Abstract

This paper introduces a methodology for predicting and mapping surface motion beneath road pavement structures caused by environmental factors. Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) measurements, geospatial analyses, and Machine Learning Algorithms (MLAs) are employed for achieving the purpose. Two single learners, i.e., Regression Tree (RT) and Support Vector Machine (SVM), and two ensemble learners, i.e., Boosted Regression Trees (BRT) and Random Forest (RF) are utilized for estimating the surface motion ratio in terms of mm/year over the Province of Pistoia (Tuscany Region, central Italy, 964 km2), in which strong subsidence phenomena have occurred. The interferometric process of 210 Sentinel-1 images from 2014 to 2019 allows exploiting the average displacements of 52,257 Persistent Scatterers as output targets to predict. A set of 29 environmental-related factors are preprocessed by SAGA-GIS, version 2.3.2, and ESRI ArcGIS, version 10.5, and employed as input features. Once the dataset has been prepared, three wrapper feature selection approaches (backward, forward, and bi-directional) are used for recognizing the set of most relevant features to be used in the modeling. A random splitting of the dataset in 70% and 30% is implemented to identify the training and test set. Through a Bayesian Optimization Algorithm (BOA) and a 10-Fold Cross-Validation (CV), the algorithms are trained and validated. Therefore, the Predictive Performance of MLAs is evaluated and compared by plotting the Taylor Diagram. Outcomes show that SVM and BRT are the most suitable algorithms; in the test phase, BRT has the highest Correlation Coefficient (0.96) and the lowest Root Mean Square Error (0.44 mm/year), while the SVM has the lowest difference between the standard deviation of its predictions (2.05 mm/year) and that of the reference samples (2.09 mm/year). Finally, algorithms are used for mapping surface motion over the study area. We propose three case studies on critical stretches of two-lane rural roads for evaluating the reliability of the procedure. Road authorities could consider the proposed methodology for their monitoring, management, and planning activities.

Highlights

  • The different aspects of the daily life of most people and communities are intertwined with the roads [1]

  • We found researches on the implementation of Persistent Scatterer (PS)-InSAR for road infrastructures [36,37,38,39,40,41,42], rail infrastructures [29,43,44,45,46], bridges [47,48,49,50], and dams [51,52,53,54]; Ozden et al [55] demonstrated by an InSAR benefit/cost analysis that SAR-based monitoring improves the effectiveness of the overall infrastructure monitoring system and reduces the total cost

  • We discussed the use of PS-InSAR measurements and GIS analyses in combination with Machine Learning Algorithms for modeling and predicting the surface motion ratio caused by environmental factors in terms of mm/year of an area of interest

Read more

Summary

Introduction

The different aspects of the daily life of most people and communities are intertwined with the roads [1]. Hazard prevention, planning, monitoring, inspection, and maintenance of roads network is critical. Non-Destructive High-Performance Techniques are essential tools for managing extended and complex road networks. By such techniques, road authorities can efficiently obtain reliable information concerning the causes of distresses (exogenous and endogenous factors) and consequences (infrastructure damages and deficiencies) of the assets they manage. Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) technique is widely employed in infrastructure monitoring and inspection since it allows achieving reliable outcomes in the identification and prevention of infrastructural instabilities over time. To the best of our knowledge, little or nothing has been discussed on the use of PS-InSAR outcomes for modeling and predicting infrastructure instabilities for road infrastructure monitoring and management

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call