Data-Driven Condition Assessment of Bridge Infrastructure in the Rabat-Salé-Kénitra Region: A Big Data Analytics Approach for Strategic Maintenance Planning

¹ ABDELMALEK ESSAADI UNIVERSITY, National School of Applied Sciences AL HOCEIMA, Laboratory of Engineering Sciences and Applications, AL HOCEIMA, Morocco.
² National School of Applied Sciences EL JADIDA, CHOUAIB DOUKKALI UNIVERSITY EL JADIDA, Morocco.
³ Energy4Water Research Center (E4W) , University Mohammed VI Polytechnic (UM6P), Benguerir, Morocco.
⁴ MOHAMMED FIRST UNIVERSITY, OUJDA faculty of sciences, Laboratory of Engineering Sciences and Applications, OUJDA, Morocco.

^* Correspondance: This email address is being protected from spambots. You need JavaScript enabled to view it. , This email address is being protected from spambots. You need JavaScript enabled to view it. .

Abstract

This paper presents a comprehensive data analytics framework for evaluating the structural condition of bridge infrastructure in Morocco's Rabat-Salé-Kénitra region, leveraging a heterogeneous dataset comprising 930 bridge structures inspected between 2018 and 2020. Drawing inspiration from established big data methodologies in infrastructure asset management, this study categorizes structures by typological families (concrete bridges, culverts, masonry vaults, submersible structures) and analyzes spatiotemporal deterioration patterns across three distinct provinces. The condition ratings of bridge elements are examined statistically and probabilistically, incorporating both structural parameters (total span, deck width) and environmental exposure variables (hydrological proximity, coastal atmospheric influence).

Statistical characterization reveals a predominance of concrete-based structures (62%), followed by culverts (28%) and historical masonry vaults (8%). Structures situated in coastal zones or aggressive environments exhibit substantially accelerated degradation trajectories compared to inland equivalents, with 34% of coastal bridges rated in critical classes (3S or 4S) requiring urgent specialized intervention. Two-factor analysis of variance (ANOVA) demonstrates statistically significant main effects of both structure type and environmental exposure on global condition indices, without confounding interaction effects. Consequently, the likelihood of rapid deterioration is notably magnified for structures traversing permanent watercourses (e.g., Oued Sebou) and those in flood-prone topographies due to persistent hydraulic scour and dynamic loading.

To operationalize these findings, a probabilistic degradation model based on discrete-time Markov chains (DTMC) is developed to estimate transition probabilities between discrete condition states. This provides a robust predictive algorithm for infrastructure managers. The findings ultimately support the deployment of a provincial-scale decision-support system (DSS) strictly aligned with Morocco's SGOAM (Système de Gestion des Ouvrages d'Art Marocain). This framework shifts the management paradigm from reactive remediation to evidence-based, predictive prioritization, thereby optimizing the life-cycle cost and ensuring the sustainable allocation of constrained public resources.