Assessing Resilience of Infrastructures Towards Exogenous Events by Using Ps-Insar-Based Surface Motion Estimates and Machine Learning Regression Techniques

Abstract

Abstract. Technologically advanced strategies in infrastructural maintenance are increasingly required in countries such as Italy, where recovery and rehabilitation interventions are preferred to new works. For this purpose, Interferometric Synthetic Aperture Radar (InSAR) techniques have been employed in recent years, achieving reliable outcomes in the identification of infrastructural instabilities. Nevertheless, using the InSAR survey exclusively, it is not feasible to recognize the reasons for such vulnerabilities, and further in-depth investigations are essential.The primary purpose of this paper is to predict infrastructural displacements connected to surface motion and the related causes by combining InSAR techniques and Machine Learning algorithms. The development and application of a Regression Tree-based algorithm have been carried out for estimating the displacement of road pavement structures detected by the Persistent Scatterer InSAR technique.The study area is located in the province of Pistoia, Tuscany, Italy. Sentinel-1 images from 2014 to 2019 were used for the interferometric process, and a set of 29 environmental parameters was collected in a GIS platform. The database is randomly split into a Training (70%) and Test sets (30%). With the Training set, through a 10-Fold Cross-Validation, the model is trained, validated, and the Goodness-of-Fit is evaluated. Also, with the Test set, the Predictive Performance of the model is assessed. Lastly, we applied the model onto a stretch of a two-lane rural road that crosses the area. Results show that the suggested procedure can be used for supporting decision-making processes on planning road maintenance by National Road Authorities.

Can Machine Learning and PS-InSAR Reliably Stand in for Road Profilometric Surveys?

“…The high capabilities of SAR sensors in terms of measurement reliability, accuracy, speed of execution, high coverage, and the possibility of data processing in near real-time and back in time have meant a bursting development of SAR-based products as high-performance NDT in monitoring and inspection activities of linear infrastructures. In the literature, there are several SAR-based applications, mainly PS-InSAR surveys, of infrastructure monitoring activities, e.g., road infrastructures [ 6 , 7 , 8 , 31 , 32 , 33 , 34 , 35 ], rail infrastructures [ 36 , 37 , 38 , 39 , 40 ], airport runways [ 41 ], and bridges [ 42 , 43 , 44 , 45 ]. In these research studies, the common objective is to identify critical infrastructural sections by processing SAR images and comparing these surveys with other techniques (e.g., leveling or GPS surveys).…”

“…Such roads are monitored and managed by the TRRA, which provided all the required environmental data for developing the previously mentioned SAR-based MLAs [ 7 , 8 ]. Two-lane roads are defined in the Highway Safety Manual [ 80 ] as single carriageway roads with one lane for each travel direction.…”

“…In our previous works [ 7 , 8 ], we calibrated some MLAs for predicting and mapping the average vertical displacement of the road pavement surface as a result of exogenous phenomena occurrence. Exogenous events are defined as external factors to the infrastructure.…”

“…Therefore, by using MLAs, we aimed to correlate PS-InSAR-based surface motion estimates and several environmental parameters. Specifically, in Reference [ 7 ], a Classification and Regression Tree algorithm (CART) [ 88 ] has been calibrated, whereas, in the next study [ 8 ], we extended the procedure by adding the calibration of a Random Forest (RF) algorithm [ 89 ], a Support Vector Machine (SVM) for Regression [ 90 , 91 ], and a Boosted Regression Tree (BRT) algorithm [ 92 , 93 ].…”

“…We aim to check if PS-InSAR is sufficiently able to detect surface irregularities highlighted by a profilometric survey. The proposed methodology stems from two previous studies [ 7 , 8 ], in which we calibrated several Machine Learning Algorithms (MLAs) for predicting vertical deformation of road pavement surfaces, in terms of [mm/year], by linking PS-InSAR-based outcomes and several environmental parameters. This modeling phase was due to insufficient PS coverage on the road surface of two-lane rural roads.…”