Data-driven framework for modeling deterioration of pavements in the state of Iowa

Abstract

<p>Highway networks serve the public by providing access to critical facilities such as hospitals, schools, and markets. Although maintenance and rehabilitation resemble a burden on transportation agencies, postponing required road maintenance can result in even higher direct and indirect costs (Burningham, 2005). Developing a robust and accurate pavement management system (PMS) is the key to supporting decision-makers at local and state highway agencies. One of the most important components of pavement management systems is predicting the deterioration of the network through performance models.</p> <p>In this research, two major objectives were investigated. In the first part, the process and outcome of deterioration modeling for three different pavement types in the state of Iowa was described. Pavement condition data is collected by the Iowa Department of Transportation (DOT) and stored in a Pavement-Management Information System (PMIS). Typically, the overall pavement condition is quantified using the Pavement Condition Index (PCI), which is a weighted average of indices representing different types of distress, roughness, and deflection. Deterioration models of PCI as a function of time were developed for the different pavement types using two modeling approaches. The first approach is the Long/Short Term Memory (LSTM), a subset of a recurrent neural network. The second approach, used by the Iowa DOT, is developing individual regression models for each section of the different pavement types. A comparison is made between the two approaches to assess the accuracy of each model. The results show that while the individual regression models achieved higher prediction accuracy with respect to asphalt pavements, the LSTM model achieved a higher prediction accuracy over time for concrete and composite pavement types.</p> <p>In the second part, describes how the accuracy of prediction models can have an effect on the decision-making process in terms of the cost of maintenance and rehabilitation activities. The process is simulating the propagation of the error between the actual and predicted values of pavement performance indicators. Different rate of error was added into the result of prediction models. The results showed a strong correlation between the prediction models' accuracy and the cost of maintenance and rehabilitation activities. Also, increasing the rate of error contribution to the prediction model resulting in a higher benefit reduction rate.</p>