Air Quality Prediction Research Articles

Multivariable Air-Quality Prediction and Modelling via Hybrid Machine Learning: A Case Study for Craiova, Romania.

Inadequate air quality has adverse impacts on human well-being and contributes to the progression of climate change, leading to fluctuations in temperature. Therefore, gaining a localized comprehension of the interplay between climate variations and air pollution holds great significance in alleviating the health repercussions of air pollution. This study uses a holistic approach to make air quality predictions and multivariate modelling. It investigates the associations between meteorological factors, encompassing temperature, relative humidity, air pressure, and three particulate matter concentrations (PM10, PM2.5, and PM1), and the correlation between PM concentrations and noise levels, volatile organic compounds, and carbon dioxide emissions. Five hybrid machine learning models were employed to predict PM concentrations and then the Air Quality Index (AQI). Twelve PM sensors evenly distributed in Craiova City, Romania, provided the dataset for five months (22 September 2021-17 February 2022). The sensors transmitted data each minute. The prediction accuracy of the models was evaluated and the results revealed that, in general, the coefficient of determination (R2) values exceeded 0.96 (interval of confidence is 0.95) and, in most instances, approached 0.99. Relative humidity emerged as the least influential variable on PM concentrations, while the most accurate predictions were achieved by combining pressure with temperature. PM10 (less than 10 µm in diameter) concentrations exhibited a notable correlation with PM2.5 (less than 2.5 µm in diameter) concentrations and a moderate correlation with PM1 (less than 1 µm in diameter). Nevertheless, other findings indicated that PM concentrations were not strongly related to NOISE, CO2, and VOC, and these last variables should be combined with another meteorological variable to enhance the prediction accuracy. Ultimately, this study established novel relationships for predicting PM concentrations and AQI based on the most effective combinations of predictor variables identified.

Time-delayed causal network analysis of meteorological variables and air pollutants in Baguio city

Air pollution contributes significantly to climate change and has recently become a significant concern. Previous studies on the interplay between air quality and the environment, such as meteorological variables, have hinted at their relevance in predicting air quality. While air quality prediction has been extensively explored, only a few studies have investigated the causal interactions, and no study has looked into identifying time-delayed causality between individual meteorological factors and air pollutants. In this work, we have deployed sensors in Baguio City, renowned as the “Summer Capital of the Philippines”, and collected data from September 2022 to April 2023. Convergent Cross Mapping (CCM) is then used to infer the time-delayed causation network for PM1, PM2.5, PM10, VOC, and local meteorological variables. Baguio City faces environmental challenges from urbanization and influx of tourists. Here, the top meteorological variables are identified and characterized according to the strength and delay of influences on air pollutants. Wind direction emerges as a leading influencer driving air quality instantly, while pollutants reciprocate with delayed feedback. Temperature holds sway after a day, with pollutants impacting it after eight days on average. Furthermore, links from wind speed to PM concentrations are observed as mediators in causal pathways. Here, the maximum lag delay is only nine days. This work highlights the intricate interdependence of local meteorological factors and air quality, pioneering the identification of time delays that optimize causal influences between these variables. The results of this work offer valuable insights into environmental management and the formulation of mitigation measures.

How to measure and control indoor air quality based on intelligent digital twin platforms: A case study in China

In order to address the current disparity between indoor air quality assessment, prediction, and control, this study proposes an intelligent management approach for indoor air quality based on digital twin platforms. By collecting and fusing multi-level, and multi-dimensional data at the physical level, a comprehensive data integration and analysis platform is established in the digital realm, encompassing the ‘Sense-Integrate-Retrieve-Analyze-Feedback’ framework. Various digital technologies, such as the Internet of Things (IoT), Building Information Modeling (BIM), and machine learning, are utilized to integrate and visualize multi-source heterogeneous data through a lightweight web-based interface so that data retrieval, rapid prediction, and intelligent control are feasible based on various backend algorithm models. Compared to traditional measurement methods, this system offers broader spatiotemporal coverage, increased mobility, and less disruption to physical infrastructure, which underscores the sophistication of monitoring technology, data integration, and environmental management. The proposed intelligent platform has been validated in a traditional Chinese dwelling, and practical results demonstrate that most air quality problems occur in the early morning of winter while this system can swiftly predict and issue control signals for adjustments in occupied spaces exceeding predefined healthy thresholds. Field measurements confirmed that most air quality problems can be solved within 30 min after their appearance. By eliminating data silos through real-time synchronization and remote intelligent control via the digital platform, it bridges the gap between problem identification by managers and problem resolution by end-users, ensuring timely responses to indoor air quality concerns.

An adaptive adjacency matrix-based graph convolutional recurrent network for air quality prediction

In recent years, air pollution has become increasingly serious and poses a great threat to human health. Timely and accurate air quality prediction is crucial for air pollution early warning and control. Although data-driven air quality prediction methods are promising, there are still challenges in studying spatial–temporal correlations of air pollutants to design effective predictors. To address this issue, a novel model called adaptive adjacency matrix-based graph convolutional recurrent network (AAMGCRN) is proposed in this study. The model inputs Point of Interest (POI) data and meteorological data into a fully connected neural network to learn the weights of the adjacency matrix thereby constructing the self-ringing adjacency matrix and passes the pollutant data with this matrix as input to the Graph Convolutional Network (GCN) unit. Then, the GCN unit is embedded into LSTM units to learn spatio-temporal dependencies. Furthermore, temporal features are extracted using Long Short-Term Memory network (LSTM). Finally, the outputs of these two components are merged and air quality predictions are generated through a hidden layer. To evaluate the performance of the model, we conducted multi-step predictions for the hourly concentration of PM2.5, PM10 and O3 at Fangshan, Tiantan and Dongsi monitoring stations in Beijing. The experimental results show that our method achieves better predicted effects compared with other baseline models based on deep learning. In general, we designed a novel air quality prediction method and effectively addressed the shortcomings of existing studies in learning the spatio-temporal correlations of air pollutants. This method can provide more accurate air quality predictions and is expected to provide support for public health protection and government environmental decision-making.

TEMPORAL ANALYSIS AND PREDICTIVE MODELING OF AMBIENT AIR QUALITY IN HULU LANGAT DISTRICT, SELANGOR, MALAYSIA: A CHEMOMETRIC APPROACH

One of the most important environmental problems facing the globe today is air pollution. The centre area for the local populace is the Hulu Langat district, which borders Kuala Lumpur, the capital. The purpose of this study is to look at how the ambient air quality varies in Hulu Langat, Selangor. The Air Quality Division of the Malaysian Department of Environment provided five years' worth of secondary data on the air quality at Hulu Langat. The database included five primary air pollutant characteristics sulphur dioxide (SO2), carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2), and particulate matter with a diameter of 10 microns or less (PM10), in addition to data from the Air Pollutant Index (API). Chemometric analysis was used to examine the results. According to the results, SO2, NO2 and PM10 had the greatest correlations with API readings. A statistical process known as statistical control (SPC) showed that certain PM10 values were over national recommendations and control limits. The artificial neural network method's air quality prediction model demonstrated good accuracy with real data (R2 = 0.9). The results of this investigation indicated a strong correlation between the Hulu Langat air quality data. In order to achieve sustainable environmental practices in the future, it is imperative to engage in extensive collaboration across environmental departments and relevant authorities and engage in continuous monitoring of air quality.

Spatiotemporal hierarchical transmit neural network for regional-level air-quality prediction

Air pollution has become a growing problem owing to its harmful effects on human health, making accurate air quality prediction an important task to avoid serious environmental impacts. Recently, graph-neural-network-based methods have emerged as promising approaches to modeling the spatial dependencies between adjacent stations. However, they have limitations in capturing the hierarchical temporal features of the time series, which include trends, and periodic components. They also overlook dynamic correlations between stations and multiple types of connections, resulting in generated graphs that lack dynamics. In this paper, we proposed a spatiotemporal hierarchical transmit neural network for the prediction of air quality by extracting long-term periodic features and short-term spatiotemporal dependencies. It incorporates a periodic feature extraction component (PFEC), a scene dynamic graph module (SDGM), a spatiotemporal extraction component (STEC), and a transmit attention (TransATT) component. The PFEC applies discrete Fourier transform and trend decomposition techniques to extract long-term periodic features from the spatiotemporal graph. The SDGM generates dynamic graphs by combining node features of time series with predefined graphs to encode diverse station relationships. The STEC comprises of two convolutional operations and attention mechanisms, enabling the model to capture the short-term spatiotemporal dependencies. TransATT integrates the extracted short-term spatiotemporal dependencies and long-term periodic features, allowing the model to transmit with short- and long-term features. To demonstrate the effectiveness of the proposed model, we conducted experiments on three real-world datasets and found that our approach outperforms state-of-the-art methods.

Statistical analysis of air quality dataset of Kathmandu, Nepal, with a New Extended Kumaraswamy Exponential Distribution.

This paper aims to create a new probability distribution and conducts statistical analysis on air quality dataset from Kathmandu. Using this innovative distribution, we have studied the ground reality of air quality conditions of Kathmandu, Nepal. In our research, we have developed a new probability distribution known as the New Extended Kumaraswamy Exponential Distribution by introducing an additional shape parameter to the Extended Kumaraswamy Exponential (EKwE) Distribution. Statistical characteristics such as cumulative distribution function, probability density function, hazard function, reversed hazard function, skewness, kurtosis, survival function, and hazard rate function are studied. The suggested model is non-normal and positively skewed with increasing and inverted bathtub-shaped hazard rate curves. To assess the model's suitability, we utilized a real dataset comprising air quality data from Kathmandu, Nepal, during the year 2021. Study shows that the air quality data exhibit an increasing failure rate, but the P2.5, P10, and total suspended particle concentrations exhibited its lowest levels during the monsoon season and its highest levels during the winter season. Parameters of the model are estimated by using the least square estimation (LSE), maximum likelihood estimation (MLE), and Cramér-von Mises (CVM) approach for P10 at Ratnapark Station, Kathmandu. To assess the model's validity, P-P plots and Q-Q plots are employed. Model comparisons are carried out using Akaike Information Criterion (AIC), Corrected Akaike Information Criterion (CAIC), Bayesian Information Criterion (BIC), and Hannan-Quinn Information Criterion (HQIC). Furthermore, the goodness of fit of the proposed model is evaluated using test statistics such as Anderson-Darling (A2) test, Cramér-von Mises (CVM) test, and the Kolmogorov-Smirnov (KS) test along with their respective p-values. From the findings, we have found that the air quality status of Kathmandu, Nepal, was found to be poor. Proposed distribution provides a better fit with greater flexibility for forecasting air quality data and conducting reliability data analyses. Dataset is analyzed and visualized using R programming.

Breathing on the job: investigating predictors of air quality protective actions and information seeking among outdoor workers

ABSTRACT Background Air quality issues, exacerbated by wildfire smoke and excessive ozone that is worsened by climate change, pose significant health risks to outdoor workers, who are often overlooked in regulatory protection and communication efforts. This study examined how outdoor worker demographics, risk perceptions, and efficacy beliefs predict air quality protective actions and information seeking. Additionally, it investigates the sources of information that this population relies on for understanding air quality. Method A survey was conducted with 256 outdoor workers in Colorado, a state regularly affected by wildfire smoke and ozone. Measures included demographics, perceived risk, efficacy beliefs, air quality actions, and information seeking behavior. Results Both perceived risk and efficacy beliefs influenced health-protective actions during poor air quality events. Interestingly, efficacy beliefs were found to be a more reliable predictor of air quality information seeking than perceived risk. The top sources of air quality information among outdoor workers were local news media, The Weather Channel, mobile apps, state public health authorities, and the National Weather Service. Conclusions These findings enhance our understanding of how perceived risk and efficacy beliefs promote health-protective behaviors among outdoor workers. They lay the groundwork for future research and initiatives to improve air quality communication and promote health-protective actions for this population group. Promoting the efficacy of health-protective actions and seeking information are important components of air quality communication.

