Prediction Of PM2 Research Articles

Evaluation of Machine Learning Application on the Prediction of Particulate Matter Concentrations in Small/Medium-Sized City

Objectives:In this study, Machine Learning (ML) algorithms were evaluated to predict the concentration of particulate matter (PM10 and PM2.5) using air quality and meteorological data in small/medium-sized city.Methods:ML models, including Multiple Linear Regression (MLR), Decision Tree Regression (DTR), Random Forest (RF), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), were used to predict PM10 and PM2.5 concentrations. Five air quality variables, including NO2, SO2, CO, PM10 and PM2.5, and seven meteorological variables, including temperature, humidity, vapor pressure, wind speed, precipitation, local atmospheric pressure, and sea-level atmosphere pressure, were collected from three air quality monitoring stations and one meteorological observatory from 2017 to 2022. A total of 52,583 sets of data were used for ML. The prediction accuracies of the applied ML models were evaluated using the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of determination (R2).Results and Discussion:Higher ML performance was obtained when using the data including PM10 and PM2.5 compared to the data excluding these variables. Among five different ML models, the XGB model showed the highest accuracy in predicting PM10 and PM2.5 one hour in the future. However, poorer performance was obtained as the predicted period increased from one hour to 72 hours.Conclusion:The application of ML algorithms for the short-term prediction of PM10 and PM2.5 was successful in this study. However, more input variables and deep learning algorithms are needed for long-term prediction of PM10 and PM2.5.

Prediction of PM2.5 Concentration Based on Deep Learning for High-Dimensional Time Series

PM2.5 poses a serious threat to human life and health, so the accurate prediction of PM2.5 concentration is essential for controlling air pollution. However, previous studies lacked the generalization ability to predict high-dimensional PM2.5 concentration time series. Therefore, a new model for predicting PM2.5 concentration was proposed to address this in this paper. Firstly, the linear rectification function with leakage (LeakyRelu) was used to replace the activation function in the Temporal Convolutional Network (TCN) to better capture the dependence of feature data over long distances. Next, the residual structure, dilated rate, and feature-matching convolution position of the TCN were adjusted to improve the performance of the improved TCN (LR-TCN) and reduce the amount of computation. Finally, a new prediction model (GRU-LR-TCN) was established, which adaptively integrated the prediction of the fused Gated Recurrent Unit (GRU) and LR-TCN based on the inverse ratio of root mean square error (RMSE) weighting. The experimental results show that, for monitoring station #1001, LR-TCN increased the RMSE, mean absolute error (MAE), and determination coefficient (R2) by 12.9%, 11.3%, and 3.8%, respectively, compared with baselines. Compared with LR-TCN, GRU-LR-TCN improved the index symmetric mean absolute percentage error (SMAPE) by 7.1%. In addition, by comparing the estimation results with other models on other air quality datasets, all the indicators have advantages, and it is further demonstrated that the GRU-LR-TCN model exhibits superior generalization across various datasets, proving to be more efficient and applicable in predicting urban PM2.5 concentration. This can contribute to enhancing air quality and safeguarding public health.

Prediction of PM2.5 concentration based on a CNN-LSTM neural network algorithm.

Fine particulate matter (PM2.5) is a major air pollutant affecting human survival, development and health. By predicting the spatial distribution concentration of PM2.5, pollutant sources can be better traced, allowing measures to protect human health to be implemented. Thus, the purpose of this study is to predict and analyze the PM2.5 concentration of stations based on the integrated deep learning of a convolutional neural network long short-term memory (CNN-LSTM) model. To solve the complexity and nonlinear characteristics of PM2.5 time series data problems, we adopted the CNN-LSTM deep learning model. We collected the PM2.5data of Qingdao in 2020 as well as meteorological factors such as temperature, wind speed and air pressure for pre-processing and characteristic analysis. Then, the CNN-LSTM deep learning model was integrated to capture the temporal and spatial features and trends in the data. The CNN layer was used to extract spatial features, while the LSTM layer was used to learn time dependencies. Through comparative experiments and model evaluation, we found that the CNN-LSTM model can achieve excellent PM2.5 prediction performance. The results show that the coefficient of determination (R2) is 0.91, and the root mean square error (RMSE) is 8.216µg/m3. The CNN-LSTM model achieves better prediction accuracy and generalizability compared with those of the CNN and LSTM models (R2 values of 0.85 and 0.83, respectively, and RMSE values of 11.356 and 14.367, respectively). Finally, we analyzed and explained the predicted results. We also found that some meteorological factors (such as air temperature, pressure, and wind speed) have significant effects on the PM2.5 concentration at ground stations in Qingdao. In summary, by using deep learning methods, we obtained better prediction performance and revealed the association between PM2.5 concentration and meteorological factors. These findings are of great significance for improving the quality of the atmospheric environment and protecting public health.

Optimizing BenMAP health impact assessment with meteorological factor driven machine learning models

This study aims to address accuracy challenges in assessing air pollution health impacts using Environmental Benefits Mapping and Analysis Program (BenMap), caused by limited meteorological factor data and missing pollutant data. By employing data increment strategies and multiple machine learning models, this research explores the effects of data volume, time steps, and meteorological factors on model prediction performance using several years of data from Tianjin City as an example. The findings indicate that increasing training data volume enhances the performance of Random Forest Regressor (RF) and Decision Tree Regressor (DT) models, especially for predicting CO, NO2, and PM2.5. The optimal prediction time step varies by pollutant, with the DT model achieving the highest R2 value (0.99) for CO and O3. Combining multiple meteorological factors, such as atmospheric pressure, relative humidity, and dew point temperature, significantly improves model accuracy. When using three meteorological factors, the model achieves an R2 of 0.99 for predicting CO, NO2, PM10, PM2.5, and SO2. Health impact assessments using BenMap demonstrated that the predicted all-cause mortality and specific disease mortalities were highly consistent with actual values, confirming the model's accuracy in assessing health impacts from air pollution. For instance, the predicted and actual all-cause mortality for PM2.5 were both 3120; for cardiovascular disease, both were 1560; and for respiratory disease, both were 780. To validate its generalizability, this method was applied to Chengdu, China, using several years of data for training and prediction of PM2.5, CO, NO2, O3, PM10, and SO2, incorporating atmospheric pressure, relative humidity, and dew point temperature. The model maintained excellent performance, confirming its broad applicability. Overall, we conclude that the machine learning and BenMap-based methods show high accuracy and reliability in predicting air pollutant concentrations and health impacts, providing a valuable reference for air pollution assessment.

BWO-BiLSTM & CNN composite model for prediction of atmospheric particulate matter mass concentration

Accurate prediction of the mass concentration of atmospheric particulate matter is of great significance for the rational formulation of atmospheric environment management strategies and the study of the spatial and temporal evolution of atmospheric pollutants. In order to solve the problems of low prediction accuracy and low efficiency of traditional prediction models, aiming at the nonlinear and stochastic characteristics of atmospheric particulate matter mass concentration changes, a composite prediction model based on Random Forest (RF) feature selection, Beluga Whale Optimization (BWO) algorithm, Convolutional Neural Network (CNN) and Bidirectional Long and Short-Term Storage Memory Neural Network (BiLSTM) is proposed in this paper. In this composite prediction model, the input variables are adjusted and screened through RF algorithm to reduce the network complexity. The weights and thresholds of CNN-BiLSTM are optimized using BWO to improve the prediction accuracy of the model. The publicly mass concentration data and Aerodynamic Particle Size Spectrometer (APS) measurements are used to train and compare with the predicted data. The experimental results indicate that this composite model has better prediction performance and prediction accuracy compared with the traditional single and the combined model. The fitting coefficient (R2) of PM2.5 prediction using publicly data and APS data can reach 0.8842 and 0.9762, respectively. The R2 for the prediction of PM10 using publicly data and APS data can reach 0.8635 and 0.976, respectively. It indicates that the model proposed in this paper has better generalization and robustness.

A Graph Attention Recurrent Neural Network Model for PM2.5 Prediction: A Case Study in China from 2015 to 2022

Accurately predicting PM2.5 is a crucial task for protecting public health and making policy decisions. In the meanwhile, it is also a challenging task, given the complex spatio-temporal patterns of PM2.5 concentrations. Recently, the utilization of graph neural network (GNN) models has emerged as a promising approach, demonstrating significant advantages in capturing the spatial and temporal dependencies associated with PM2.5 concentrations. In this work, we collected a comprehensive dataset spanning 308 cities in China, encompassing data on seven pollutants as well as meteorological variables from January 2015 to September 2022. To effectively predict the PM2.5 concentrations, we propose a graph attention recurrent neural network (GARNN) model by taking into account both meteorological and geographical information. Extensive experiments validated the efficiency of the proposed GARNN model, revealing its superior performance compared to other existing methods in terms of predictive capabilities. This study contributes to advancing the understanding and prediction of PM2.5 concentrations, providing a valuable tool for addressing environmental challenges.

Prediction of PM2.5 Concentration Based on Deep Learning, Multi-Objective Optimization, and Ensemble Forecast

Accurate and stable prediction of atmospheric PM2.5 concentrations is crucial for air pollution prevention and control. Existing studies usually rely on a single model or use a single evaluation criterion in multi-model ensemble weighted forecasts, neglecting the dual needs for accuracy and stability in PM2.5 forecast. In this study, a novel ensemble forecast model is proposed that overcomes these drawbacks by simultaneously taking into account both forecast accuracy and stability. Specifically, four advanced deep learning models—Long Short-Term Memory Network (LSTM), Graph Convolutional Network (GCN), Transformer, and Graph Sample and Aggregation Network (GraphSAGE)—are firstly introduced. And then, two combined models are constructed as predictors, namely LSTM–GCN and Transformer–GraphSAGE. Finally, a combined weighting strategy is adopted to assign weights to these two combined models using a multi-objective optimization algorithm (MOO), so as to carry out more accurate and stable predictions. The experiments are conducted on the dataset from 36 air quality monitoring stations in Beijing, and results show that the proposed model achieves more accurate and stable predictions than other benchmark models. It is hoped that this proposed ensemble forecast model will provide effective support for PM2.5 pollution forecast and early warning in the future.

A hybrid model for enhanced forecasting of PM2.5 spatiotemporal concentrations with high resolution and accuracy

Forecasting concentrations of PM2.5 is important due to its known impacts on public health and environment. However, PM2.5 concentrations can vary significantly over short distances and time, which can be influenced by local emissions and short-term weather patterns. This spatiotemporal variability makes accurate PM2.5 forecasting an inherently complex and challenging task. This study presented novel methodologies for short-term PM2.5 concentration forecast by combining the atmospheric chemistry transport model Community Multiscale Air Quality Modeling System (CMAQ) with data-driven machine learning methods, namely long short-term memory (LSTM) and random forest (RF) models. The combined model system forecast PM2.5 with 1 h, 1km × 1 km spatiotemporal resolution. The LSTM system forecast time-dependent PM2.5 concentrations at observation sites with a maximum root mean square error (RMSE) of 3.66 μg/m3 for 1-hr forecast and 23.75 μg/m3 for 72-hr forecast, leveraging results obtained from the atmospheric transport model with RMSE of 45.81 μg/m3. Wavelet transform in the LSTM system allowed learning and prediction of PM2.5 concentrations at different frequencies, capturing temporal variability of PM2.5 at various time scales. The RF model predicted distributions of PM2.5 concentrations by learning LSTM results and integrating crucial features such as CMAQ results, meteorological and topographical information. The feature significance of CMAQ results was the highest among the input features in RF models. Overall, the hybrid model could help with managing and mitigating the adverse effects of air pollution by enabling informed decision-making at the individual, community and policy levels.

Predicting ambient PM2.5 concentrations via time series models in Anhui Province, China.

Due to rapid expansion in the global economy and industrialization, PM2.5 (particles smaller than 2.5µm in aerodynamic diameter) pollution has become a key environmental issue. The public health and social development directly affected by high PM2.5 levels. In this paper, ambient PM2.5 concentrations along with meteorological data are forecasted using time series models, including random forest (RF), prophet forecasting model (PFM), and autoregressive integrated moving average (ARIMA) in Anhui province, China. The results indicate that the RF model outperformed the PFM and ARIMA in the prediction of PM2.5 concentrations, with cross-validation coefficients of determination R2, RMSE, and MAE values of 0.83, 10.39µg/m3, and 6.83µg/m3, respectively. PFM achieved the average results (R2 = 0.71, RMSE = 13.90µg/m3, and MAE = 9.05µg/m3), while the predicted results by ARIMA are comparatively poorer (R2 = 0.64, RMSE = 15.85µg/m3, and MAE = 10.59µg/m3) than RF and PFM. These findings reveal that the RF model is the most effective method for predicting PM2.5 and can be applied to other regions for new findings.

Application of Doppler sodar in short-term forecasting of PM10 concentration in the air in Krakow (Poland)

Abstract. This paper describes an attempt to use data obtained from sodar (sound detection and ranging) for short-term forecasting of PM10 concentration levels in Krakow. Krakow is one of the most polluted cities in central Europe (CE) in terms of PM10 concentration. This is due to the high municipal emissions. Thanks to intensive corrective actions taken by the city authorities, these are being effectively eliminated, but the unfavourable topographic location of the city limits natural ventilation. The article describes all these conditions, focusing on presenting the method of short-term correction of air quality for the time needed to take quick corrective actions by the city authorities in the event of anticipated exceedances of the permissible values. Based on several years of measurements of the physical properties of the atmosphere with sodar, the authors of the paper suggest that sodar data could be considered for operational use to generate short-term predictions. The proposed method is based on the use of the spectrum, i.e. the set of amplitudes of signals returning to the sodar receiver from the reflection of a single-frequency sound transmission and its characteristic properties depending on the physical state of the atmosphere. Similar spectra were parameterised with a single numerical value using statistical methods. It was found that, in some cases preceding high concentrations of PM10, the spectral parameters had similar values. This made it possible to develop a forecasting method for such concentrations by using data mining to search for conditions in historical data closest to the state of the atmosphere at the time of forecasting. In this part of the study, data from 2017–2018 were used. In the next step, three methods of using the sodar data developed for PM10 prediction were proposed, comparing them with the method without sodar use. The study results were tested on independent material using data concerning the episodes of high concentrations of pollutants from October 2021 to March 2022 in Krakow. The findings were considered to be encouraging, also taking into account the speed and low cost of preparing the forecast.

A hybrid optimization prediction model for PM2.5 based on VMD and deep learning

PM2.5 has caused serious harm to human health and the environment, so it is particularly important to accurately predict PM2.5 concentration. Aiming at the problem that the nonlinear features of PM2.5 data are difficult to be learned accurately, which results in low prediction accuracy, the WOA-VMD-BiLSTM hybrid model is proposed in this paper. This model optimizes the parameters of the variational modal decomposition (VMD) by the Whale Optimization Algorithm (WOA), after which the PM2.5 sequence is broken down into several intrinsic modal function (IMF) using the VMD. Next, the nonlinear and temporal features of each IMF are captured using a bidirectional long short-term memory neural network (BiLSTM). Finally, all features are fused to get the prediction of PM2.5 concentration. According to the experimental findings, in contrast to the most accurate baseline model, the proposed model reduced the values of RMSE by 18.12, 20.17, and 5.36 in 1∼6 h, 7–12 h, and 13–24 h, respectively. In addition, the model can successfully capture the trend of PM2.5 concentration changes in the long-term prediction.

Prediction of PM2.5 with a piecewise affine model considering spatial-temporal correlation

Over the past several decades, several air pollution prevention measures have been developed in response to the growing concern over air pollution. Using models to anticipate air pollution accurately aids in the timely prevention and management of air pollution. However, the spatial-temporal air quality aspects were not properly taken into account during the prior model construction. In this study, the distance correlation coefficient (DC) between measurements made in various monitoring stations is used to identify appropriate correlated monitoring stations. To derive spatial-temporal correlations for modeling, the causality relationship between measurements made in various monitoring stations is analyzed using Transfer Entropy (TE). This work explores the process of identifying a piecewise affine (PWA) model using a larger dataset and suggests a unique hierarchical clustering-based identification technique with model structure selection. This work improves the BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) by introducing Kullback-Leibler (KL) Divergence as the dissimilarity between clusters for handling clusters with arbitrary shapes. The number of clusters is automatically determined using a cluster validity metric. The task is formulated as a sparse optimization problem, and the model structure is selected using parameter estimations. Beijing air quality data is used to demonstrate the method, and the results show that the proposed strategy may produce acceptable forecast performance.

Improving 3-day deterministic air pollution forecasts using machine learning algorithms

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.

Classification of Particulate Matter (PM2.5) Concentrations Using Feature Selection and Machine Learning Strategies

Abstract This research employed machine learning approaches to classify acceptable or non-acceptable particulate matter (PM2.5) concentrations using a dataset that was obtained from the Nairobi expressway road corridor. The dataset contained air quality data, traffic volume, and meteorological data. The Boruta Algorithm (BA) was utilized in conjunction with the Random Forests (RF) classifier to select the most appropriate features from the dataset. The findings of the BA analysis indicated that humidity was the most influential factor in determining air quality. This was closely followed by the variables of ‘day_of_week’ and the volume of traffic bound for Nairobi. The temperature of the site was determined to have a lower significance. The comparison among different machine learning classifiers for the classification of acceptable and unacceptable PM2.5 concentrations revealed that the Extreme Gradient Boosting (XGBoost) classifier displayed superior performance in terms of Sensitivity (0.774), Specificity (0.943), F1-Score (0.833), and AU-ROC (0.874). The Binary Logistic Regression (BLR) model demonstrated comparatively poorer performance in terms of Sensitivity (0.244), Specificity (0.614), F1-Score (0.455), and AU-ROC (0.508) when compared to other ML models. The prediction of PM2.5 has the potential to provide valuable insights to transport policymakers in their deliberations on urban transport policy formulation.

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.

Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR

Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR

Prediction of PM2.5 concentration based on the weighted RF-LSTM model

Prediction of PM2.5 concentration based on the weighted RF-LSTM model

Spatiotemporal graph neural networks for predicting mid-to-long-term PM2.5 concentrations

Predicting the concentration of PM2.5 particles is of critical importance in public health management because their small size enables them to penetrate deep into the lungs and even enter the bloodstream. However, achieving accurate predictions is challenging due to the complexity of the transport and dispersion processes involved, which are influenced by multiple factors, including atmospheric pollutants, meteorological conditions, and geographic features. To address this challenge, we developed a novel framework for PM2.5 prediction that utilizes multiple edges for feature extraction and employs a multi-gated graph neural network for feature calculations. The model utilizes multiple edges, created by combining an atmospheric diffusion coefficient with a PM2.5 similarity metric, to elucidate the complex characteristics of PM2.5 interactions between different monitoring stations. Node features are computed by aggregating connected nodes' features, weighted by these multi-faceted edges. The experimental results demonstrate that the proposed method outperforms conventional time-series prediction models in the mid-to-long-term prediction of PM2.5 concentrations (96 h in advance), with improvements in Root Mean Square Error (RMSE) by 2.613%, Critical Success Index (CSI) by 3.143%, and R-squared (R2) by 5.263%. Using the proposed model, the learning of global features can be achieved and issues related to local dependency can be mitigated.

Prediction of PM2.5 concentration based on the CEEMDAN-RLMD-BiLSTM-LEC model.

Air quality has emerged as a critical concern in recent years, with the concentration of PM2.5 recognized as a vital index for assessing it. The accuracy of predicting PM2.5 concentrations holds significant value for effective air quality monitoring and management. In response to this, a combined model comprising CEEMDAN-RLMD-BiLSTM-LEC has been introduced, analyzed, and compared against various other models. The combined decomposition method effectively underlines the fundamental characteristics of the data compared to individual decomposition techniques. Additionally, local error correction (LEC) efficiently addresses the issue of prediction errors induced by excessive disturbances. The empirical results of nine steps indicate that the combined CEEMDAN-RLMD-BiLSTM-LEC model outperforms single prediction models such as RLMD and CEEMDAN, reducing MAE, RMSE, and SAMPE by 36.16%, 28.63%, 45.27% and 16.31%, 6.15%, 37.76%, respectively. Moreover, the inclusion of LEC in the model further diminishes MAE, RMSE, and SMAPE by 20.69%, 7.15%, and 44.65%, respectively, exhibiting commendable performance in generalization experiments. These findings demonstrate that the combined CEEMDAN-RLMD-BiLSTM-LEC model offers high predictive accuracy and robustness, effectively handling noisy data predictions and severe local variations. With its wide applicability, this model emerges as a potent tool for addressing various related challenges in the field.

Hour-by-Hour Prediction Model of Air Pollutant Concentration Based on EIDW-Informer—A Case Study of Taiyuan

Prediction of air pollutant concentrations is currently one of the most important methods for the prevention and control of urban air pollution in most countries, and accurate and timely prediction of pollutant concentrations is of great significance for urban pollution control. Using Taiyuan, China, as a case study, this study examines how to predict hourly air pollutant concentrations over longer periods of time while ensuring their accuracy. In this paper, an air pollutant concentration prediction method based on improved inverse distance interpolation and Informer model (EIDW-Informer), and hour-by-hour prediction of PM2.5, NO2, and O3 concentrations in Taiyuan, China is carried out. In this study, historical data from seven environmental monitoring stations in Taiyuan City were used to build multidimensional environmental vectors and calculate the similarity between sample points. Then, the missing values in the dataset were interpolated according to the similarity and distance weights, and the long series prediction was performed by Informer. The experimental results show that the EIDW-Informer method has advantages in hour-by-hour prediction compared to LSTM, CNN-LSTM, and Attention-LSTM models, which improves by 20%, 27%, and 43% on 1 h, 8 h, and 72 h time scales, respectively.