Reliable urban air-quality assessment increasingly depends on integrating heterogeneous data sources, yet doing so in data-sparse cities, where reference monitoring is limited and low-cost sensors dominate, remains an open challenge. This study presents a reproducible framework for integrating and analyzing heterogeneous urban sensor data, demonstrated on Almaty, Kazakhstan. Two complementary sources were linked at the station level through a shared identifier: a historical low-cost network of 146 stations (2020–2026; 544,943 records) and a real-time collector providing traffic and source-context features. A three-stage quality-control pipeline retained 442,322 records across 39 stations. Spatial inequality was quantified with complementary indices, attributed to emission sources through geometric descriptors, and used to compare predictive models. Exposure was substantially unequal (winter, seasonally standardized Gini 0.197; full-period Gini 0.210; population-weighted Gini 0.09), with the population-weighted annual mean PM2.5 (19.8 µg/m³) nearly four times the WHO annual guideline (5 µg/m³); virtually the entire population lives in districts whose annual mean exceeds this guideline. The inequality showed a spatial association with position downwind (p = 0.056), reported as exploratory given Almaty’s lack of a consistent prevailing winter wind. On the sparse network, regression failed to predict continuous concentrations (R² ≈ 0), and once evaluation leakage was removed, classification of high-exposure locations did not exceed a prevalence-aware baseline either (best model 72%, 95% CI overlapping the baseline), indicating that neither task is reliably validated at this network size—a cautionary finding for data-sparse settings generally. The framework provides a transferable template for air-quality assessment in data-scarce urban environments.

Urban air pollution driven by road traffic poses a significant public health challenge in cities with high vehicle density and frequent congestion, particularly in topographically constrained environments such as Almaty, Kazakhstan. This study presents a web-based digital twin prototype for the integrated monitoring and analysis of traffic flow and air quality in Almaty, Kazakhstan. The system autonomously collects data from the TomTom Traffic, OpenWeather Air Pollution, and WAQI APIs and official population statistics for five fixed monitoring stations, computing traffic density, vehicles per hour, road congestion, estimated CO₂ emissions, an air pollution index, and a population exposure index, and providing real-time dashboard visualization alongside longitudinal data accumulation. Over a 50-day deployment (26 May–16 July 2026), 4961 real co-located observations across 18 active days were analyzed; records generated by the prototype’s fallback mechanism during API outages were excluded from the scientific analysis. During this summer period, PM2.5 was low (mean ≈ 6 µg/m³) and spatially uniform, and showed no statistically significant association with traffic intensity (r ≈ −0.03). Traffic indicators were instead weakly but significantly correlated with the vehicle-emitted gases NO₂ (r ≈ 0.16) and CO (r ≈ 0.10), which they preceded by up to about one hour. A short-horizon PM2.5 nowcasting task, evaluated across temporal resolutions with time-series cross-validation, was dominated by temporal persistence, with traffic-derived features contributing negligibly. The absence of a summer traffic–PM2.5 association does not preclude such a relationship during the heating season, when particulate levels are higher. The results indicate that the traffic–air-quality relationship in Almaty is season- and pollutant-dependent, and demonstrate a lightweight, reproducible platform suitable for longitudinal monitoring and future heating-season assessment.