This Ph.D. dissertation focuses on optimizing automated decision-making processes involving critical aspects of road management tasks. Specifically, the research aims to define and implement specific strategies for supplying support to decision-makers considering two leading elements: road maintenance and road safety. We propose some novel applications based on the integrated use of high-performance Non-Destructive Techniques (NDTs) and Geographical Information Systems (GISs) in order to obtain a “fully sensed” infrastructure, creating a multi-scale database concerning structural, geometrical, functional, social, and environmental characteristics. The environmental aspect is essential since climate change phenomena and extreme natural events are increasingly linked with infrastructure damage and serviceability; nonetheless, current Pavement Management Systems (PMSs) commonly rely solely on road pavement structural characteristics and surface functional performance. The high amount of collected data serves as input for calibrating different data-driven approaches, such as Machine Learning Algorithms (MLAs) and statistical regressions. Considering the aspect of road monitoring and maintenance, such models allow identifying the environmental factors that have the most significant impact on road damage and serviceability, as well as recognizing road sites with critical health conditions that need to be restored. Moreover, the calibrated MLAs enable decision-makers to determine the road maintenance interventions with higher priority. Considering road safety, the calibrated MLAs allow identifying the sites where serious road crashes can be triggered and estimating the crash count in a specified time frame. Moreover, it is possible to recognize infrastructure-related factors that significantly impact crash likelihood. Road authorities may consider the outcomes of the dissertation as a novel approach for drafting appropriate guidelines and defining more objective management programs.

Intelligent solutions for supporting decision-making processes in road management: A general framework accounting for environment, road serviceability, and user’s safety / Nicholas Fiorentini. - (2022).

Intelligent solutions for supporting decision-making processes in road management: A general framework accounting for environment, road serviceability, and user’s safety

Nicholas Fiorentini
2022

Abstract

This Ph.D. dissertation focuses on optimizing automated decision-making processes involving critical aspects of road management tasks. Specifically, the research aims to define and implement specific strategies for supplying support to decision-makers considering two leading elements: road maintenance and road safety. We propose some novel applications based on the integrated use of high-performance Non-Destructive Techniques (NDTs) and Geographical Information Systems (GISs) in order to obtain a “fully sensed” infrastructure, creating a multi-scale database concerning structural, geometrical, functional, social, and environmental characteristics. The environmental aspect is essential since climate change phenomena and extreme natural events are increasingly linked with infrastructure damage and serviceability; nonetheless, current Pavement Management Systems (PMSs) commonly rely solely on road pavement structural characteristics and surface functional performance. The high amount of collected data serves as input for calibrating different data-driven approaches, such as Machine Learning Algorithms (MLAs) and statistical regressions. Considering the aspect of road monitoring and maintenance, such models allow identifying the environmental factors that have the most significant impact on road damage and serviceability, as well as recognizing road sites with critical health conditions that need to be restored. Moreover, the calibrated MLAs enable decision-makers to determine the road maintenance interventions with higher priority. Considering road safety, the calibrated MLAs allow identifying the sites where serious road crashes can be triggered and estimating the crash count in a specified time frame. Moreover, it is possible to recognize infrastructure-related factors that significantly impact crash likelihood. Road authorities may consider the outcomes of the dissertation as a novel approach for drafting appropriate guidelines and defining more objective management programs.
Massimo Losa, Markus Gerke
ITALIA
Nicholas Fiorentini
File in questo prodotto:
File Dimensione Formato  
Thesis_Nicholas_Fiorentini_Official_2022.pdf

embargo fino al 22/06/2023

Tipologia: Pdf editoriale (Version of record)
Licenza: Open Access
Dimensione 66.43 MB
Formato Adobe PDF
66.43 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/2158/1279821
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact