There are three critical factors in pavement design. Asphalt material properties change with temperature because of the viscoelastic behavior of the asphalt. The asphalt pavement may experience fatigue damage because of thermal contraction and expansion [1]. Transverse top-down cracking may occur in asphalt pavements due to the extreme temperature drop in a day. Researchers have developed regression models for predicting asphalt temperature by measuring pavement temperature using solar radiation and air temperature (AirT) [2]–[10]

Methods

Results

Conclusion