The given research employs high-resolution air quality monitoring and contemporary statistical methods to address gaps in understanding the urban air pollution in Pavlodar, a city with a significant industrial presence and promising touristic potential. Using mobile air quality sensors for detailed spatial data collection, the research aims to quantify concentrations of particulate matter (PM_2.5, PM₁₀), carbon monoxide (CO), nitrogen dioxide (NO₂), sulfur dioxide (SO₂), and ground-level ozone (O₃); assess their distribution; and identify key influencing factors. In this study, we employed Geographic Information Systems (GISs) for spatial analysis, integrating multi-level B-spline interpolation to model spatial variability. Correlation analysis and structural equation modeling were utilized to explore the relationships between variables, while regression analysis was conducted to quantify these relationships. These techniques were crucial for accurately mapping and interpreting spatial patterns and their underlying factors. The study identifies PM_2.5 and NO₂ as the primary contributors to air pollution in Pavlodar, with NO₂ exceeding the 24 h threshold in 87.38% of locations and PM_2.5 showing the highest individual air quality index (AQI) in 75.7% of cases. Correlation analysis reveals a positive association between PM_2.5 and AQI and a negative correlation between NO₂ and AQI, likely due to the dominant influence of PM_2.5 in AQI calculations. Structural equation modeling (SEM) further underscores PM_2.5 as the most significant impactor on AQI, while NO₂ shows no significant direct impact. Humidity is positively correlated with AQI, though this relationship is context-specific to seasonal patterns observed in May. The sectoral analysis of landscape indices reveals weak correlations between the green space ratio (GSR) and air quality, indicating that while vegetation reduces pollutants, its impact is minimal due to urban planting density. The road ratio (RR) lacks sufficient statistical evidence to draw conclusions about its effect on air quality, possibly due to the methodology used. Spatial variability in pollutant concentrations is evident, with increasing PM_2.5, PM₁₀, and AQI towards the east-northeast, likely influenced by industrial activities and prevailing wind patterns. In contrast, NO₂ pollution does not show a clear geographic pattern, indicating vehicular emissions as its primary source. Spatial interpolation highlights pollution hotspots near industrial zones, posing health risks to vulnerable populations. While the city’s overall AQI is considered “moderate”, the study highlights the necessity of implementing measures to improve air quality in Pavlodar. This will not only enhance the city’s attractiveness to tourists but also support its sustainable development as an industrial center.

This study addressed the critical challenge of filling gaps in PM2.5 time series data from Pavlodar, Kazakhstan. We developed and evaluated a comprehensive hierarchy of 46 gap-filling methods across five representative gap lengths (5–72 hours), introducing dynamic models capable of adapting to gaps of variable duration. Tree-based models with bidirectional sequence-to-sequence architectures delivered superior performance, with XGB Seq2Seq achieving a mean absolute error of 5.231 ± 0.292 μg/m³ for 12-hour gaps, representing a 63% improvement over basic statistical methods. The advantage of multivariate models incorporating meteorological variables increased substantially with gap length, from modest improvements of 2–3% for 5-hour gaps to significant enhancements of 16–18% for 48–72 hour gaps. Dynamic multivariate models demonstrated remarkable operational flexibility by successfully processing real-world gaps ranging from 1 to 191 hours despite being trained on maximum lengths of 72 hours. Analysis of the reconstructed complete time series revealed that 61.2% of monitored hours exceeded the WHO daily threshold of 15 μg/m³, with strong seasonal patterns and pronounced diurnal cycles. This research advances environmental monitoring capabilities by providing robust methodological tools for addressing data continuity challenges that currently limit the utility of PM2.5 measurements for public health applications and scientific analysis.

This study focused on predicting the spatial distribution of environmental risk indicators using mathematical modeling methods including machine learning. The northern industrial zone of Pavlodar City in Kazakhstan was used as a model territory for the case. Nine models based on the methods kNN, gradient boosting, artificial neural networks, Kriging, and multilevel b-spline interpolation were employed to analyze pollution data and assess their effectiveness in predicting pollution levels. Each model tackled the problem as a regression task, aiming to estimate the pollution load index (PLI) values for specific locations. It was revealed that the maximum PLI values were mainly located to the southwest of the TPPs over some distance from their territories according to the average wind rose for Pavlodar City. Another area of high PLI was located in the northern part of the studied region, near the Hg-accumulating ponds. The high PLI level is generally attributed to the high concentration of Hg. Each studied method of interpolation can be used for spatial distribution analysis; however, a comparison with the scientific literature revealed that Kriging and MLBS interpolation can be used without extra calculations to produce non-linear, empirically consistent, and smooth maps.

A Pavlodari Alumíniumgyár hamu-iszap gyűjtőjéből szerzett minták alapján elkészítettünk egy idegpálya hálózati modellt, amely segítségével előre jelezhető a termelés során keletkező hulladék anyagok koncentrációja és mennyisége. Minden egyes elem külön idegpálya modellen van reprezentálva. A modellt a Levenberg-Marquardt algoritmus vezérli. Az idegpálya 5 szintből áll, az első a bemenet, az ötödik a kimenet, köztük pedig 3 rejtett szint található. Az idegpálya modell nagy pontossággal elemzi a tó különböző részeiről beszerzett mintákat, Az elemzés kimutatja, hogy nevezett helyeken nagy fokú a szilicium (Si), kalcium (Ca), réz (Cu, és vas (Fe) koncentráció, ugyanakkor a mangán (Mn), vanádium (V), titán (Ti), szkandium (Sc) és gallium (Ga) kisebb mennyiségben van jelen. Az idegpálya modell pontosságát meghatározó tényezők között említendő a rétegek, vagy szintek száma, illetve az irányító algoritmus.