Integrating Heterogeneous Sensor Data for Source-Aware Air-Quality Analysis in Data-Sparse Urban Networks: A Case Study of Almaty

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.