Air quality monitoring using statistical learning models for sustainable environment

High levels of air pollutants pose significant health risks, increasing the chances of respiratory infections, lung cancer, and heart complications, particularly for those already susceptible to illness. Modern societal advancements have worsened air quality degradation, with daily activities such as transportation, industrial processes, and domestic operations releasing harmful contaminants. This study addresses the urgent need for air quality monitoring and forecasting, especially in developing nations like India, where machine learning-based prediction technologies play a crucial role in understanding environmental aspects. Our study focuses on analyzing and predicting air quality using data from two distinct areas in Kolkata—Victoria and Rabindra. Thorough pre-processing and data analysis have been conducted to identify essential features and detect undermining patterns in the data. Utilizing five classic machine learning algorithms, we predict the air quality category by categorizing the predicted AQI into six AQI classes, emphasizing extensive hyper-parameter tuning for each model. The Rabindra dataset yields the best-performing Support Vector Machine (SVC) model with a 97.98% accuracy, while the best prediction accuracy for Victoria location is 93.29% from Random Forest Classifier (RFC). This study offers valuable insights into the effectiveness of machine learning algorithms for air quality prediction, with the novelty of the study lying in the focus on hyper-parameter tuning to achieve the highest accuracy.

An empirical study of indoor air quality in badminton stadiums in hot summer and cold winter regions of China during spring and fall seasons

The indoor air quality has a direct impact on human health. In order to obtain the current status of indoor air quality in typical sports buildings in hot summer and cold winter climate zones in China, indoor badminton courts in 10 cities in Hubei Province in this climate zone were selected as research objects for field testing of indoor environmental parameters in spring and autumn, and predict air quality parameters for non-testing times. All the tested stadiums are naturally ventilated in non-event conditions, and the average daily indoor CO2 concentration was 526.78 ppm in spring and 527.63 ppm in autumn, and the average daily PM2.5 concentration was 0.035 mg/m3 in spring and 0.024 mg/m3 in autumn, all of which met the requirements of GB/T 18883-2022, the average concentration of CO2 ≤ 1000 ppm and PM2.5 ≤ 0.05 mg/m3. The indoor CO2 concentration and PM2.5 concentration of the tested badminton halls under natural ventilation gradually increased with the accumulation of exercise time, making the indoor air quality of the badminton halls decrease, which would negatively affect the health of the people exercising in this environment.

Technical note: Accurate, reliable, and high-resolution air quality predictions by improving the Copernicus Atmosphere Monitoring Service using a novel statistical post-processing method

Abstract. Starting from the regional air quality forecasts produced by the Copernicus Atmosphere Monitoring Service (CAMS), we propose a novel post-processing approach to improve and downscale results on a finer scale. Our approach is based on the combination of ensemble model output statistics (EMOS) with a spatio-temporal interpolation process performed through the stochastic partial differential equation–integrated nested laplace approximation (SPDE-INLA). Our interpolation approach includes several spatial and spatio-temporal predictors, including meteorological variables. A use case is provided that scales down the CAMS forecasts on the Italian peninsula. The calibration is focused on the concentrations of several air quality pollutants (PM10, PM2.5, NO2, and O3) at a daily resolution from a set of 750 monitoring sites, distributed throughout the Italian country. Our results show the key role that conditioning variables play in improving the forecast capabilities of ensemble predictions, thus allowing for a net improvement in the calibration with respect to ordinary EMOS strategies. From a deterministic point of view, the performance of the predictive model shows a significant improvement in the performance of the raw ensemble forecast, with an almost-zero bias, significantly reduced root mean square errors, and correlations that are almost always higher than 0.9 for each pollutant; moreover, the post-processing approach is able to significantly improve the prediction of exceedances, even for very low thresholds, such as those recently recommended by the World Health Organisation. This is particularly significant if a forecasting approach is used to predict air quality conditions and plan adequate human health protection measures, even for low alert thresholds. From a probabilistic point of view, the quality of the forecast was verified in terms of reliability and credible intervals. After post-processing, the predictive probability density functions were sharp and much better calibrated than the raw ensemble forecast. Finally, we present some additional results based on a set of gridded (4 km × 4 km) maps covering the entire Italian country for the detection of areas where pollution peaks occur (exceedances of the current and/or proposed regulatory thresholds).

Comparative Analysis of Aerosol Vertical Characteristics over the North China Plain Based on Multi-Source Observation Data

In this paper, multi-source observation, such as aircraft, ground-based remote sensing, and satellite-retrieved data, has been utilized to compare and analyze the vertical characteristics of aerosol optical properties and the planetary boundary layer height (HPBL) over the North China Plain (NCP) region during May–June 2016. Aircraft observations show the vertical profiles of aerosol absorption coefficients (σabs), scattering coefficients (σsca), and extinction coefficients (σext) gradually decrease with altitude, with their maximum values near HPBL. The vertical profiles of σext depended most on the vertical distribution of measured σsca, indicating a significant contribution of scattering aerosols. In addition, the prominent characteristic of the inverse relationship between σext and moisture profile could serve as a reference for predicting air quality in the NCP region. The lower layer pollution during the field experiment was likely caused by the accumulation of fine-mode aerosols, characterized by the vertical distribution of the Ångström exponent and the Aerosol Robotic Network (AERONET) products. Typically, HPBL derived from aircraft and surface Micro Pulse Lidar (MPL) was approximate, while the predicted HPBL by meteorological data indicates an underestimation of ~192 m. Aerosol optical depth (AOD) calculated from aircraft and ground-based remote sensing (such as MPL and AERONET) experienced a strong correlation, and both of them exhibited a similar tendency. However, the AOD retrieved from satellites was significantly larger than that from aircraft and ground-based remote sensing. Overall, the inversion algorithm, cloud identification algorithm, representativeness of the space, and time of the observation may lead to an overestimation or underestimation of AOD under certain circumstances. This study may serve as a re-evaluation of AOD retrieved from multi-source observations and provide a reference to uncover the actual atmospheric environment in the NCP regions.

Advancing air quality prediction models in urban India: a deep learning approach integrating DCNN and LSTM architectures for AQI time-series classification

Advancing air quality prediction models in urban India: a deep learning approach integrating DCNN and LSTM architectures for AQI time-series classification

A Hybrid Air Quality Prediction Model Based on Empirical Mode Decomposition

A Hybrid Air Quality Prediction Model Based on Empirical Mode Decomposition

Artificial Intelligence Algorithms for Prediction and Diagnosis of Air Pollution Affecting Human Health

The complexity and growth of data in healthcare means that artificial intelligence (AI) will be increasingly applied in this area. This article (study) de-scribes the types of AI used by care providers and life and biophysical sciences companies. This paper describes the structure of the methodology of artificial intelligence (AI) algorithms and its machine learning (ML) subsystem with respect to the prediction of environmental pollution and its negative impact on humans. Key categories of AI applications focus on diagnosis and treatment or referral, patient engagement and adherence, and administrative activities. Diagnosis of diseases is a crucial and very important task of the physician in planning the right treatment and ensuring the health status of patients. The application of artificial intelligence (AI) can improve the level of diagnostic accuracy and efficiency. Indoor air quality (IAQ) is an important issue for well-being and good health, as most people spend almost all of their time in different types of buildings. Given the increasing availability of data and the rapid expansion of AI techniques, it is essential to explore the development of indoor and outdoor air quality predictions using AI techniques to improve and maintain IAQ.

