A Meta-Analysis of Artificial Intelligence in the Built Environment: High-Efficacy Silos and Fragmented Ecosystems

Cities face mounting pressures to deliver reliable, low-carbon services amid rapid urbanization and budget constraints. Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and the Internet of Things (IoT) are widely promoted to automate operations and strengthen decision-support across the built environment; however, it remains unclear whether these interventions are both effective and systemically integrated across domains. We conducted a Preferred Reporting Items for Systematic Reviews (PRISMA) aligned systematic review and meta-analysis (January 2015–July 2025) of empirical AI/ML/DL/IoT interventions in urban infrastructure. Searches across five open-access indices Multidisciplinary Digital Publishing Institute (MDPI), Directory of Open Access Journals (DOAJ), Connecting Repositories (CORE), Bielefeld Academic Search Engine (BASE), and Open Access Infrastructure for Research in Europe (OpenAIRE)returned 7432 records; after screening, 71 studies met the inclusion criteria for quantitative synthesis. A random-effects model shows a large, pooled effect (Hedges’ g = 0.92; 95% CI: 0.78–1.06; p < 0.001) for within-domain performance/sustainability outcomes. Yet 91.5% of implementations operate at integration Levels 0–1 (isolated or minimal data sharing), and only 1.4% achieve real-time multi-domain integration (Level 3). Publication bias is likely (Egger’s test p = 0.03); a conservative bias-adjusted estimate suggests a still-positive effect of g ≈ 0.68–0.70. Findings indicate a dual reality: high efficacy in silos but pervasive fragmentation that prevents cross-domain synergies. We outline actions, mandating open standards and APIs, establishing city-level data governance, funding Level-2/3 integration pilots, and adopting cross-domain evaluation metrics to translate local gains into system-wide value. Overall certainty of evidence is rated Moderate based on Grading of Recommendations Assessment, Development, and Evaluation (GRADE) due to heterogeneity and small-study effects, offset by the magnitude and consistency of benefits.