Skip to main content

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

PID2022-141875OA-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
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): 4
Encontrada(s) 1 página(s)

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

A Machine Learning Framework for Pavement Performance Prediction Under Extreme Climate Conditions

  • Molinero-Pérez, Noelia|||0000-0001-8279-4585
  • García-Segura, Tatiana|||0000-0002-7059-0566
  • Heras, Stella|||0000-0001-6212-9377
  • Sanz-Benlloch, Amalia|||0000-0001-8051-0649
  • Ortiz-Garrido, Pedro
[EN] Accurate pavement performance prediction is critical for effective pavement management systems (PMS), enabling optimal maintenance and rehabilitation decisions. The Pavement Condition Index (PCI) is the most widely used performance indicator, yet reliable prediction requires models that capture full spectrum of deterioration drivers, including structural characteristics, traffic loads, and the increasingly impactful extreme climate events. While machine learning (ML) approaches have improved PCI prediction, most existing models overlook climate extremes. This study proposes a comprehensive ML-based PCI model that integrates extreme climate variables from the Expert Team on Climate Change Detection and Indices (ETCCDI). Eleven algorithms were evaluated on a dataset combining pavement age, structural characteristics, traffic loads, and extreme climate variables. Among the evaluated models, categorical boosting model achieved the lowest error values and the highest R2 (0.81). Explainability analyses using feature importance and SHapley Additive exPlanations (SHAP) identified the number of icing days (ID), daily temperature range in December (DTR_Dec) and consecutive dry days (CDD) as the extreme climate indicators with the greatest negative predictive influence on PCI. Incorporating ETCCDI indices provided additional explanatory power beyond traditional annual average climatic variables, significantly improving both predictive accuracy and model interpretability. These findings highlight the importance of integrating standardized extreme climate indicators into PMS frameworks to support more resilient and sustainable pavement management under evolving climate conditions., This research is part of the grant PID2022-141875OA-I00, funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU.
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.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Sustainable pavement maintenance using reinforcement learning with systematic reward design

  • 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] Efficient and sustainable pavement maintenance planning remains a challenge for infrastructure managers. This study introduces a reinforcement learning methodology, based on the Q-Learning algorithm, to optimize long-term pavement maintenance policies under multiple objectives. The contribution is a systematic framework for designing tailored reward functions aligned with planning goals, including economic cost, environmental impact, user savings, and maintenance effectiveness. This alignment enables the model to adapt and learn optimal strategies according to different priorities. The approach is validated through fifteen real-world case studies from the Spanish road network, incorporating traffic, structural, and climatic data. For each case, Q-Learning is trained with alternative reward formulations and evaluated over a 20-year horizon, followed by robustness analysis to assess policy stability. Results show that reward functions lead to differentiated intervention strategies, influenced by the planning objective. Cost- and emissions-oriented rewards generate reactive policies, recommending intervention only when inaction would significantly increase maintenance and rehabilitation costs. In contrast, rewards focused on user savings or technical effectiveness promote proactive continuous maintenance to preserve surface conditions and reduce indirect user costs. The proposed approach underscores the critical role of reward definition in reinforcement learning and provides a practical tool to support adaptive, sustainable, and long-term pavement management., This research is part of the grant PID2022-141875OA-I00, funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Artículo científico (JournalArticle)

Dual Model for International Roughness Index Classification and Prediction

  • Molinero-Pérez, Noelia|||0000-0001-8279-4585
  • Montalbán-Domingo, Laura|||0000-0002-9506-0350
  • Sanz-Benlloch, Amalia|||0000-0001-8051-0649
  • García-Segura, Tatiana|||0000-0002-7059-0566
[EN] Existing models for predicting the international roughness index (IRI) of a road surface often lack adaptability, struggling to accurately reflect variations in climate, traffic, and pavement distresses¿factors critical for effective and sustainable maintenance. This study presents a novel dual-model approach that integrates pavement condition index (PCI), pavement distress types, climatic, and traffic data to improve IRI prediction. Using data from the Long-Term Pavement Performance database, a dual-model approach was developed: pavements were classified into groups based on key factors, and tailored regression models were subsequently applied within each group. The model exhibits good predictive accuracy, with R2 values of 0.62, 0.72, and 0.82 for the individual groups. Furthermore, the validation results (R2 = 0.89) confirm that the combination of logistic regression and linear regression enhances the precision of IRI value predictions. This approach enhances adaptability and practicality, offering a versatile tool for estimating IRI under diverse conditions. The proposed methodology has the potential to support more effective, data-driven decisions in pavement maintenance, fostering sustainability and cost efficiency., This research is part of the grant PID2022-141875OA-I00, funded by MCIN/AEI/10.13039/501100011033 and by ERDF/EU.