Forecasting air pollutant concentration using a novel spatiotemporal deep learning model based on clustering, feature selection and empirical wavelet transform

Variation pattern, influential factors, and prediction models of PM2.5 concentrations in typical urban functional zones of northeast China

This study investigated the spatial and temporal variations of PM2.5 concentrations in Harbin, China, under the influence of meteorological parameters and gaseous pollutants. The complex relationship between meteorological parameters and pollutants was explored using Pearson correlation analysis and interaction effect analysis. Using the correlation analysis and interaction analysis methods, four mechanical learning models, PCC-Is-CNN, PCC-Is-LSTM, PCC-Is-CNN-LSTM and PCC-Is-BP neural network, were developed for predicting PM2.5 concentration in different time scales by combining the long-term and short-term data with the basic mechanical learning models. The results show that the PCC-Is-CNN-LSTM model has superior prediction performance, especially when integrating short-term and long-term historical data. Meanwhile, applying the model to cities in other climatic zones, the results show that the model performs well in the Dwa climatic zone, while the prediction performance is lower in the CWa climatic zone. This suggests that although the model is well adapted in regions with a similar climate to Harbin, model performance may be limited in areas with complex climatic conditions and diverse pollutant sources. This study emphasizes the importance of considering meteorological and pollutant interactions to improve the accuracy of PM2.5 predictions, providing valuable insights into air quality management in cold regions.

A deep learning model integrating a wind direction-based dynamic graph network for ozone prediction

Ozone pollution is an important environmental issue in many countries. Accurate forecasting of ozone concentration enables relevant authorities to enact timely policies to mitigate adverse impacts. This study develops a novel hybrid deep learning model, named wind direction-based dynamic spatio-temporal graph network (WDDSTG-Net), for hourly ozone concentration prediction. The model uses a dynamic directed graph structure based on hourly changing wind direction data to capture evolving spatial relationships between air quality monitoring stations. It applied the graph attention mechanism to compute dynamic weights between connected stations, thereby aggregating neighborhood information adaptively. For temporal modeling, it utilized a sequence-to-sequence model with attention mechanism to extract long-range temporal dependencies. Additionally, it integrated meteorological predictions to guide the ozone forecasting. The model achieves a mean absolute error of 6.69 μg/m3 and 18.63 μg/m3 for 1-h prediction and 24-h prediction, outperforming several classic models. The model's IAQI accuracy predictions at all stations are above 75 %, with a maximum of 81.74 %. It also exhibits strong capabilities in predicting severe ozone pollution events, with a 24-h true positive rate of 0.77. Compared to traditional static graph models, WDDSTG-Net demonstrates the importance of incorporating short-term wind fluctuations and transport dynamics for data-driven air quality modeling. In principle, it may serve as an effective data-driven approach for the concentration prediction of other airborne pollutants.

Deep-learning architecture for PM2.5 concentration prediction: A review

Accurately predicting the concentration of fine particulate matter (PM2.5) is crucial for evaluating air pollution levels and public exposure. Recent advancements have seen a significant rise in using deep learning (DL) models for forecasting PM2.5 concentrations. Nonetheless, there is a lack of unified and standardized frameworks for assessing the performance of DL-based PM2.5 prediction models. Here we extensively reviewed those DL-based hybrid models for forecasting PM2.5 levels according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We examined the similarities and differences among various DL models in predicting PM2.5 by comparing their complexity and effectiveness. We categorized PM2.5 DL methodologies into seven types based on performance and application conditions, including four types of DL-based models and three types of hybrid learning models. Our research indicates that established deep learning architectures are commonly used and respected for their efficiency. However, many of these models often fall short in terms of innovation and interpretability. Conversely, models hybrid with traditional approaches, like deterministic and statistical models, exhibit high interpretability but compromise on accuracy and speed. Besides, hybrid DL models, representing the pinnacle of innovation among the studied models, encounter issues with interpretability. We introduce a novel three-dimensional evaluation framework, i.e., Dataset-Method-Experiment Standard (DMES) to unify and standardize the evaluation for PM2.5 predictions using DL models. This review provides a framework for future evaluations of DL-based models, which could inspire researchers to standardize DL model usage in PM2.5 prediction and improve the quality of related studies.

Predicting dust pollution from dry bulk ports in coastal cities: A hybrid approach based on data decomposition and deep learning

Dust pollution from storage and handling of materials in dry bulk ports seriously affects air quality and public health in coastal cities. Accurate prediction of dust pollution helps identify risks early and take preventive measures. However, there remain challenges in solving non-stationary time series and selecting relevant features. Besides, existing studies rarely consider impacts of port operations on dust pollution. Therefore, a hybrid approach based on data decomposition and deep learning is proposed to predict dust pollution from dry bulk ports. Port operational data is specially integrated into input features. A secondary decomposition and recombination (SDR) strategy is presented to reduce data non-stationarity. A dual-stage attention-based sequence-to-sequence (DA-Seq2Seq) model is employed to adaptively select the most relevant features at each time step, as well as capture long-term temporal dependencies. This approach is compared with baseline models on a dataset from a dry bulk port in northern China. The results reveal the advantages of SDR strategy and integrating operational data and show that this approach has higher accuracy than baseline models. The proposed approach can mitigate adverse effects of dust pollution from dry bulk ports on urban residents and help port authorities control dust pollution.

Prediction of air pollutant concentrations based on the long short-term memory neural network

In recent years, environmental problems caused by air pollutants have received increasing attention. Effective prediction of air pollutant concentrations is an important way to protect the public from harm. Recently, due to extreme climate and social development, the forest fire frequency has increased. During the biomass combustion process caused by forest fires, the content of particulate matter (PM) in the atmosphere increases significantly. However, most existing air pollutant concentration prediction methods do not consider the considerable impact of forest fires, and effective long-term prediction models have not been established to provide early warnings for harmful gases. Therefore, in this paper, we collected a daily air quality data set (aerodynamic diameter smaller than 2.5 µm, PM2.5) for Heilongjiang Province, China, from 2017 to 2023 and A novel Long Short-Term Memory (LSTM) model was proposed to effectively predict the situation of air pollutants. The model could automatically extract information of the effective time step from the historical data set and combine forest fire disturbance and climate data as auxiliary data to improve the model prediction ability. Moreover, we created artificial neural network (ANN) and permissive regression (support vector machine, SVR) models for comparative experiments. The results showed that the precision accuracy of the developed LSTM model is higher. Unlike the other models, the LSTM neural network model could effectively predict the concentration of air pollutants in long-term series. Regarding long-term observation missions (7 days), the proposed model performed well and stably, with R2 reaching over 88%.

Spatiotemporal informer: A new approach based on spatiotemporal embedding and attention for air quality forecasting

Accurate prediction of air pollution is essential for public health protection. Air quality, however, is difficult to predict due to the complex dynamics, and its accurate forecast still remains a challenge. This study suggests a spatiotemporal Informer model, which uses a new spatiotemporal embedding and spatiotemporal attention, to improve AQI forecast accuracy. In the first phase of the proposed forecast mechanism, the input data is transformed by the spatiotemporal embedding. Next, the spatiotemporal attention is applied to extract spatiotemporal features from the embedded data. The final forecast is obtained based on the attention tensors. In the proposed forecast model, the input is a 3-dimensional data that consists of air quality data (AQI, PM2.5, O3, SO2, NO2, CO) and geographic information, and the output is a multi-positional, multi-temporal data that shows the AQI forecast result of all the monitoring stations in the study area. The proposed forecast model was evaluated by air quality data of 34 monitoring stations in Beijing, China. Experiments showed that the proposed forecast model could provide highly accurate AQI forecast: the average of MAPE values for from 1 h to 20 h ahead forecast was 11.61%, and it was much smaller than other models. Moreover, the proposed model provided a highly accurate and stable forecast even at the extreme points. These results demonstrated that the proposed spatiotemporal embedding and attention techniques could sufficiently capture the spatiotemporal correlation characteristics of air quality data, and that the proposed spatiotemporal Informer could be successfully applied for air quality forecasting.

Simulating daily PM2.5 concentrations using wavelet analysis and artificial neural network with remote sensing and surface observation data

Accurate PM2.5 concentrations predicting is critical for public health and wellness as well as pollution control. However, traditional methods are difficult to accurately predict PM2.5. An adaptive model coupled with artificial neural network (ANN) and wavelet analysis (WANN) is utilized to predict daily PM2.5 concentrations with remote sensing and surface observation data. The four evaluation metrics, namely Pearson correlation coefficient (R), mean absolute percentage error (MAPE), root mean square error (RMSE), and mean absolute error (MAE), are utilized to evaluate the performances of the artificial neural network (ANN) and WANN methods. From the predicting results, The WANN model has a higher R (R = 0.9990) during the testing period compared with R (R = 0.6844) based on the ANN model. Similarly, the WANN model has a lower MAPE (3.6988%), RMSE (1.0145 μg/m3), MAE (1.3864 μg/m3), compared with MAPE (80.0086%), RMSE (16.5838 μg/m3), MAE (12.2420 μg/m3) of the ANN. In addition, comparing the outcomes of the proposed WANN method with the ANN method, it was observed that the error during the training and verification period has decreased significantly. Furthermore, the statistical methods are used to analyze WANN and ANN, showing that WANN has higher training accuracy and better stability. Therefore, it is feasible to establish WANN to predict PM2.5 concentrations (1 day in advance) by using remote sensing and surface observation data.

Exploring ozone formation rules and concentration response to the change of precursors based on artificial neural network simulation in a typical industrial park

Industrial parks have more complex O3 formation mechanisms due to a higher concentration and more dense emission of precursors. This study establishes an artificial neural network (ANN) model with good performance by expanding the moment and concentration changes of pollutants into general variables of meteorological factors and concentrations of pollutants. Finally, the O3 formation rules and concentration response to the changes of volatile organic compounds (VOCs) and nitrogen oxides (NOx) was explored. The results showed that the studied area belonged to the NOx-sensitive regime and the sensitivity was strongly affected by relative humidity (RH) and pressure (P). The concentration of O3 tends to decrease with a higher P, lower temperature (Temp), and medium to low RH when nitric oxide (NO) is added. Conversely, at medium P, high Temp, and high RH, the addition of nitrogen dioxide (NO2) leads to a larger decrease capacity in O3 concentration. More importantly, there is a local reachable maximum incremental reactivity (MIRL) at each certain VOCs concentration level which linearly increased with VOCs. The general maximum incremental reactivity (MIR) may lead to a significant overestimation of the attainable O3 concentration in NOx-sensitive regimes. The results can significantly support the local management strategies for O3 and the precursors control.

A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network

Short-term prediction of urban air quality is critical to pollution management and public health. However, existing studies have failed to make full use of the spatiotemporal correlations or topological relationships among air quality monitoring networks (AQMN), and hence exhibit low precision in regional prediction tasks. With this consideration, we proposed a novel deep learning-based hybrid model of Res-GCN-BiLSTM combining the residual neural network (ResNet), graph convolutional network (GCN), and bidirectional long short-term memory (BiLSTM), for predicting short-term regional NO₂ and O₃ concentrations. Auto-correlation analysis and cluster analysis were first utilized to reveal the inherent temporal and spatial properties respectively. They demonstrated that there existed temporal daily periodicity and spatial similarity in AQMN. Then the identified spatiotemporal properties were sufficiently leveraged, and monitoring network topological information, as well as auxiliary pollutants and meteorology were also adaptively integrated into the model. The hourly observed data from 51 air quality monitoring stations and meteorological data in Shanghai were employed to evaluate it. Results show that the Res-GCN-BiLSTM model was better adapted to the pollutant characteristics and improved the prediction accuracy, with nearly 11% and 17% improvements in mean absolute error for NO₂ and O₃, respectively compared to the best performing baseline model. Among the three types of monitoring stations, traffic monitoring stations performed the best for O₃, but the worst for NO₂, mainly due to the impacts of intensive traffic emissions and the titration reaction. These findings illustrate that the hybrid architecture is more suitable for regional pollutant concentration.

Spatiotemporal characteristics of air pollution in Chengdu-Chongqing urban agglomeration (CCUA) in Southwest, China: 2015-2021

Studying the spatiotemporal characteristics of air pollutants in urban agglomerations and their response factors will help to improve the quality of urban living. In combining air quality monitoring data and wavelet analysis from the Chengdu-Chongqing urban agglomeration (CCUA), this study assessed the spatiotemporal distribution characteristics and influential factors of air pollutants on daily, monthly and annual scales. The results showed that the concentration of air pollutants in the CCUA has decreased year by year, and air quality has improved. Except for O₃, pollutants in autumn and winter were higher than those in summer. The spatial distribution of air pollutants was obvious distributed in Chengdu, Chongqing, Zigong and Dazhou. Pollution incidents were mainly concentrated in winter. The 6 air pollutants and air quality index (AQI) have dominant periods on multiple time scales. AQI showed positive coherence with PM_2.5 and PM₁₀ on multiple time scales, and obvious positive coherence with SO₂, CO, NO₂ and O₃ in the short term scale. AQI was not strongly correlated with the fire point, but exhibited obvious negative coherence in the long term scale. In addition, AQI showed an obvious positive correlation with temperature and sunshine hours in short term, and a clear negative correlation with humidity and rainfall. The research results of this paper will provide a reference for pollution prevention and control in the CCUA.

Water quality forecasting based on data decomposition, fuzzy clustering and deep learning neural network

Water quality forecasting can provide useful information for public health protection and support water resources management. In order to forecast water quality more accurately, this paper proposes a novel hybrid model by combining data decomposition, fuzzy C-means clustering and bidirectional gated recurrent unit. Firstly, the original water quality data is decomposed into several subseries by empirical wavelet transform, and then, the decomposed subseries are recombined by fuzzy C-means clustering. Next, for each clustered series, bidirectional gated recurrent unit is applied to develop prediction model. Finally, the forecast result is obtained by the summation of the predictions for the subseries. The proposed forecast model is evaluated by the water quality data of Poyang Lake, China. Results show that the proposed forecast model provides highly accurate forecast result for all of the six water quality data: the average of MAPE of the forecast results for the six water quality datasets is 4.59% for 7 day ahead prediction. Furthermore, our model shows better forecast performance than the other models. Particularly, compared with the single BiGRU model, MAPE decreased by 32.86% in average. Results demonstrate that the proposed forecast model can be used effectively for water quality forecasting.