Prediction of Airport Pavement Moduli - Using Machine Learning Methodology with Non-destructive Field Testing Data Augmentation

Aug 5, 2026

Upload by Anda

The work supports Airport Pavement Management System decisions by predicting pavement stiffness moduli from non-destructive Heavy Weight Deflectometer (HWD) investigations. Because HWD surveys are costly and time-consuming, measurements are typically limited to grid center impact points, leaving stiffness estimates needed at unsampled locations. The proposed feedforward shallow neural network uses HWD deflection data plus location and stratigraphy variables. Bayesian regularization and k-fold cross-validation train the model, while data augmentation enlarges the dataset using generated additional samples. Testing shows strong correlation, enabling reliable evaluation of any paved area.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Non-destructive testing and HWD role

Backcalculation of stiffness moduli

Machine learning and data augmentation approach

Prediction of Airport Pavement Moduli by Machine Learning Methodology Using Non-destructive Field Testing Data Augmentation Nicola Baldo 1 , Fabio Rondinella 1 , and Clara Celauro2(B) 1 Polytechnic Department of Engineering and Architecture (DPIA), University of Udine, Via del Cotoniﬁcio 114, 33100 Udine, Italy [nicola.baldo@uniud.it](nicola.baldo@uniud.it) , fabio .rondinella@phd .units .it 2 Department of Engineering, University of Palermo, Viale delle Scienze, Ed. 8, 90128 Palermo, Italy [clara.celauro@unipa.it](clara.celauro@unipa.it) Abstract. For the purpose of the Airport Pavement Management System (APMS), in order to optimize the maintenance strategies, it is fundamental monitoring the pavement conditions’ deterioration with time. In this way, the most damaged areas can be detected and intervention can be prioritized. The conventional approach consists in performing non-destructive tests by means of a Heavy Weight Deﬂectometer (HWD) . This equipment allows the measurement of the pavement deﬂections induced by a deﬁned impact load. This is a quite expensive and time-consuming procedure, therefore, the points to be investigated are usually limited to the center points of a very large mesh grid. Starting from the measured deﬂections at the impact points, the layers’ stiffness moduli can be backcalculated. This paper outlines a methodology for predicting such stiffness moduli, even at unsampled locations, based on Machine Learning approach, speciﬁcallyon a feedforward backpropagation Shallow Neural Network (SNN) . Such goal is achieved by processing HWD investigation and backcalculation results along with other variables related to the location ofthe investigation points and the underlying stratigraphy. Bayesian regularization algorithm and k-fold cross-validation procedure were both implemented to train the neural model. To enhance the training, a data analysis technique commonly referred to as data augmentation was used in order to increase the dataset by generating additional data from the existing ones. The results obtained during the model testing phase are characterized by a very satisfactory correlation coefﬁcient, thus suggesting that the proposed Machine Learning approach is highly reliable. Notably, the proposed methodology can be implemented to evaluate the performance of every paved area. Keywords: Airport pavement · Stiffness modulus · Data augmentation · Machine learning · Non-destructive testing data © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023 A. Gomes Correia et al. (Eds.): ISIC 2022, LNCE 306, pp. 62–75, 2023 . [https://doi.org/10.1007/978-3-031-20241-4](https://doi.org/10.1007/978-3-031-20241-4_5)[_](https://doi.org/10.1007/978-3-031-20241-4_5)[5](https://doi.org/10.1007/978-3-031-20241-4_5) Prediction of Airport Pavement Moduli by Machine Learning Methodology 63 1 Introduction Airport infrastructure network of a country, whether already developed or developing, is always astrategic asset for economic and social development[1]. It is therefore necessary to guarantee, despite all potential factors of degradation such as ageing, increase intrafﬁc, budget shortfalls and ﬁnancial constraints as in the pandemic since 2020 [2], a constant performance level so that the service offered may always meet the requirement for safety, efﬁciency and functionality. In airport infrastructures, great attention is paid to the runway as it is one of the core structure. In order to evaluate the deterioration level of a runway and its maintenance needs with time, both destructive [3] and nondestructive investigation techniques are usually performed. However, a gradual shift to non-destructive [4] testing (NDT) methods has been observed over the years. The former, by requiring borings, cores and excavation pits on an existing runway, require its temporary closure to trafﬁc and cause a huge ﬁnancial effort as well as service interruption [5] . The latter, on

FAQs

How is dataset size increased for machine learning training?

A data augmentation technique is applied to generate additional data from existing results, improving the model’s ability to learn from a larger effective dataset.

Aug 5, 2026

Upload by Anda