Air Quality Class Prediction Using Machine Learning Methods Based on Monitoring Data and Secondary Modeling

Since most of the existing air quality index (AQI) predicting models focused on prediction of the time series data of a single target monitoring station, they failed to consider the correlation and mutual influence among the air quality monitoring station sites and the spatio-temporal characteristics of air quality. And this will lead to a certain one-sidedness during air quality prediction of a particular site. Aimed at this problem, a short-term air quality prediction model based on K-nearest neighbor (KNN) and Long Short-Term Memory (LSTM) was proposed. The model firstly used KNN algorithm to select the time and space-related monitoring stations, then the air quality index sequences of these stations were constructed into data sets, followed by training and testing processes in the LSTM model, and finally the model was verified with real data. It is suggested that the prediction accuracy of the hybrid prediction model constructed in this paper is acceptable in terms of the space-time correlation, and it could be an alternative for further application of air quality prediction.

In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo's derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

With the quick development of society and industry, air quality has become a grim and global environmental concern. Predicting and rating air quality for many cities remains a significant challenge. Consequently, machine learning algorithms have garnered considerable attention for their potential to address these issues effectively. In this paper, firstly, based on daily air quality data from July 1, 2022 to June 30, 2023 in Lanzhou city of China, five machine learning models, including Bayes Model Averaging (BMA), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) are developed to predict the Air Quality Index (AQI) via six major air pollutants (PM2.5, PM10, SO2, NO2, O3 and CO). Secondly, we integrate Bootstrap algorithm into the optimal model, leading to the proposal of the LSTM-Bootstrap algorithm for deriving the standard errors and confidence intervals of the predicted AQI. Thirdly, a cumulative logit model is employed to evaluate and forecast AQI rating. The analysis results indicate that AQI rating is significantly affected by PM10, CO and O3. Additionally, to validate the efficacy of the suggested methods, a similar analysis is conducted on air quality data from Chengdu city for the same period. The findings provide valuable insights for future environmental policies and air quality management strategies.

Clean air is essential for maintaining a healthy lifestyle, yet poor air quality remains a major contributor to numerous respiratory ailments.Air pollutants such as PM2.5, NOx, COx, and SOx significantly impact human health, emphasizing the need for accurate forecasting models.However, predicting air quality is challenging due to the dynamic interplay of various factors, including meteorological conditions, vehicular emissions, and industrial discharges.This study proposes a novel hybrid forecasting model, Hyb_LSTM+KCNN, which combines Long Short-Term Memory (LSTM) networks and Kernel Convolutional Neural Networks (KCNN) for time-series prediction of the Air Quality Index (AQI).The LSTM component captures temporal dependencies in air quality data, enabling effective modeling of sequential patterns over time.Meanwhile, the KCNN module enhances feature extraction by leveraging convolutional kernels to identify local data patterns.By integrating these complementary strengths, the hybrid architecture provides a more robust and accurate AQI forecasting model.The proposed model was evaluated on comprehensive datasets, incorporating various pollutant levels and meteorological parameters.Experimental results demonstrated that the Hyb_LSTM+KCNN model consistently outperforms traditional forecasting techniques, achieving higher prediction accuracy and generalization capabilities.The model effectively captures correlations between pollutants and environmental factors, leading to precise AQI forecasts even under dynamic and complex conditions.This study presents a promising solution for air quality prediction, with practical implications for environmental monitoring and public health management.Future research will explore further optimization of the model for real-time applications and investigate its performance when integrating additional data sources, such as satellite and hyperspectral imagery.

Along with the rapid development of industries and the acceleration of urbanisation, the problem of air pollution is becoming more serious. Exploring the relevant factors affecting air quality and accurately predicting the air quality index are significant in improving the overall environmental quality and realising green economic development. Machine learning algorithms and statistical models have been widely used in air quality prediction and ranking assessment. In this paper, based on daily air quality data for the city of Xi’an, China, from 1 October 2022 to 30 September 2023, we construct support vector regression (SVR), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), random forests (RF), neural network (NN) and long short-term memory (LSTM) models to analyse the influence of the air quality index for Xi’an and to conduct comparative tests. The predicted values and 95% prediction intervals of the AQI for the next 15 days for Xi’an, China, are given based on the Bootstrap-XGBoost algorithm. Further, the ordinal logit regression and ordinal probit regression models are constructed to evaluate and accurately predict the AQI ranks of the data from 1 October 2023 to 15 October 2023 for Xi’an. Finally, this paper proposes some suggestions and policy measures based on the findings of this paper.

Abstract. As air pollution is regarded as the single largest environmental health risk in Europe it is important that communication to the public is up to date and accurate and provides means to avoid exposure to high air pollution levels. Long- and short-term exposure to outdoor air pollution is associated with increased risks of mortality and morbidity. Up-to-date information on present and coming days' air quality helps people avoid exposure during episodes with high levels of air pollution. Air quality forecasts can be based on deterministic dispersion modelling, but to be accurate this requires detailed information on future emissions, meteorological conditions and process-oriented dispersion modelling. In this paper, we apply different machine learning (ML) algorithms – random forest (RF), extreme gradient boosting (XGB), and long short-term memory (LSTM) – to improve 1, 2, and 3 d deterministic forecasts of PM10, NOx, and O3 at different sites in Greater Stockholm, Sweden. It is shown that the deterministic forecasts can be significantly improved using the ML models but that the degree of improvement of the deterministic forecasts depends more on pollutant and site than on what ML algorithm is applied. Also, four feature importance methods, namely the mean decrease in impurity (MDI) method, permutation method, gradient-based method, and Shapley additive explanations (SHAP) method, are utilized to identify significant features that are common and robust across all models and methods for a pollutant. Deterministic forecasts of PM10 are improved by the ML models through the input of lagged measurements and Julian day partly reflecting seasonal variations not properly parameterized in the deterministic forecasts. A systematic discrepancy by the deterministic forecasts in the diurnal cycle of NOx is removed by the ML models considering lagged measurements and calendar data like hour and weekday, reflecting the influence of local traffic emissions. For O3 at the urban background site, the local photochemistry is not properly accounted for by the relatively coarse Copernicus Atmosphere Monitoring Service ensemble model (CAMS) used here for forecasting O3 but is compensated for using the ML models by taking lagged measurements into account. Through multiple repetitions of the training process, the resulting ML models achieved improvements for all sites and pollutants. For NOx at street canyon sites, mean squared error (MSE) decreased by up to 60 %, and seven metrics, such as R2 and mean absolute percentage error (MAPE), exhibited consistent results. The prediction of PM10 is improved significantly at the urban background site, whereas the ML models at street sites have difficulty capturing more information. The prediction accuracy of O3 also modestly increased, with differences between metrics. Further work is needed to reduce deviations between model results and measurements for short periods with relatively high concentrations (peaks) at the street canyon sites. Such peaks can be due to a combination of non-typical emissions and unfavourable meteorological conditions, which are rather difficult to forecast. Furthermore, we show that general models trained using data from selected street sites can improve the deterministic forecasts of NOx at the station not involved in model training. For PM10 this was only possible using more complex LSTM models. An important aspect to consider when choosing ML algorithms is the computational requirements for training the models in the deployment of the system. Tree-based models (RF and XGB) require fewer computational resources and yield comparable performance in comparison to LSTM. Therefore, tree-based models are now implemented operationally in the forecasts of air pollution and health risks in Stockholm. Nevertheless, there is big potential to develop generic models using advanced ML to take into account not only local temporal variation but also spatial variation at different stations.

Urban air quality index forecasting using multivariate convolutional neural network based customized stacked long short-term memory model

With air quality issues becoming ever greater global concerns, many countries are facing numerous air pollution problems. Among all the particulate matter of air pollution, PM2.5 (whose aerodynamic diameter is 2.5 μm or less) is of particular concern. Long-term exposure to high concentrations of PM2.5 can negatively affect human health. The negative effects of PM2.5 make forecast its concentration an urgent need. In this paper, we propose a novel Factory-aware Attentional LSTM Model (FAA-LSTM) for PM2.5 air pollution predictions. The proposed model collects air pollution data from both the monitor stations and micro air quality sensors, in which a spatial transformation is designed to obtain the local area data of PM2.5 grids. Next, a novel factory-aware attention mechanism over a long short-term memory (LSTM) neural network is proposed to extract the hidden features of industrial factors and derive their factory attention weights on the influences of PM2.5 concentrations. The influence of neighboring factory data over local PM2.5 grids can be weighted to discover the importance of PM2.5 concentrations of neighboring areas. Moreover, the model combines these heterogeneous data and the global station data to forecast PM2.5 concentrations. The experiment’s evaluation is conducted using both air pollution data and industrial data. The results show that the factory-aware attention mechanism helps to improve the prediction performance by exploring the effect of the factory distribution on PM2.5 pollutants in the local areas. While monitoring stations have been established to collect air quality information and forecast air quality, few studies have taken the different monitoring areas and industrial features into account. The proposed novel model considering PM2.5 concentrations from local neighboring areas and global station, and industrial data as features can effectively indicate the impact of PM2.5 pollution with industrial emissions and spatial relationships. Our research work can improve the prediction accuracy of PM2.5 and contribute to increasing the practical value for air quality management.

