Skip to main content

REINFORCEMENT LEARNING ADAPTADO AL MANTENIMIENTO RESILIENTE DE CARRETERAS FRENTE AL CAMBIO CLIMATICO

PREP2022-000319

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Desarrollar, Atraer y Retener Talento
Subprogram Subprograma Estatal de Formación
Call Contratos Predoctorales
Call year 2022
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Reinforcement learning for sustainable pavement maintenance planning under increasingly extreme climate conditions

  • Molinero-Pérez, Noelia|||0000-0001-8279-4585
  • Sanz-Benlloch, Amalia|||0000-0001-8051-0649
  • Montalbán-Domingo, Laura|||0000-0002-9506-0350
  • García-Segura, Tatiana|||0000-0002-7059-0566
[EN] Extreme climatic events are increasingly recognized as key drivers of pavement deterioration, yet their implications for long-term maintenance planning remain insufficiently understood. This article proposes a framework for evaluating optimal maintenance strategies under the influence of climate extremes. The framework combines a machine learning model that predicts Pavement Condition Index evolution using extreme climate indicators with a multi-objective reinforcement learning (RL) approach to maintenance planning. A regional pairedscenario analysis, based on data from the Long-Term Pavement Performance (LTPP) program, demonstrates the model's ability to capture differences in deterioration between scenarios with similar mean climate conditions but contrasting extreme event profiles. Results show that climate extremes substantially accelerate deterioration, leading to earlier and more frequent interventions. The RL-based framework identifies climate-aware policies that balance pavement performance, user benefits, costs, and environmental impacts. These findings underscore the need for climate-sensitive, multi-objective pavement management approaches to support sustainable and resilient infrastructure systems., This research is part of the grant PID2022-141875OA-I00, funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU.