Pavement performance spatio-temporal prediction based on multi-stage deep learning approach

Road Materials and Pavement Design, pp. 1–20

Abstract

Pavement deterioration tracking faces various challenges, including partial data shortage, short observation cycles and spatio-temporal randomness. This paper presents a multi-stage deep learning framework integrating a random forest neural network (RF-NN), a long short-term memory network (LSTM) and a temporal convolutional network (TCN) for pavement performance prediction. The RF-NN model quantifies the relationships among various pavement performance indicators, while the LSTM model performs time-series prediction of the pavement surface condition index (PCI), riding quality index (RQI) and rutting depth index (RDI) using single- and multi-indicator strategies. Incorporating spatial information, the TCN further improves prediction accuracy and analyses spatio-temporal sensitivity. The results show that the RF-NN model produces high-confidence and well-distributed PCI estimates. The multi-indicator LSTM model outperforms the single-indicator LSTM model. The TCN model yields a lower error than the LSTM model. The mean absolute percentage error of RQI in the TCN prediction is 0.757%.

Authors 6

1. Junzhe Wang

   China Academy of Transportation Sciences

   Affiliation as printed

   Testing Technology (Beijing) Co., Ltd. of China Academy of Transportation Sciences (CATS)

2. Jinchao Guan corresponding

   Chang'an University

   Affiliation as printed

   Chang’an University

   Zhejiang Expressway Co., Ltd

3. Hossein Nowamooz

   Institut National des Sciences Appliquées de Strasbourg

   Affiliation as printed

   Institute National des Sciences Appliquées (INSA) de Strasbourg

4. Can Jin

   Hefei University of Technology

   Affiliation as printed

   Hefei University of Technology

5. Xu Yang

   Chang'an University

   Affiliation as printed

   Chang’an University

6. Pengfei Liu corresponding Aachen Institute of Highway Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute of Highway Engineering, RWTH Aachen University