An interval AQI combination prediction model based on multiple data decomposition and information aggregation operator.

In this paper, an interval Air Quality Index (AQI) combination prediction model based on EEMD, VMD, and the weighted power average (WPA) operator is proposed. EEMD and VMD decompose complex AQI data effectively, while WPA operator reasonably aggregates the prediction results of different models. We validate the effectiveness of the proposed model using Shenzhen's daily interval AQI. Furthermore, three kinds of prediction models are compared with the proposed model to highlight its advantages from various perspectives. The results show that the introduction of data decomposition methods significantly improves the model's prediction accuracy, WPA operator further enhances the model's prediction capability, and the incorporation of EEMD and VMD enables the proposed model to have stronger feature extraction capabilities for complex time series. As a result, the model proposed in this paper demonstrates strong generalization ability and prediction accuracy, making it applicable not only for air quality prediction but also for other domains such as economics and environment.

Modeling below-cloud scavenging of size-resolved particles in GEM-MACHv3.1

Abstract. Below-cloud scavenging (BCS) is the process of aerosol removal from the atmosphere between cloud base and the ground by precipitation (e.g., rain or snow), and affects aerosol number or mass concentrations, size distribution, and lifetime. An accurate representation of precipitation phases is important in treating BCS as the efficiency of aerosol scavenging differs significantly between liquid and solid precipitation. The impact of different representations of BCS on existing model biases was examined through implementing a new aerosol BCS scheme in the Environment and Climate Change Canada (ECCC) air quality prediction model GEM-MACH and comparing it with the existing scavenging scheme in the model. Further, the current GEM-MACH employs a single-phase precipitation for BCS: total precipitation is treated as either liquid or solid depending on a fixed environment temperature threshold. Here, we consider co-existing liquid and solid precipitation phases as they are predicted by the GEM microphysics. GEM-MACH simulations, in a local-area domain over the Athabasca oil sands areas, Canada, are compared with observed precipitation samples, with a focus on the particulate base cation NH4+; acidic anions NO3-, SO4=, HSO3- in precipitation; and observed ambient particulate sulfate, ammonium, and nitrate concentrations. Overall, the introduction of the multi-phase approach and the new scavenging scheme enhances GEM-MACH performance compared to previous methods. Including a multi-phase approach leads to altered SO4= scavenging and impacts the BCS of SO2 into the aqueous phase over the domain. Sulfate biases improved from +46 % to −5 % relative to Alberta Precipitation Quality Monitoring Program wet sulfate observations. At Canadian Air and Precipitation Monitoring Network stations the biases became more negative, from −10 % to −30 % for the tests carried out here. These improvements contrast with prior annual average biases of +200 % for SO4=, indicating enhanced model performance. Improvements in model performance (via scores for correlation coefficient, normalized mean bias, and/or fractional number of model values within a factor of 2 of observations) could also be seen between the base case and the two simulations based on multi-phase partitioning for NO3-, NH4+, and SO4=. Whether or not these improvements corresponded to increases or decreases in NO3- and NH4+ wet deposition varied over the simulation region. The changes were episodic in nature – the most significant changes in wet deposition were likely at specific geographic locations and represent specific cloud precipitation events. The changes in wet scavenging resulted in a higher formation rate and larger concentrations of atmospheric particle sulfate.

Air quality forecasting‐driven cloud resource allocation for sustainable energy consumption: An ensemble classifier approach

AbstractIn recent times, air quality prediction is turned out to be one of the important research topics among research communities to prevent lives from negative health impacts. Random fluctuations of PM2.5 level brought about by frequent variations in meteorological factors create difficulties air pollution management. Forecasting the quality of air using time series data serves as a defense mechanism against threatening hazards by providing immense support to take preventive measures. Besides, handling dynamic real time workloads, forecasted by the prediction model requires appropriate computing resources to distribute workloads based on demands. To achieve this goal, this paper proposes a new Air Quality Prediction‐enabled Resource Allocation scheme for cloud‐based software services, which offers dynamic adjustment of resources based on workload demands with high energy efficiency. The proposed system is a two phase system that executes both air quality prediction and resource allocation processes consecutively. A new weighted average ensemble classifier is designed by combining support vector machine (SVM), artificial neural network (ANN), and gradient boosting machine (GBM) techniques to measure PM2.5 level on time series information of Beijing PM2.5 dataset. The system then dynamically allocates appropriate computing resources using crossover particle swarm optimization (CPSO) algorithm based on the forecasted results of PM2.5 level. This system has the potential to contribute significantly to reducing energy consumption and improving air quality in cities worldwide. The experimental results conducted to determine the efficiency of the proposed system in terms of different metrics proves that it achieves greater performance with less error functions for PM2.5 level prediction as well as minimizes energy consumption for resource allocation when compared with existing methods.

Prediction of atmospheric PM2.5 level by machine learning techniques in Isfahan, Iran

With increasing levels of air pollution, air quality prediction has attracted more attention. Mathematical models are being developed by researchers to achieve precise predictions. Monitoring and prediction of atmospheric PM2.5 levels, as a predominant pollutant, is essential in emission mitigation programs. In this study, meteorological datasets from 9 years in Isfahan city, a large metropolis of Iran, were applied to predict the PM2.5 levels, using four machine learning algorithms including Artificial Neural |Networks (ANNs), K-Nearest-Neighbors (KNN), Support Vector |Machines (SVMs) and ensembles of classification trees Random Forest (RF). The data from 7 air quality monitoring stations located in Isfahan City were taken into consideration. The Confusion Matrix and Cross-Entropy Loss were used to analyze the performance of classification models. Several parameters, including sensitivity, specificity, accuracy, F1 score, precision, and the area under the curve (AUC), are computed to assess model performance. Finally, by introducing the predicted data for 2020 into ArcGIS software and using the IDW (Inverse Distance Weighting) method, interpolation was conducted for the area of Isfahan city and the pollution map was illustrated for each month of the year. The results showed that, based on the accuracy percentage, the ANN model has a better performance (90.1%) in predicting PM2.5 grades compared to the other models for the applied meteorological dataset, followed by RF (86.1%), SVM (84.6%) and KNN (82.2%) models, respectively. Therefore, ANN modelling provides a feasible procedure for the managerial planning of air pollution control.

Complex Real-Time Monitoring and Decision-Making Assistance System Based on Hybrid Forecasting Module and Social Network Analysis

Timely short-term spatial air quality forecasting is essential for monitoring and prevention in urban agglomerations, providing a new perspective on joint air pollution prevention. However, a single model on air pollution forecasting or spatial correlation analysis is insufficient to meet the strong demand. Thus, this paper proposed a complex real-time monitoring and decision-making assistance system, using a hybrid forecasting module and social network analysis. Firstly, before an accurate forecasting module was constructed, text sentiment analysis and a strategy based on multiple feature selection methods and result fusion were introduced to data preprocessing. Subsequently, CNN-D-LSTM was proposed to improve the feature capture ability to make forecasting more accurate. Then, social network analysis was utilized to explore the spatial transporting characteristics, which could provide solutions to joint prevention and control in urban agglomerations. For experiment simulation, two comparative experiments were constructed for individual models and city cluster forecasting, in which the mean absolute error decreases to 7.8692 and the Pearson correlation coefficient is 0.9816. For overall spatial cluster forecasting, related experiments demonstrated that with appropriate cluster division, the Pearson correlation coefficient could be improved to nearly 0.99.