Environmental Monitoring Station Research Articles

Characteristics of Ozone Photochemical Reaction and Emission Reduction Strategies in Summer and Autumn in Shangqiu

Recently, ozone （O3） pollution in Shangqiu has become increasingly prominent, especially in summer and autumn, crucially affecting the local environmental air quality. Based on the monitoring data of O3 pollution days from the Environmental Monitoring Station in June and September 2022 （representing summer and autumn） in Shangqiu, an observation-based model （OBM） was used to study the causes and photochemical reaction characteristics of O3 pollution in the city and precursor emission reduction strategies were studied. The observation results indicated that during summer in Shangqiu, the ρ（O3） and O3 daily maximum 8 h moving concentrations [ρ（MDA8-O3）] were 149.7 μg·m-3 and 195.4 μg·m-3, whereas in autumn, ρ（O3） and ρ（MDA8-O3） were 119.8 μg·m-3 and 173.9 μg·m-3, respectively； the O3 concentration in summer was significantly higher than that in autumn. Ozone sensitivity research showed that the generation of O3 in summer and autumn in Shangqiu was controlled by volatile organic compounds （VOCs）. Among them, oxygen-containing volatile organic compounds （OVOCs）, aromatic hydrocarbons, and alkenes contributed the most to the ozone generation potential （OFP） and ·OH reactivity （L·OH）, and the control must have been strengthened. The OBM simulation results indicated that the maximum O3 generation rates in summer and autumn were 23.0×10-9 h-1 and 13.6×10-9 h-1, with maximum net generation rates of 17.4×10-9 h-1 and 10.4×10-9 h-1 and the maximum and maximum net generation rates of O3 in summer were 1.68 times higher than those in autumn, indicating that the photochemical reactions in summer were significantly stronger than those in autumn. Compared with that in summer, the generation of O3 in autumn was greatly influenced by regional inputs from other regions or cities, with a maximum input of 14.2×10-9 h-1. The prevention and control of O3 pollution in the summer and autumn seasons in Shangqiu should mainly focus on controlling VOCs. The reduction ratio of VOCs/nitrogen oxides （NOx） in autumn should be greater than that in summer and the reduction ratios of 3∶1 in summer and 4∶1 in autumn could be adopted for control.

Near-surface ozone concentration variability analysis in the Karadag Nature Reserve

The article presents the results of a study of a near-surface ozone concentration variability in the Crimea at the background environmental monitoring station in the Karadag Nature Reserve for 2012–2021 years with a more detailed analysis of the last six years from 2016 to 2021. A significantly high level air pollution of а near-surface ozone was revealed in the observation region, despite the absence of nearby sources of industrial emissions. The relationship of near-surface ozone concentration and meteorological parameters was investigated. Wind directions leading to increased levels of near-surface ozone pollution are established. Intra-annual variations of near-surface ozone concentration are analyzed, the factors causing the local summer minimum of surface ozone concentration in some years are established. By using the NOAA HYSPLIT model and ERA5 reanalysis, a spatial analysis of the atmospheric circulation pattern in the region was carried out. The recurrence of episodes of exceeding the ozone concentration 100 micrograms/m3 during 8 or more hours (WHO recommendation) was estimated. Possible causes of these episodes were determined. The mechanisms of long-range transport and its contribution to the near-surface ozone regime in the area of the station have been established. Annual trends of near-surface ozone concentration in the period 2012–2021 years are estimated as statistically insignificant.

Air Pollution and Urban Economic Growth: A Study Based on Dynamic Models

<p class="Paragraph"><span lang="EN-US">With China's economic growth, the issue of air pollution has become increasingly prominent. As the core of political and economic development, 184 major cities in China face severe air pollution and significant environmental pressures due to high population density. Consequently, China has established key urban environmental monitoring stations in these cities to monitor pollution emissions in real time. This paper utilizes panel data from 184 Chinese cities spanning 2012-2022 and employs dynamic GMM models, fixed effects models, and mediation effect models to empirically examine the impact of air pollution on urban environmental pollution and its mediation mechanisms. From the perspective of cities with different income levels, a dynamic GMM model is established to determine the correlation between air pollution and various factors influencing urban economic growth. The study finds that air pollution significantly reduces economic growth in Chinese cities at the 1 per cent level, with each unit increase in air pollution reducing economic growth in Chinese cities by 0.84 units. Urbanization and human capital are identified as two crucial channels through which air pollution affects the economic development of Chinese cities. The negative impact of air pollution on economic growth is more pronounced in larger cities compared to smaller ones, and the adverse effects of haze pollution become increasingly significant over time. Therefore, policymakers should take the cultivation and application of new quality productivity as a key strategy to enhance the quality of economic development, and realise a win-win situation between economic growth and environmental protection through scientific and technological innovation and industrial restructuring. This will not only help alleviate the air pollution problem, but also inject new momentum into the high-quality development of China’s economy.</span></p>

Weighted Averages and Polynomial Interpolation for PM2.5 Time Series Forecasting

This article describes a novel method for the multi-step forecasting of PM2.5 time series based on weighted averages and polynomial interpolation. Multi-step prediction models enable decision makers to build an understanding of longer future terms than the one-step-ahead prediction models, allowing for more timely decision-making. As the cases for this study, hourly data from three environmental monitoring stations from Ilo City in Southern Peru were selected. The results show average RMSEs of between 1.60 and 9.40 ug/m3 and average MAPEs of between 17.69% and 28.91%. Comparing the results with those derived using the presently implemented benchmark models (such as LSTM, BiLSTM, GRU, BiGRU, and LSTM-ATT) in different prediction horizons, in the majority of environmental monitoring stations, the proposed model outperformed them by between 2.40% and 17.49% in terms of the average MAPE derived. It is concluded that the proposed model constitutes a good alternative for multi-step PM2.5 time series forecasting, presenting similar and superior results to the benchmark models. Aside from the good results, one of the main advantages of the proposed model is that it requires fewer data in comparison with the benchmark models.

Enhancing Air-Quality Predictions on University Campuses: A Machine-Learning Approach to PM2.5 Forecasting at the University of Petroșani

This study focuses on predicting PM2.5 levels at the University of Petroșani by employing advanced machine-learning techniques to analyze a dataset that encapsulates a wide array of air pollutants and meteorological factors. Utilizing data from Internet of Things (IoT) sensors and established environmental monitoring stations, the research leverages Random Forest, Gradient Boosting Machines, and Support Vector Regression models to forecast air quality, emphasizing the complex interplay between various pollutants. The models demonstrate varying degrees of accuracy, with the Random Forest model achieving the highest predictive power, indicated by an R2 score of 0.82764. Our findings highlight the significant impact of specific pollutants such as NO, NO2, and CO on PM2.5 levels, suggesting targeted mitigation strategies could enhance local air quality. Additionally, the study explores the role of temporal dynamics in pollution trends, employing time-series analysis to further refine the predictive accuracy. This research contributes to the field of environmental science by providing a nuanced understanding of air-quality fluctuations in a university setting and offering a replicable model for similar environments seeking to reduce airborne pollutants and protect public health.

Research on characteristics and influencing factors of road dust emission in a southern city in China.

One of the primary causes of urban atmospheric particulate matter, which is harmful to human health in addition to affecting air quality and atmospheric visibility, is road dust. This study used online monitoring equipment to examine the characteristics of road dust emissions, the effects of temperature, humidity, and wind speed on road dust, as well as the correlation between road and high-space particulate matter concentrations. A section of a real road in Jinhua City, South China, was chosen for the study. The findings demonstrate that the concentration of road dust particles has a very clear bimodal single-valley distribution throughout the day, peaking between 8:00 and 11:00 and 19:00 and 21:00 and troughing between 14:00 and 16:00. Throughout the year, there is a noticeable seasonal change in the concentration of road dust particles, with the highest concentration in the winter and the lowest in the summer. Simultaneously, it has been discovered that temperature and wind speed have the most effects on particle concentration. The concentration of road dust particles reduces with increasing temperature and wind speed. The particle concentrations of road particles and those from urban environmental monitoring stations have a strong correlation, although the trend in the former is not entirely consistent, and the changes in the former occur approximately 1 h after the changes in the latter.

The impact of the urban landscape on PM2.5 from LCZ perspective: A case study of Shenyang

Based on the World City Database Access Portal tool (WUDAPT), the local Climate zoning (LCZ) classification of Shenyang(China) was carried out. With 8 environmental monitoring stations at the observation of the study area, LCZ landscape categories in the buffer zone of 500 m, 1000 m, and 3000 m were analyzed using ArcMap and Fragstats. The sensitivity analysis of the landscape category index correlated with PM2.5 was conducted to select the representativeness index. Matlab was used to construct the regression equation between the LCZ categories and PM2.5. The results show that AI_500, LSI_500, PD_500, LSI_1000, AI_1000, LSI_3000, and AI_3000 can be used as representative landscape indices to represent the aggregation and diversity of LCZ categories. The regression equations for PM2.5 in all four seasons include factors influencing the LCZ category landscape. This study analyzed the relationship between PM2.5 distribution and urban patterns from the perspective of the LCZ types. It provided the scientific reference for rational planning of urban layout and coordination of environment and urban development.

Environmental and legal aspects of the armed aggression of the Russian Federation against Ukraine

The article examines the environmental and legal aspects of the armed aggression of the Russian Federation against Ukraine. The problems of bringing the aggressor state to responsibility for ecocide are analyzed. Having found a legislative enshrinement in the national criminal law (Article 441 of the Criminal Code of Ukraine), ecocide has not been enshrined in international criminal law. It is not recognized as a crime either in the Rome Statute of the International Criminal Court or in any other international legal act. As of today, Russian crimes against the environment can be investigated by the International Criminal Court as war crimes. The author of the article supports the proposal regarding the need to include the crime of ecocide in the Rome Statute. The ecological and legal aspect of the formation of an international compensation mechanism is studied, the components of which are: 1) an international register of damages; 2) compensation commission (which will consider individual applications for compensation by the Russian Federation for losses from citizens, companies and the state); 3) compensation fund (which will accumulate funds to pay commission decisions, including at the expense of confiscated Russian assets). The mechanism of compensation for environmental damage caused as a result of the armed aggression of the Russian Federation against Ukraine is analyzed, and ways of its optimization are proposed. The future compensation mechanism should be based on the «ecosystem services approach», which will significantly increase the amount of environmental damage that the Russian Federation will pay to Ukraine. The international practice of compensation for environmental damage caused by the aggressor as a result of military actions and temporary occupation was studied and analyzed. The author emphasized the need to reform the state environmental monitoring system. Without reliable monitoring data, it is difficult to prove a causal relationship between the illegal actions of the aggressor state and the damage caused to the environment.

Sensitivity analysis of a Martian atmospheric column model with data from the Mars Science Laboratory

Abstract. An extensive sensitivity analysis was performed for a horizontally homogeneous and hydrostatic 1-D column model at the Mars Science Laboratory (MSL) location. Model experiments were compared with observations from the Curiosity Rover Environmental Monitoring Station humidity (REMS-H) device and ChemCam. Based on our earlier column model investigations, model surface temperature and pressure, dust optical depth (τ), and column precipitable water content (PWC) were the parameters that we investigated with our sensitivity analysis. Our analysis suggests that the most sensitive parameters for the column model temperature profile are τ and surface temperature. The initial value of PWC does not affect the temperature profile of the model, but it is the most important parameter for the humidity profile. The fixed value of τ also seems to have some effect on the humidity profile of the model. Based on our analysis, variations in surface pressure initialization are negligible for the model's temperature and almost negligible for the model's humidity predictions. The model simulations are generally in good agreement with the observations. Our additional model experiments with a different shape of the model's initial humidity profile yielded better results compared to the well-mixed assumption in the predicted water vapor volume mixing ratios at 1.6 m.

Long-term effects of air quality on hospital readmission for heart failure in patients with acute myocardial infarction

BackgroundCardiovascular disease (CVD) is the leading cause of death worldwide, with air pollution posing significant risks to cardiovascular health. The effect of air quality on heart failure (HF) readmission in acute myocardial infarction (AMI) patients is unclear.The aim of this study was to evaluate the role of a single measure of air pollution exposure collected on the day of first hospitalization. MethodsWe retrospectively analyzed data from 12,857 acute coronary syndrome (ACS) patients (January 2015–March 2023). After multiple screenings, 4023 AMI patients were included. The air pollution data is updated by the automatic monitoring data of the national urban air quality monitoring stations in real time and synchronized to the China Environmental Monitoring Station. Cox proportional hazards regression assessed the impact of air quality indicators on admission and outcomes in 4013 AMI patients. A decision tree model identified the most susceptible groups. ResultsAfter adjusting for confounders, NO2 (HR 1.009, 95% CI 1.004–1.015, P = 0.00066) and PM10 (HR 1.006, 95% CI 1.002–1.011, P = 0.00751) increased the risk of HF readmission in ST-segment elevation myocardial infarction (STEMI) patients. No significant effect was observed in non-STEMI (NSTEMI) patients (P > 0.05). STEMI patients had a 2.8-fold higher risk of HF readmission with NO2 > 13 μg/m3 (HR 2.857, 95% CI 1.439–5.670, P = 0.00269) and a 1.65-fold higher risk with PM10 > 55 μg/m3 (HR 1.654, 95% CI 1.124–2.434, P = 0.01064). ConclusionNO2 and PM10 are linked to increased HF readmission risk in STEMI patients, particularly when NO2 exceeds 13 μg/m3 and PM10 exceeds 55 μg/m3. Younger, less symptomatic male STEMI patients with fewer underlying conditions are more vulnerable to these pollutants.

Prawne podstawy ochrony przed hałasem drogowym (ze szczególnym uwzględnieniem przygotowania i realizacji inwestycji drogowej oraz etapu eksploatacji dróg)

The article discusses the regulations under which information on the state of the environment is collected, which can be used at the stage of planning, designing, constructing and operating roads (state environmental monitoring, programmes of environment protection against noise, strategic noise maps). It also addresses the issue of protection against road traffic noise at the stage of road design, construction and alteration, as well as at the stage of road operation. It also identifies environmental protection authorities that play an important role in the context of supervising compliance with noise protection regulations, and briefly discusses the legal remedies available to people exposed to excessive road traffic noise.

Application of Random Forest in a Predictive Model of PM10 Particles in Mexico City

Over time, predictive models tend to become more accurate but also more complex, thus achieving better predictive accuracy. When the data is improved by increasing its quantity and availability, the models are also better, which implies that the data must be processed to filter and adapt it for initial analysis and then modeling. This work aims to apply the Random Forest model to predict PM10 particles. For this purpose, data were obtained from environmental monitoring stations in Mexico City, which operates 29 stations of which 12 belong to the State of Mexico. The pollutants analyzed were CO carbon monoxide, NO nitrogen oxide, and PM10 particulate matter equal to or less than 10 μg.m-3, NOx nitrogen oxide, NO2 nitrogen dioxide, SO2 sulfur dioxide, O3 ozone, and PM2.5 particulate matter equal to or less than 2.5 μg.m-3. The result was that when calculating the certainty of our model, we have a value of 80.40% when calculating the deviation from the mean, using 15 reference variables.

A six-year measurement-based analysis of traffic-related particulate matter pollution in urban areas: the case of Warsaw, Poland (2016-2021)

This study used PM10 and PM2.5 measurements from the State Environmental Monitoring stations in Warsaw and its suburban areas. Analysis of variability characteristics at the traffic and urban background stations was carried out for 2016-2021. A six-year analysis (2016-2021) of air quality in Warsaw, Poland, focusing highlights the persistent impact of transportation on particulate matter concentrations. Comparing a city centre traffic station with urban background locations reveals consistently higher PM10 concentrations at the traffic station throughout the year, with an annual traffic-related increase of 12.6 μg/m³ (32%). PM2.5 concentrations at the traffic station are also consistently about 1.5 μg/m³ (7%) higher. For monthly averages, the highest PM10 concentrations at the traffic station were noted in March, which may be related to the resuspention of sand and salt left over from winter snow removalp rocesses. In the case of PM2.5, the typical annual cycle with maximum concentrations in winter and minimum concentrations in summer was not observed. Diurnal variability patterns show elevated PM10 concentrations at the traffic station from 8:00 a.m. to 10:00 p.m., attributed to the resuspension process. PM2.5 patterns exhibit a smaller amplitude at the traffic station, with nighttime accumulation due to inflow. This study emphasizes the lasting impact of transportation on air quality, providing insights into pollution control strategies in urban areas.

High-Precision Photoacoustic Nitrogen Dioxide Gas Analyzer for Fast Dynamic Measurement.

A high-precision photoacoustic (PA) gas analyzer for fast dynamic measurement of ambient nitrogen dioxide (NO2) was developed. The PA analyzer used a differential PA cell combined with two mufflers to achieve rapid gas flow gas detection. A high-power laser diode (LD) with a center wavelength of 450 nm was used as the PA signal excitation source. To reduce the saturated absorption effect of NO2, ambient air was pumped into the analyzer at a flow rate of 900 sccm. Two mufflers were combined with the differential PA cell to reduce the noise caused by the airflow and pump. The parameters of the mufflers were optimized by using a finite element method. The experimental results showed that the gas flow noise was suppressed by 95%. The response time of the PAS analyzer was 34 s. The detection limits of the analyzer were 0.64 and 0.17 ppb when the integration times were 1 and 15 s, respectively. A 120 h continuous monitoring result was compared with the data from the National Environmental Monitoring Station to demonstrate the high reliability of the analyzer.

The nearshore aquatic environment of eastern Lake Erie: A thirty-year perspective from a monitoring station

Abstract Dreissenid mussels arrived at the Waverly Shoal located above the inflow of the Niagara River in 1989, initiating marked changes in the water and sediment chemistry, and benthic invertebrate community composition at an Ontario Ministry of the Environment, Conservation and Parks monitoring station. Here we examine change in the nearshore of eastern Lake Erie until 2019, inferred from monitoring at this station. Dreissenid numbers peaked in 1991, exceeding 200,000 individual m-2, and remained above 20,000 individual m-2 until 2004 after which numbers progressively declined. In 1993, the population transitioned from mixed Dreissena polymorpha and D. bugensis, to D. bugensis in subsequent years. The decrease in particle size and increase in organic content of surficial sediment which began the year after mussel arrival has persisted until present time. The low concentrations of trace metals and PAHs at the station increased slightly after the physical alteration in bed sediments and has either not changed or declined. After an initial increase in Secchi depth, water clarity changed little over post invasion years, with prevailing moderate water clarity interspersed with periods of bed resuspension and high turbidity. Calcium concentration in the water column, which fell dramatically after the arrival of dreissenids, has gradually increased in recent years. Chlorophyll a and total phosphorus levels indicating oligo-mesotrophic conditions have not varied systematically over the years, other than a modest decline in chlorophyll a after dreissenid arrival. Benthic invertebrate assemblages have gone through multiple alterations, with shifting abundance of amphipods, oligochaetes, chironomids, gastropods and sphaeriids attributed to invasive species rather than the physical environment. Collectively, the data suggests the nearshore ecosystem has shifted in benthic productivity and trophic transfers mediated by the benthos and invasive species, with water and sediment quality appearing to not vary beyond the range driven by inherently fluctuating physical conditions.

ІНВЕНТАРИЗАЦІЯ ЛІСІВ: ОБЛІКОВО-ПРАКТИЧНИЙ АСПЕКТ

The article examines the process of forest inventory in Ukraine as a key element to ensure effective management of forest resources. The inventory is a system of regular sample surveys that allows you to obtain statistically based information on quantitative and qualitative indicators of the state and dynamics of forests, their resource potential, as well as for the needs of state management, strategic planning, environmental monitoring and international reporting. In Ukraine, experimental production work on the preparation and implementation of the national forest inventory began in 2006. The National Forest Inventory Center of the "Ukrderzhlisproekt" VO was identified as the responsible organization, and state budget funding was provided for the national forest inventory, which was to be implemented over a 5-year cycle and to develop technical documentation regulating the technological aspects of the national forest inventory work. It was established that the inventory procedures involve a reconnaissance survey of crops, an assessment of their condition, the transfer of forest crops to forested land and the preparation of primary documents. The technical documentation compiled by forestry enterprises and their subordinate forestry companies mainly contains natural and qualitative indicators. An important component is data quality control, which includes three stages: data entry control, data collection control, and reliability control. The results of the inventory are used to evaluate the effectiveness of forest protection and regeneration measures, as well as to monitor negative impacts. The importance of integrating the components of the national inventory and forest monitoring, improving the inventory methodology to optimize the use of forest territories and the development of protective afforestation is determined. The conclusions of the article confirm that the forest inventory is the basis for the development of effective plans for forest use, protection and restoration of forests, providing accurate information for sound management of forest resources.

A densely connected causal convolutional network separating past and future data for filling missing PM2.5 time series data

Air pollution poses a significant threat to human health and the environment globally. Precise analysis and prediction of pollutant concentrations are essential for monitoring and managing air quality. However, reliable analysis and prediction require comprehensive and high-quality data, which is often compromised due to missing data during collection. Unfortunately, conventional methods for addressing missing data fall short of providing adequate solutions. The missing data for air quality indicators are commonly systematic, with all data points missing for extended periods. This makes it difficult to establish correlations and populate the missing data accurately. To address this problem, we propose a Densely Connected Causal Convolutional Network Separating Past and Future Data (DCCN-SPF), a deep learning-based model that fills in continuous missing PM2.5 concentration data in the original dataset. It extracts features from past and future data separately using densely connected causal convolutional networks and incorporates linear interpolation and deep learning structures to improve prediction accuracy. Using air quality monitoring data from the China Environmental Monitoring Station between 2017 and 2021 in Beijing, we compare our proposed model with baseline models and find that our model outperforms others in predicting PM2.5 concentrations. The evaluation metrics MAE and RMSE are used, revealing significant reductions of 8.7–21.6 % for MAE and 7.1–23.5 % for RMSE in favor of our proposed DCCN-SPF model.

Ecological monitoring technologies for rational nature use

The article identifies the problems of environmental monitoring at enterprises of the Russian Federation and the level of severity of environmental problems in the regions of Russia. The main objects of environmental monitoring in accordance with the legislation and regulatory legal acts of Russia are presented. The characteristics and functions of the Russian Unified State Environmental Monitoring System are presented. The necessity of monitoring the level of environmental pollution using specially designed automated information systems has been determined. The possibilities and advantages of environmental control and monitoring systems used in the territory of the Russian Federation are revealed. The necessity of implementing the multilevel principle through the information system developed in the Russian Federation – "Ecology. 1C-KSU: Environmental Protection".

On the formation and development of the State environmental monitoring system (State environmental monitoring)

The article talks about scientific and methodological issues of the development of state environmental monitoring. The authors have considered the structure of State environmental monitoring (State environmental monitoring) and the procedure for its implementation. The legal basis of state environmental monitoring systems.
 We present the work within the Framework of the national program of the unified system of state environmental monitoring (State environmental monitoring, SEM). The goals, objectives and procedure for the implementation of the SEM, its main subsystems.
 The scientists examined the role of the Ministry of Natural Resources and Ecology of the Russian Federation (Ministry of Natural Resources of Russia) and the Federal Service for Hydrometeorology and Environmental Monitoring (Roshydromet) in ensuring the functioning of state environmental monitoring and its information resources. The activities of the State Environmental Monitoring Data Fund (State environmental monitoring) and the Unified State Data Fund (USDF) are presented. The researchers have the work of the monitoring system using the state system of observations and control by Roshydromet of indicators of the content of pollutants in atmospheric air, surface waters, marine waters, soil, radiation monitoring, etc.
 The authors have considered the prospects for the development of state environmental monitoring in connection with the adoption by the Government of the Russian Federation of the State program "Environmental Protection" for 2012–2030.
 Ethics. This study did not require the conclusion of the Ethics Committee.

Spatial and temporal urban air pollution patterns based on limited data of monitoring stations

Urban air pollution is one of the serious environmental problems in the development of high-density cities, especially for traffic-related pollution. Effective urban environmental monitoring technologies are helpful to predict and control the air pollution emitted by traffic sectors. However, the complex temporal and spatial characteristics of air pollution in urban areas pose a great challenge for its monitoring, prediction, and control. This work investigated on the spatiotemporal air pollution patterns and its correlation mechanism with urban elements (such as traffic) based on limited data of monitoring stations, which is significant for the accurate prediction and regulation of urban environment. Regional Cluster Monitoring (RCM) methods were proposed through integrating multi-source data, including data from U.S. Geological Survey (USGS) Landsat, OpenStreetMap (OSM) road network, and environmental monitoring stations to categorize different monitoring stations. According to different urban areas (defined as U: ‘urban’ or S: ‘suburban’) and traffic densities (T: ‘traffic’ or B: ‘background’), monitoring stations areas were categorized into U-B, U-T, S-B, and S-T. Then the spatiotemporal characteristics of traffic-related pollutants in different region categories were analyzed. The rapid prediction of air pollution distribution in different categories of urban regions was realized by RCM method-based Long Short-Term Memory (LSTM) neural network. Results showed that the proposed methods could accurately represent the spatiotemporal distribution characteristics of urban air pollution. The mean absolute percentage errors (MAPE) between the predicted results and actual observed values were 20.31% to 28.05% (absolute errors were 3.9-14.3 μg/m³). This work can significantly impact on low-cost & effective monitoring and control strategies for urban area, and further contribute to comprehend the spatial-temporal distribution patterns of urban traffic-related air pollution from limited data of monitoring stations.