Particulate Matter Prediction Research Articles

Prediction of particulate matter during the combustion of wood pellets with the addition of face mask waste

The amount of plastic waste has increased enormously due to the using of protective equipment in order to slow down the viral transmission of COVID-19. The usage of protective face masks brought a huge environmental burden. Moreover, a lot of disposed masks enter the ocean or end on landfills, where they threaten the ecosystem. It is still necessary to deal with environmental-friendly disposal or to reuse and recycle of these masks. This article is focused on the disposal of FFP2 face masks by their co-combustion with wood. Due to the possibility of produced emissions, disintegrated masks were blended with spruce and beech sawdust and compared with pure wood. These materials were compressed into pellets with the aim of higher density. The emissions such as carbon monoxide, nitrogen oxides, sulphur oxides and particulate matter were measured during pellet combustion. The heat output of the automatic pellet boiler was also determined. The filters with captured particulate matter were sent to the investigation of dioxin and furan concentration. Except for this, the regression model has been created for the prediction the concentration of particulate matter. The results confirmed that the co-combustion of wood with FFP2 masks could be one of the environmental-friendly ways of face mask disposal when they are used as an additive in a small percentage. The fuel composition and operational conditions are also very important parameters during the combustion process. However, the concentration of gas emissions and particulate matter, as well as heat output, did not change significantly, when the content of FFP2 masks of 5 % or 10 % was used.

Building reliable AI for quantifying uncertainty in particulate matter predictions with deep learning

Predicting the concentrations of particulate matter (PM) has recently become crucial because of its significant impact on air pollution. As the adoption of artificial intelligence (AI) in this domain increases, ensuring the reliability of AI-driven predictions has become paramount. Although many previous studies have harnessed the power of AI for PM prediction, the inherent uncertainty in the results, which is influenced by spatial data imbalances and varying meteorological factors, poses a challenge. Addressing this uncertainty is central to building reliable AI systems. Therefore, we employed the Monte Carlo dropout (MCDO) approach, which is a technique that integrates dropout layers in neural networks during both the training and inference phases, to estimate the prediction uncertainty. Our objective was to address the challenge of prediction uncertainty in PM concentrations, with the ultimate aim of enhancing the reliability and trustworthiness of AI-driven predictions in air quality forecasting. By applying the MCDO approach to grids formed from multidimensional arrays of air quality and weather data, we obtained a 95% confidence interval for the prediction results, thereby demonstrating the trustworthiness of our model. Our evaluation revealed an R-square greater than 0.97 for PM10 and PM2.5, showcasing the robust and reliable predictive performance of the model. This study highlights not only the accuracy of this approach but also the critical role of quantifying uncertainty in building reliable AI systems. Our findings mark a significant step towards a holistic approach to predictive modeling in which reliability and uncertainty quantification are at the forefront.

Parsimonious Random-Forest-Based Land-Use Regression Model Using Particulate Matter Sensors in Berlin, Germany.

Machine learning (ML) methods are widely used in particulate matter prediction modelling, especially through use of air quality sensor data. Despite their advantages, these methods' black-box nature obscures the understanding of how a prediction has been made. Major issues with these types of models include the data quality and computational intensity. In this study, we employed feature selection methods using recursive feature elimination and global sensitivity analysis for a random-forest (RF)-based land-use regression model developed for the city of Berlin, Germany. Land-use-based predictors, including local climate zones, leaf area index, daily traffic volume, population density, building types, building heights, and street types were used to create a baseline RF model. Five additional models, three using recursive feature elimination method and two using a Sobol-based global sensitivity analysis (GSA), were implemented, and their performance was compared against that of the baseline RF model. The predictors that had a large effect on the prediction as determined using both the methods are discussed. Through feature elimination, the number of predictors were reduced from 220 in the baseline model to eight in the parsimonious models without sacrificing model performance. The model metrics were compared, which showed that the parsimonious_GSA-based model performs better than does the baseline model and reduces the mean absolute error (MAE) from 8.69 µg/m3 to 3.6 µg/m3 and the root mean squared error (RMSE) from 9.86 µg/m3 to 4.23 µg/m3 when applying the trained model to reference station data. The better performance of the GSA_parsimonious model is made possible by the curtailment of the uncertainties propagated through the model via the reduction of multicollinear and redundant predictors. The parsimonious model validated against reference stations was able to predict the PM2.5 concentrations with an MAE of less than 5 µg/m3 for 10 out of 12 locations. The GSA_parsimonious performed best in all model metrics and improved the R2 from 3% in the baseline model to 17%. However, the predictions exhibited a degree of uncertainty, making it unreliable for regional scale modelling. The GSA_parsimonious model can nevertheless be adapted to local scales to highlight the land-use parameters that are indicative of PM2.5 concentrations in Berlin. Overall, population density, leaf area index, and traffic volume are the major predictors of PM2.5, while building type and local climate zones are the less significant predictors. Feature selection based on sensitivity analysis has a large impact on the model performance. Optimising models through sensitivity analysis can enhance the interpretability of the model dynamics and potentially reduce computational costs and time when modelling is performed for larger areas.

Machine learning models application for spatiotemporal patterns of particulate matter prediction and forecasting over Morocco in north of Africa

Atmospheric air pollution exposure raises morbidity and mortality rates and is a major cause of the world's illness burden. In this context, we explored spatial and temporal trends in particulate matter PM10 from 2003 to 2020 over Morocco to assess air pollution exposure. We use the capabilities of ML models to study PM10 trends using 26 predictor variables, including meteorological parameters, volatile organic compounds, atmospheric oxidants, and aerosol optical depth data from the Copernicus Atmosphere Monitoring Service (CAMS). For this purpose, three ML models were built: Multiple Linear Regression (MLR), Random Forest Regression (RFR), and Generalized Additive Model (GAM). To match and optimize these models, a set of ML algorithms has been coupled with each model. The results show all these models are highly accurate in predicting and forecasting PM10 total column trends. Cross-validation showed that GAM had better prediction ability for the PM10 total column with R2 = 0.994 and a very low root mean squared error (RMSE) not exceeding 0.046 × 10−16 kg/m2. The GAM model showed much higher predictive ability and lower bias than the other models. This finding can be explained by the advantages of GAMs, including their ability to capture complex and non-linear patterns in the data, making them particularly useful when relationships are not easily represented by linear models. This study has presented a comprehensive methodology for predicting the spatiotemporal variability of PM10. The proposed methodology holds potential applicability across all regions, facilitating the generation of high-resolution PM10 monitoring and the establishment of systems for the early detection of air pollution incidents in Morocco. Furthermore, the developed models exhibit versatility, enabling their application for estimating future trends of individual pollutants or making real-time predictions of air quality levels. This research contributes to advancing the understanding and proactive management of air quality in the context of Morocco, offering valuable insights for pollution control efforts.

Outdoor air pollution and risk of incident adult haematologic cancer subtypes in a large US prospective cohort

BackgroundOutdoor air pollution and particulate matter (PM) are classified as Group 1 human carcinogens for lung cancer. Pollutant associations with haematologic cancers are suggestive, but these cancers are aetiologically heterogeneous and sub-type examinations are lacking.MethodsThe American Cancer Society Cancer Prevention Study-II Nutrition Cohort was used to examine associations of outdoor air pollutants with adult haematologic cancers. Census block group level annual predictions of particulate matter (PM2.5, PM10, PM10-2.5), nitrogen dioxide (NO2), ozone (O3), sulfur dioxide (SO2), and carbon monoxide (CO) were assigned with residential addresses. Hazard ratios (HR) and 95% confidence intervals (CI) between time-varying pollutants and haematologic subtypes were estimated.ResultsAmong 108,002 participants, 2659 incident haematologic cancers were identified from 1992–2017. Higher PM10-2.5 concentrations were associated with mantle cell lymphoma (HR per 4.1 μg/m3 = 1.43, 95% CI 1.08–1.90). NO2 was associated with Hodgkin lymphoma (HR per 7.2 ppb = 1.39; 95% CI 1.01–1.92) and marginal zone lymphoma (HR per 7.2 ppb = 1.30; 95% CI 1.01–1.67). CO was associated with marginal zone (HR per 0.21 ppm = 1.30; 95% CI 1.04–1.62) and T-cell (HR per 0.21 ppm = 1.27; 95% CI 1.00–1.61) lymphomas.ConclusionsThe role of air pollutants on haematologic cancers may have been underestimated previously because of sub-type heterogeneity.

Particulate matter concentrations around natural gas-fired power plants and their associated health impact assessment

The quantification and prediction of particulate matter (PM) concentrations in the air are essential due to their negative impacts on human health and the environment. This study quantified PM concentrations and associated health effects at four natural gas-based power plants in Bangladesh. The measurement of PM2.5 and PM10 using the respirable dust samplers APS-113NL and APS-113BL, respectively from the year of 2015 to 2021 revealed that the concentration of both types of particles fluctuated over the years. The highest recorded levels of particles were in 2019, with PM2.5 at 126 µg/m3 and PM10 at 283 µg/m3 and the lowest recorded levels of particles were in 2017, with PM2.5 at 76.3 µg/m3 and PM10 at 203.3 µg/m3. In 2021, PM2.5 and PM10 concentrations were 88.5 and 225 µg/m3, respectively, lower than in the past two years. Statistical modeling assessed atmospheric contaminants analyzed time series data, and projected air quality. ARIMA, ETS, and ANN modeling methods have been used to predict the monthly average of PM2.5 and PM10 concentrations. RMSE, MAPE, MASE, and MAE have been utilized for model orders, time series analysis, and forecasting validation. There is a significant variation between the forecasting models and forecasts for average PM2.5 and PM10 concentrations in natural gas-fired power plants from 2022 to 2024. This study also conducted a face-to-face interview with over 100 employees using a structured questionnaire to assess the health effects they are facing due to poor air quality in the power generation complex and found that 2 and 13 % of employees had respiratory and skin issues, respectively. Nonetheless, regular health checks, air filtration, and renewable energy consumption may benefit residents and the environment.

Integrating land use and traffic to spatial prediction of particulate matter

With degrading air quality and inefficient monitoring systems, spatial prediction of pollutants has become necessary. Air pollution exposure causes significant impacts on human health in urban areas around the world. The current study focuses on developing a deep learning model for spatial prediction of particulate matter at locations where the monitored data is unavailable. Delhi, India, is selected as the study area due to its high air pollution and fewer fixed monitoring stations throughout the city. The parameters used for the prediction modeling included PM2.5 from fixed monitoring stations, PM2.5 from mobile sensors, meteorological parameters (atmospheric temperature and relative humidity), traffic flow data, and land use parameters. The data is taken for six months, from November 2022 to April 2023, at an interval of 15 min. Four buffer sizes are used to find the spatial variability. The ANN model is used for the spatial predictions using the above-mentioned parameters. K-fold cross-validation is used to validate the robustness of the model. The SHAP summary plot is used to identify the feature importance of the features used in the model. It is observed that the integration of the land use data and traffic data increases the prediction capability of the model.

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery.

In this study, we propose a novel long short-term memory (LSTM) neural network model that leverages color features (HSV: hue, saturation, value) extracted from street images to estimate air quality with particulate matter (PM) in four typical European environments: urban, suburban, villages, and the harbor. To evaluate its performance, we utilize concentration data for eight parameters of ambient PM (PM1.0, PM2.5, and PM10, particle number concentration, lung-deposited surface area, equivalent mass concentrations of ultraviolet PM, black carbon, and brown carbon) collected from a mobile monitoring platform during the nonheating season in downtown Augsburg, Germany, along with synchronized street view images. Experimental comparisons were conducted between the LSTM model and other deep learning models (recurrent neural network and gated recurrent unit). The results clearly demonstrate a better performance of the LSTM model compared with other statistically based models. The LSTM-HSV model achieved impressive interpretability rates above 80%, for the eight PM metrics mentioned above, indicating the expected performance of the proposed model. Moreover, the successful application of the LSTM-HSV model in other seasons of Augsburg city and various environments (suburbs, villages, and harbor cities) demonstrates its satisfactory generalization capabilities in both temporal and spatial dimensions. The successful application of the LSTM-HSV model underscores its potential as a versatile tool for the estimation of air pollution after presampling of the studied area, with broad implications for urban planning and public health initiatives.

A novel four-stage hybrid intelligent model for particulate matter prediction

A novel four-stage hybrid intelligent model for particulate matter prediction

Predictions of air quality and challenges for eliminating air pollution during the 2022 Olympic Winter Games

Scientifically and efficiently ensuring good air quality for important events is an issue of concern to the government. In addition to analysis based on historical data, advanced prediction before an event is essential for the government having ample time to take effective actions to improve air quality during the event period. Taking “the 2022 Olympic Winter Games (OWG)” as a typical case, a chemical transport model coupled with a tracer-tagged module was used to evaluate the air quality and source apportionment of ambient pollutants in the OWG host cities under historical and predicted meteorological conditions. Driven by the downscaling of meteorological fields from an operational real-time climate forecast system, the potential ability of air quality forecasting three months ahead was investigated, which was meaningful for designing control strategies. Sensitive simulations indicated that under unfavorable meteorological conditions, such as those during February 2014, both Beijing and Zhangjiakou faced a high risk of experiencing haze episodes, even based on current anthropogenic emission intensity. The contribution of the joint prevention and control region to Beijing and Zhangjiakou would become larger under worse meteorological conditions, which favor heavy air pollution. The source apportionment results indicated that strengthened emission control in cities including Beijing, Zhangjiakou and south of Beijing (Baoding, Langfang, Tianjin, and Tangshan) is effective for reducing haze episodes in the host cities. There is still a long way to make accurate daily fine particulate matter predictions on a seasonal-scale in advance; however, it could capture the trends in air quality in host cities around the OWG period three months ahead. The comparison of observations and predictions confirmed and highlighted the role of regional emission controls on the realization of the “OWG blue”.

Forecasting PM10 levels in Sri Lanka: A comparative analysis of machine learning models PM10

Forecasting of particulate matter (PM10) which adversely impacts air quality is highly important in ever-urbanizing cities. The relationship between particulate matter and other air quality parameters and climatic parameters is frequently investigated due to their nonlinearity. Machine learning models have been extensively used in these nonlinear predictions and showcased their ability and robustness. However, among the tested machine learning models, a comparative analysis is essential in the localized context to understand the best model that can be used to forecast future scenarios. Therefore, this research investigates the applicability of eight state-of-the-art machine learning models (ANN, Bi-LSTM, Ensemble, XGBoost, CatBoost, LightGBM, LSTM, and GRU) in the prediction of particulate matter in two urbanized areas (Battaramulla and Kandy) Sri Lanka. Regression coefficient, Root Mean Squared Error, Mean Squared Error, Mean Absolute Error, Mean Absolute Relative Error, and Nash-Sutcliffe Efficiency were incorporated to assess the best-suited model for both cities. Results revealed that the Ensemble model has the capability of accurate and precise prediction of PM10 for both cities outperforming all other models (R2≈1). Therefore, the Ensemble model is recommended for future investigation of PM10 for Sri Lanka which has a growing concern due to high air pollution levels.

Improved prediction of hourly PM2.5 concentrations with a long short-term memory and spatio-temporal causal convolutional network deep learning model

Accurate prediction of particulate matter with aerodynamic diameter ≤ 2.5 μm (PM2.5) is important for environmental management and human health protection. In recent years, many efforts have been devoted to develop air quality predictions using the machine learning and deep learning techniques. In this study, we propose a deep learning model for short-term PM2.5 predictions. The salient feature of the proposed model is that the convolution in the model architecture is causal, where the output of a time step is only convolved with components of the same or earlier time step from the previous layer. The model also weighs the spatial correlation between multiple monitoring stations. Through temporal and spatial correlation analysis, relevant information is screened from the monitoring stations with a strong relationship with the target station. Information from the target and related sites is then taken as input and fed into the model. A case study is conducted in Nanjing, China from January 1, 2020 to December 31, 2020. Using historical air quality and meteorological data from nine monitoring stations, the model predicts PM2.5 concentrations for the next hour. The experimental results show that the predicted PM2.5 concentrations are consistent with observation, with correlation coefficient (R2) and Root Mean Squared Error (RMSE) of our model are 0.92 and 6.75 μg/m3. Additionally, to better understand the factors affecting PM2.5 levels in different seasons, a machine learning algorithm based on Principal Component Analysis (PCA) is used to analyze the correlations between PM2.5 and its influencing factors. By identifying the main factors affecting PM2.5 and optimizing the input of the predictive model, the application of PCA in the model further improves the prediction accuracy, with decrease of up to 17.2 % in RMSE and 38.6 % in mean absolute error (MAE). The deep learning model established in this study provide a valuable tool for air quality management and public health protection.

EvalPM: a framework for evaluating machine learning models for particulate matter prediction

Air pollution through particulate matter (PM) is one of the largest threats to human health. To understand the causes of PM pollution and enact suitable countermeasures, reliable predictions of future PM concentrations are required. In the scientific literature, many methods exist for machine learning (ML)-based PM prediction, though their quality is difficult to compare because, among other things, they use different data sets and evaluate the resulting predictions differently. For a new data set, it is not apparent which of the existing prediction methods is best suited. In order to ease the assessment of said models, we present evalPM, a framework to easily create, evaluate, and compare different ML models for immission-based PM prediction. To achieve this, the framework provides flexibility regarding data sets, input features, target variables, model types, hyperparameters, and model evaluation. It has a modular design consisting of several components, each providing at least one required flexibility. The individual capabilities of the framework are demonstrated using 16 different models from the related literature by means of temporal prediction of PM concentrations for four European data sets, showing the capabilities and advantages of the evalPM framework. In doing so, it is shown that the framework allows fast creation and evaluation of ML-based PM prediction models.

Optimization of neural network parameters in improvement of particulate matter concentration prediction of open-pit mining

The prediction of particulate matter (PM) concentration around open-pit mining is crucial for its control. To achieve this, machine learning (ML) techniques have been attempted in PM estimation without reaching their full potential. In the current study, an artificial neural network (ANN) is employed for the prediction of PM2.5 concentration (PM < 2.5 μm), PM10 concentration (PM < 10 μm), and total suspended particulate (TSP). The influence of training algorithms and epochs on the modeling accuracy of ANN is investigated. Moreover, the convergence of ANN modeling is studied using Monte Carlo simulations. Compared with the quasi-Newton method (QNM) and conjugate gradient backpropagation (CGB), the one-step secant algorithm (OSSM) is the most suitable training algorithm for PM concentration prediction. Using the 0.1% bound as a convergence criterion, 500 Monte Carlo simulations are enough to get the converged results. The ANN-OSSM achieves high accuracy in PM concentration prediction. The R values on the testing set of PM2.5, PM10, and TSP are 0.887, 0.943, 0.886, respectively. Compared with the results in the literature, accuracy improvement is achieved using ANN-OSSM, with R increases from 0.86 to 0.92 (TSP dataset), from 0.91 to 0.94 (PM2.5 dataset), and from 0.84 to 0.89 (PM10 dataset). The present ML model is higher in accuracy and more straightforward in methodology compared with the hybridized model in the literature, which will promote its industrial application in the near future.

A novel approach for the prediction and analysis of daily concentrations of particulate matter using machine learning

Traditional air quality analysis and prediction methods depend on the statistical and numerical analyses of historical air quality data with more information related to a specific region; therefore, the results are unsatisfactory. In particular, fine particulate matter (PM2.5, PM10) in the atmosphere is a major concern for human health. The modelling (analysis and prediction) of particulate matter concentrations remains unsatisfactory owing to the rapid increase in urbanization and industrialization. In the present study, we reconstructed a prediction model for both PM2.5 and PM10 with varying meteorological conditions (windspeed, temperature, precipitation, specific humidity, and air pressure) in a specific region. In this study, a prediction model was developed for the two observation stations in the study region. The analysis of particulate matter shows that seasonal variation is a primary factor that highly influences air pollutant concentrations in urban regions. Based on historical data, the maximum number of days (92 days in 2019) during the winter season exceeded the maximum permissible level of particulate matter (PM2.5 = 15 μg/m3) concentration in air. The prediction results showed better performance of the Gaussian process regression model, with comparatively larger R2 values and smaller errors than the other models. Based on the analysis and prediction, these novel methods may enhance the accuracy of particulate matter prediction and influence policy- and decision-makers among pollution control authorities to protect air quality.

LASSO and attention-TCN: a concurrent method for indoor particulate matter prediction.

Long time exposure to indoor air pollution environments can increase the risk of cardiovascular and respiratory system damage. Most previous studies focus on outdoor air quality, while few studies on indoor air quality. Current neural network-based methods for indoor air quality prediction ignore the optimization of input variables, process input features serially, and still suffer from loss of information during model training, which may lead to the problems of memory-intensive, time-consuming and low-precision. We present a novel concurrent indoor PM prediction model based on the fusion model of Least Absolute Shrinkage and Selection Operator (LASSO) and an Attention Temporal Convolutional Network (ATCN), together called LATCN. First, a LASSO regression algorithm is used to select features from PM1, PM2.5, PM10 and PM (>10) datasets and environmental factors to optimize the inputs for indoor PM prediction model. Then an Attention Mechanism (AM) is applied to reduce the redundant temporal information to extract key features in inputs. Finally, a TCN is used to forecast indoor particulate concentration in parallel with inputting the extracted features, and it reduces information loss by residual connections. The results show that the main environmental factors affecting indoor PM concentration are the indoor heat index, indoor wind chill, wet bulb temperature and relative humidity. Comparing with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) approaches, LATCN systematically reduced the prediction error rate (19.7% ~ 28.1% for the NAE, and 16.4% ~ 21.5% for the RMSE) and improved the model running speed (30.4% ~ 81.2%) over these classical sequence prediction models. Our study can inform the active prevention of indoor air pollution, and provides a theoretical basis for indoor environmental standards, while laying the foundations for developing novel air pollution prevention equipment in the future.

Nocturnal Boundary Layer Height Uncertainty in Particulate Matter Simulations during the KORUS-AQ Campaign

Vertical mixing in the planetary boundary layer (PBL) is an important factor in the prediction of particulate matter (PM) concentrations; however, PBL height (PBLH) in the stable atmosphere remains poorly understood. In particular, the assessment of uncertainties related to nocturnal PBLH (nPBLH) is challenging due to the absence of stable atmosphere observations. In this study, we explored nPBLH–PM2.5 interactions by comparing model results and observations during the Korea–United States Air Quality Study (KORUS-AQ) campaign (1–31 May 2016). Remote sensing measurements (e.g., aerosol and wind Doppler lidar) and on-line WRF-Chem modeling results were used by applying three different PBL parameterizations: Yonsei University (YSU), Mellor–Yamada–Janjic (MYJ), and Asymmetrical Convective Model v2 (ACM2). Our results indicated that the uncertainties of PBLH–PM interactions were not large in daytime, whereas the uncertainties of nPBLH–PM2.5 interactions were significant. All WRF-Chem experiments showed a clear tendency to underestimate nighttime nPBLH by a factor of ~3 compared with observations, and shallow nPBLH clearly led to extremely high PM2.5 peaks during the night. These uncertainties associated with nPBLH and nPBLH–PM2.5 simulations suggest that PM2.5 peaks predicted from nighttime or next-morning nPBLH simulations should be interpreted with caution. Additionally, we discuss uncertainties among PBL parameterization schemes in relation to PM2.5 simulations.

Particulate Matter Prediction and Shapley Value Interpretation in Korea through a Deep Learning Model

Particulate Matter Prediction and Shapley Value Interpretation in Korea through a Deep Learning Model

Concentration Separation Prediction Model to Enhance Prediction Accuracy of Particulate Matter

Demand for more accurate particulate matter forecasts is accumulating owing to the increased interest and issues regarding particulate matter. Incredibly low concentration particulate matter, which accounts for most of the overall particulate matter, is often underestimated when a particulate matter prediction model based on machine learning is used. This study proposed a concentration-specific separation prediction model to overcome this shortcoming. Three prediction models based on Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), commonly used for performance evaluation of the proposed prediction model, were used as comparative models. Root mean squared error (RMSE), mean absolute percentage error (MAPE), and accuracy were utilized for performance evaluation. The results showed that the prediction accuracy for all Air Quality Index (AQI) segments was more than 80 percent in the entire concentration spectrum. In addition, the study confirmed that the over-prediction phenomenon of single neural network models concentrated in the ‘normal’ AQI region was alleviated.

Monitoring and Prediction of Particulate Matter (PM2.5 and PM10) around the Ipbeja Campus

Nowadays, most of the world’s population lives in urban centres, where air quality levels are not strictly checked; citizens are exposed to air quality levels over the limits of the World Health Organization. The interaction between the issuing and atmospheric sources influences the air quality or level. The local climate conditions (temperature, humidity, winds, rainfall) determine a greater or less dispersion of the pollutants present in the atmosphere. In this sense, this work aimed to build a math modelling prediction to control the air quality around the campus of IPBeja, which is in the vicinity of a car traffic zone. The researchers have been analysing the data from the last months, particle matter (PM10 and PM2.5), and meteorological parameters for prediction using NARX. The results show a considerable increase in particles in occasional periods, reaching average values of 135 μg/m3 for PM10 and 52 μg/m3 for PM2.5. Thus, the monitoring and prediction serve as a warning to perceive these changes and be able to relate them to natural phenomena or issuing sources in specific cases.