Artificial intelligence is becoming an increasingly used component in municipal operations, with applications spanning administrative automation, decision support, citizen interfaces, and predictive analytics across domains such as mobility, health and social services, and environmental management. While the literature documents benefits in operational efficiency and decision quality, most concrete evidence focuses primarily on internal efficiency. Urban digital twins have become commonplace in most European cities and smart cities globally. However, the role of AI within urban digital twins remains comparatively underexplored. This article addresses these gaps through a qualitative analysis of AI in Helsinki’s Experimentation Accelerator platform experiments and by comparing them against a DT framework based on the literature. Through this, we analyze how AI is piloted in municipal applications and how the identified use cases of AI align with the components of urban digital twins, identifying potential roles for AI in the urban digital twin as well as directions for future development.
Intelligent Transportation Systems (ITS) leverage fog computing to process high-frequency vehicular data locally, but securing these continuous data streams against future quantum computers remains a critical challenge. A systematic review using the Context–Intervention–Mechanism–Outcome (CIMO) framework shows that existing architectures address Zero-Trust principles, fog computing, and Post-Quantum Cryptography (PQC) independently, leaving a significant convergence gap. To bridge this gap, this paper proposes a Hybrid Post-Quantum Zero-Trust Architecture (HPQC-ZTA) for public transportation. It combines the NIST-standardized ML-KEM-768 (CRYSTALS-Kyber) and ML-DSA-65 (CRYSTALS-Dilithium) with classical X25519 and ECDSA-P256 in hybrid mode, and it verifies message signatures in parallel micro-batches at the fog layer. Fog nodes act as Zero-Trust Policy Enforcement Points: they compute a dynamic trust score from firmware integrity, location, and speed, issue five-minute Zero-Trust Access Tokens, and enforce pseudonym rotation every 10 min with random jitter to prevent tracking. The architecture was implemented as a working prototype and evaluated in a discrete-event simulation of a 5G transit hub with up to 5000 buses. Batch verification is 2.6 times faster than serial verification, and the design delivers every message with a 95th-percentile end-to-end latency of about 25 ms for up to 2000 buses per hub, four times the capacity of a naive PQC deployment. It also passed all executed Shor and Grover resilience tests, including forward secrecy against harvest-now-decrypt-later attacks, showing that quantum-resilient Zero-Trust security is practical for large-scale public transportation.
Pedestrian crossings are essential elements of sustainable road design because they mediate interactions among motorized traffic, active mobility, and users with diverse abilities. At night, poor pedestrian visibility, delayed yielding, excessive approach speed, and inaccessible or poorly coordinated infrastructure can turn a compliant crossing into a high-risk conflict point. Intelligent pedestrian-crossing illumination integrates approach-specific photometry, warning devices, sensing, communications, edge processing, and artificial intelligence to adapt the road environment to pedestrian presence and traffic conditions. This critical review evaluates such systems as people-centered smart-road infrastructure rather than isolated lighting devices. Evidence is synthesized across road-safety performance, human factors, sensing and AI reliability, inclusive design, operational energy, life-cycle burdens, economic considerations, and ecological effects of artificial light at night. Studies show that improved pedestrian contrast, appropriate luminaire placement, vertical illumination, and timely warnings can enhance detection, yielding, approach speed, and stopping behavior. However, current evidence is heterogeneous and dominated by simulators, staged pedestrians, single-site demonstrations, short monitoring periods, and surrogate outcomes. Critical aspects such as crash reduction, adverse-weather reliability, accessibility, resilience, life-cycle performance, and biodiversity impacts are rarely assessed together. Three complementary outputs are proposed: an evidence-maturity framework, a multidimensional trade-off framework, and a stage-gated pathway for context-sensitive deployment.
The anomaly detection of urban rail vehicle door systems is crucial for the security and reliability of rail vehicles, and unsupervised methods have received particular attention in anomaly detection due to the scarcity of anomaly data. However, existing studies have the following limitations: (1) The dynamic interrelationships between different sensor variables are not explicitly considered, which is detrimental to the learning of normal patterns. (2) The detection performance is limited due to the reliance on manual threshold settings and the lack of confidence measures for different sensor variables. To overcome the abovementioned limitations, a dynamic graph attention-based unsupervised bi-learning framework for the anomaly detection of rail vehicle door systems is proposed in this paper. First, a dynamic graph attention block (DGAT block) is designed to model dynamic interactions between sensor variables and fuse information during signal coding. Then, a bi-learning framework is developed to automatically learn thresholds and quantify the confidence of sensor variables for anomaly detection. The proposed method is verified on a real rail vehicle door system. Compared with the state-of-the-art autoencoder-based methods that are applicable to multivariate time series data, the proposed method improves the best competing precision and F1-score by 7.7% and 4.3%, respectively, while reducing the false positive rate (FPR) by 88.9%.
The management of urban heat in Saudi Arabia needs decision-support methods to separate persistent thermal patterns from city-specific climate and morphology effects. The study presents a reproducible open-data framework for Riyadh, Jeddah, and Dammam based on observations during the summer months (June–September) from 2014 to 2025. We derived land surface temperature (LST), NDVI and NDBI from Landsat 8/9 Collection 2 Level 2 imagery, background meteorology from ERA5-Land, built-up surface and time-varying population from GHSL, and a 2020 age-structure vulnerability layer from WorldPop. Each city was studied within a standard 30 km radial study window with permanent water masked. The final database included 545,027 spatial records and a Landsat manifest of 720 scenes, with no missing values for the main analytical variables. Annual median summer LST P90 varied significantly at the city level (Kruskal–Wallis H = 20.20, p < 0.001). The highest 12-year median was observed in Dammam (56.80 °C) followed by Jeddah (54.90 °C) and Riyadh (53.66 °C). No statistically significant monotonic trend was detected in the annual spatial median of summer LST P90 in any of the three cities over 2014–2025. NDVI was negatively correlated with LST P90, while NDBI positively correlated with LST P90 in all three cities. Under 0.05° spatial-block cross-validation, histogram gradient boosting achieved R2 = 0.679 ± 0.044 and RMSE = 1.54 ± 0.06 °C. Because ERA5-Land predictors are spatially coarser than the validation blocks, these performance estimates may be optimistic for independently sampled locations. Leave-one-city-out tests showed restricted transferability under a two-city training design, potentially reflecting environmental distribution shifts and limited model extrapolation. Permutation importance and SHAP identified background air temperature, relative humidity, elevation, NDBI and population intensity as important predictors. A 2025 adaptation-priority index combining thermal hazard, population exposure, and age-related sensitivity showed similar rankings under geometric and arithmetic aggregation (Spearman ρ = 0.90–0.95), although this agreement does not constitute independent validation, and the resulting classes are strongly differentiated by population exposure. The results support city-specific and spatially targeted heat-resilience planning, rather than a single national thermal model.