The adverse effect of air pollution has always been a problem for human health. The presence of a high level of air pollutants can cause severe illnesses such as emphysema, chronic obstructive pulmonary disease (COPD), or asthma. Air quality prediction helps us to undertake practical action plans for controlling air pollution. The Air Quality Index (AQI) reflects the degree of concentration of pollutants in a locality. The average AQI was calculated for the various cities in China to understand the annual trends. Furthermore, the air quality index has been predicted for ten major cities across China using five different deep learning techniques, namely, Recurrent Neural Network (RNN), Bidirectional Gated Recurrent unit (Bi-GRU), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network BiLSTM (CNN-BiLSTM), and Convolutional BiLSTM (Conv1D-BiLSTM). The performance of these models has been compared with a machine learning model, eXtreme Gradient Boosting (XGBoost) to discover the most efficient deep learning model. The results suggest that the machine learning model, XGBoost, outperforms the deep learning models. While Conv1D-BiLSTM and CNN-BiLSTM perform well among the deep learning models in the estimation of the air quality index (AQI), RNN and Bi-GRU are the least performing ones. Thus, both XGBoost and neural network models are capable of capturing the non-linearity present in the dataset with reliable accuracy.

Air pollution is one of the most critical environmental challenges affecting public health and economic sustainability. Continuous monitoring and accurate air quality prediction are essential for effective environmental management. This paper presents SmartAQI, an intelligent air quality monitoring and prediction system that integrates environmental data analytics with machine learning techniques. The proposed system utilizes historical air pollution datasets, India district-level geographic information, and real-time meteorological data obtained through the OpenWeather API to analyze air quality conditions across different regions of India. Major pollutants, including PM2.5, PM10, NO₂, SO₂, CO, and O₃, are processed to compute the Air Quality Index (AQI) according to the guidelines established by the Central Pollution Control Board. To improve prediction capability, multiple machine learning models such as Linear Regression, Random Forest, and Time Series forecasting are implemented and evaluated. The system further provides an interactive visualization dashboard that displays live AQI values, pollutant concentration levels, predicted AQI values, and geographic air quality distribution through charts and maps. Results demonstrate that integrating environmental data with machine learning models enables reliable AQI prediction and effective spatial analysis of pollution trends. The SmartAQI framework offers a practical solution for environmental monitoring and can support researchers, policymakers, and the public in understanding and managing air quality conditions more effectively, which is reliable

Due to critical impacts of air pollution, prediction and monitoring of air quality in urban areas are important tasks. However, because of the dynamic nature and high spatio-temporal variability, prediction of the air pollutant concentrations is a complex spatio-temporal problem. Distribution of pollutant concentration is influenced by various factors such as the historical pollution data and weather conditions. Conventional methods such as the support vector machine (SVM) or artificial neural networks (ANN) show some deficiencies when huge amount of streaming data have to be analyzed for urban air pollution prediction. In order to overcome the limitations of the conventional methods and improve the performance of urban air pollution prediction in Tehran, a spatio-temporal system is designed using a LaSVM-based online algorithm. Pollutant concentration and meteorological data along with geographical parameters are continually fed to the developed online forecasting system. Performance of the system is evaluated by comparing the prediction results of the Air Quality Index (AQI) with those of a traditional SVM algorithm. Results show an outstanding increase of speed by the online algorithm while preserving the accuracy of the SVM classifier. Comparison of the hourly predictions for next coming 24 h, with those of the measured pollution data in Tehran pollution monitoring stations shows an overall accuracy of 0.71, root mean square error of 0.54 and coefficient of determination of 0.81. These results are indicators of the practical usefulness of the online algorithm for real-time spatial and temporal prediction of the urban air quality.

In recent times, the air quality level of Dhaka city has been termed as hazardous. The weather of Dhaka city has gone through some drastic changes because of extreme air pollution. In this paper, we have applied several machine learning models that include deep learning such as Long Short-Term Memory (LSTM) and proposed different techniques to forecast the air quality level of Dhaka city. Furthermore, we demonstrate the applicability of machine learning and deep learning models in the classification and prediction of the Air Quality Index (AQI) based on some pre-determined range. The novelty of this approach is that we have considered daily temperature as a parameter for air pollution prediction. We conduct an extensive evaluation of these models and show that different machine learning models can classify the AQI of different places of Dhaka city. LSTM models can also forecast hourly and daily AQI with optimal performance.

Air quality in Yogyakarta City is declining along with the increase in air pollution caused by human activities, such as transportation and industry, thus having a serious impact on health and the environment. Some of the parameters are PM10, SO2, Com O3, and NO2 which are based on ISPU (Air Pollution Standard Index) data from the Yogyakarta City Environment Agency from 2020 to 2023. In this study, classification and prediction were carried out using the LSTM (Long Short-Term Memory) algorithm to predict air quality standards with five pollution parameters of PM10, SO2, CO, O3, and NO2. The results of this study on the performance graph showed that the model was likely to be overfitted in some phases of training, although the simulation results on the random data showed consistency in the prediction with the "Good" category for air quality. So it can be concluded that this study using the LSTM (Long Short-Term Memory) model is able to classify and predict air quality effectively with results that are almost in accordance with the actual data and this study will run better with several improvements such as the use of additional parameters such as PM2.5 and increased model accuracy for optimal results.

Air quality index forecast in Beijing based on CNN-LSTM multi-model

Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction