A Bayesian Network model to integrate blue-green and gray infrastructure systems for different urban conditions

ORAK N. H., Smail L.

Journal of Environmental Management, vol.375, 2025 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 375
  • Publication Date: 2025
  • Doi Number: 10.1016/j.jenvman.2025.124293
  • Journal Name: Journal of Environmental Management
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, International Bibliography of Social Sciences, PASCAL, Aerospace Database, Agricultural & Environmental Science Database, Aqualine, Aquatic Science & Fisheries Abstracts (ASFA), BIOSIS, CAB Abstracts, Communication Abstracts, Environment Index, Geobase, Greenfile, Index Islamicus, Metadex, Pollution Abstracts, Public Affairs Index, Veterinary Science Database, Civil Engineering Abstracts
  • Keywords: Bayesian Network, Blue-Green infrastructure, Climate change adaptation, Gray infrastructure, Hybrid systems, Infrastructure planning, Nature-based solutions, Urban areas
  • Marmara University Affiliated: Yes

Abstract

In facing growing challenges in cities and the environment, cities need to make informed decisions on where and how to allocate resources for infrastructure investments. Nature-based Solutions present a promising approach to urban environmental and socioeconomic challenges, but their successful integration into urban planning requires a nuanced understanding of both their benefits and limitations. This paper presents a preliminary Bayesian Network model designed to model the optimal integration of specific blue-green and gray Infrastructure solutions in hybrid systems for specific local contexts. The preliminary model considers a wide range of factors related to both infrastructure solutions, giving policymakers suitable arrangements tailored to their specific local conditions. With its probabilistic approach, the Bayesian Network model is a powerful tool for navigating the complex world of infrastructure planning. While the current model provides initial insights, its practical utility will be enhanced through the incorporation of higher-resolution data and application to specific case studies, enabling more accurate, context-sensitive recommendations. This research aims to connect data-driven modeling with practical urban planning, pushing forward the discussion on combining blue, green, and gray solutions for cities that are more sustainable and resilient.