Short-term PM2.5 forecasting based on CEEMD-RF in five cities of China

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 2.5 µm 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, 10.39 µg/m3, and 6.83 µg/m3, respectively. PFM achieved the average results (R2 = 0.71, RMSE = 13.90 µg/m3, and MAE = 9.05 µg/m3), while the predicted results by ARIMA are comparatively poorer (R2 = 0.64, RMSE = 15.85 µg/m3, and MAE = 10.59 µg/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.

An Autoregressive-Based Kalman Filter Approach for Daily PM2.5 Concentration Forecasting in Beijing, China

With the acceleration of urbanization, air pollution, especially PM2.5, has seriously affected human health and reduced people's life quality. Accurate PM2.5 prediction is significant for environmental protection authorities to take actions and develop prevention countermeasures. In this article, an adapted Kalman filter (KF) approach is presented to remove the nonlinearity and stochastic uncertainty of time series, suffered by the autoregressive integrated moving average (ARIMA) model. To further improve the accuracy of PM2.5 forecasting, a hybrid model is proposed by introducing an autoregressive (AR) model, where the AR part is used to determine the state-space equation, whereas the KF part is used for state estimation on PM2.5 concentration series. A modified artificial neural network (ANN), called AR-ANN is introduced to compare with the AR-KF model. According to the results, the AR-KF model outperforms the AR-ANN model and the original ARIMA model on the predication accuracy; that is, the AR-ANN obtains 10.85 and 15.45 of mean absolute error and root mean square error, respectively, whereas the ARIMA gains 30.58 and 29.39 on the corresponding metrics. It, therefore, proves that the presented AR-KF model can be adopted for air pollutant concentration prediction.

A spatiotemporal XGBoost model for PM2.5 concentration prediction and its application in Shanghai

This paper innovatively constructed an analytical and forecasting framework to predict PM2.5 concentration levels for 16 municipal districts in Shanghai. By means of XGBoost parameters adjustment, empirical mode decomposition, and model fusion, improvements are made on XGBoost prediction accuracy and stability so that prediction deviation at extreme points can be avoided. The main findings of this paper can be summarized as follows: 1) Compared with the original model, the goodness of fit of the modified XGBoost model on the test set increased by 17 %, and the root mean square error decreased by 28 %; 2) The variation of PM2.5 concentration in Shanghai has a significant seasonal (cyclical) effect, and its fluctuation period is 3 months (a quarter). In winter, the frequency of extreme value points is significantly higher than that in other seasons; 3) In terms of spatial distribution, the PM2.5 concentration in the central city of Shanghai is higher than that in the rural areas, and the PM2.5 concentration gradually decreases from center city to the surrounding areas. The innovation and contribution of this paper can be summarized as follows: 1) EEMD algorithm verified by SSA was used to decompose the original model without reconstructing all subsequences and get the best weighing among each part of the hybrid model by using variable weight assignment; 2) The city was cut into pieces according to administrative districts in avoid of the duplicate analysis when utilizing advised Kriging interpolation; 3) IDW method was applied to verified Kriging interpolation to increase the accuracy; 4) The latitude and longitude were innovatively converted into the arc length of the corresponding spherical surface; 5) Hierarchical analysis method was used to obtain the order of importance among the PM2.5 monitoring stations, which could improve the accuracy and achieve dimension reduction.

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

As the core of pollution prevention and management, accurate PM2.5 concentration prediction is crucial for human survival. However, due to the nonstationarity and nonlinearity of PM2.5 concentration data, the accurate prediction for PM2.5 concentration remains a challenge. In this study, a PM2.5 concentration prediction method using weighted complementary ensemble empirical mode decomposition with adaptive noise (WCEEMDAN) and improved long and short-term memory (ILSTM) neural network is proposed. Firstly, a novel WCEEMDAN method is proposed to correctly identify the non-stationary and non-linear characteristics and divide the PM2.5 sequences into various layers. Through the correlation analysis with PM2.5 data, these sub-layers are given different weights. Secondly, the adaptive mutation particle swarm optimization (AMPSO) algorithm is developed to obtain the main hyperparameters of the long short-term memory network (LSTM) neural network, improving the prediction accuracy of PM2.5 concentration. The optimization convergence speed and accuracy are improved by adjusting the inertia weight and introducing the mutation mechanism to enhance the global optimization ability. Finally, three groups of PM2.5 concentration data are utilized to verify the effectiveness of the proposed model. Compared with other methods, the experimental results demonstrate the superiority of the proposed model. The source code can be downloaded from https://github.com/zhangli190227/WCEENDAM-ILSTM .

Prediction of atmospheric pollutants in urban environment based on coupled deep learning model and sensitivity analysis

Accurate and efficient predictions of pollutants in the atmosphere provide a reliable basis for the scientific management of atmospheric pollution. This study develops a model that combines an attention mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) unit to predict the O₃ and PM_2.5 levels in the atmosphere, as well as an air quality index (AQI). The prediction results given by the proposed model are compared with those from CNN-LSTM and LSTM models as well as random forest and support vector regression models. The proposed model achieves a correlation coefficient between the predicted and observed values of more than 0.90, outperforming the other four models. The model errors are also consistently lower when using the proposed approach. Sobol-based sensitivity analysis is applied to identify the variables that make the greatest contribution to the model prediction results. Taking the COVID-19 outbreak as the time boundary, we find some homology in the interactions among the pollutants and meteorological factors in the atmosphere during different periods. Solar irradiance is the most important factor for O₃, CO is the most important factor for PM_2.5, and particulate matter has the most significant effect on AQI. The key influencing factors are the same over the whole phase and before the COVID-19 outbreak, indicating that the impact of COVID-19 restrictions on AQI gradually stabilized. Removing variables that contribute the least to the prediction results without affecting the model prediction performance improves the modeling efficiency and reduces the computational costs.

A novel hybrid prediction model for PM2.5 concentration based on decomposition ensemble and error correction

PM_2.5 concentration is an important index to measure the degree of air pollution. It is necessary to establish an accurate PM_2.5 concentration prediction system for urban air monitoring and control. Due to the nonlinear characteristics of PM_2.5 concentration, it is difficult to predict it directly. Therefore, a novel hybrid model for PM_2.5 concentration based on improved variational mode decomposition (IVMD), outlier-robust extreme learning machine (ORELM) optimized by hybrid cuckoo search (CS), and chimp optimization algorithm (ChOA), error correction (EC) is proposed named IVMD-ChOACS-ORELM-EC. First of all, an improved VMD based on energy loss coefficient, named IVMD, is proposed. IVMD decomposes the original data to obtain K IMF components. Then, a hybrid optimization algorithm based on ChOA improved by CS is proposed, named ChOACS. The hybrid optimization algorithm is used to optimize ORELM. On this basis, the prediction model ChOACS-ORELM is proposed, and the K IMF components are predicted by ChOACS-ORELM. Finally, the EC model based on decomposition ensemble is established to further improve the prediction accuracy. The PM_2.5 concentration data collected at hourly intervals in Beijing, Shanghai, Shenyang, and Qingdao in China are used as experimental data. The experimental results show that the correlation coefficients between the prediction results and the actual values of the four cities are 0.9999, and the prediction performance of the proposed model is better than that of all comparison models.

PM2.5 concentration prediction based on WD-SA-LSTM-BP model: a case study of Nanjing city

PM_2.5 concentration is an important indicator to measure the concentration of air pollutants, and it is of important social significance and application value to realize accurate prediction of PM_2.5 concentration. To further improve the accuracy of PM_2.5 concentration prediction, this paper proposes a hybrid machine learning model (WD-SA-LSTM-BP model) based on simulated annealing (SA) optimization and wavelet decomposition. Firstly, the wavelet decomposition algorithm was used to realize the multiscale decomposition and single-branch reconstruction of PM_2.5 concentrations to weaken the prediction error caused by time series data. Secondly, the SA optimization method was used to optimize the super-parameters of each machine learning model under each reconstructed component, so as to solve the problem that it is difficult to determine the parameters of machine learning model. Thirdly, the optimized machine learning model was used to predict the PM_2.5 concentration, and the error value was calculated from the actual measured value. Then, the optimized machine learning model was used to predict the error value. Finally, the predicted error value was added to the predicted PM_2.5 concentration to obtain the final predicted PM_2.5 concentration. The study is experimentally validated based on daily PM_2.5 data collected from Nanjing air quality monitoring stations. The experimental results showed that the RMSE and MAE values of the constructed WD-SA-LSTM-BP model were 5.26 and 3.72, respectively, which were superior to those of the WD-LSTM and LSTM models, indicating that the hybrid machine learning model based on SA optimization and wavelet decomposition could better predict the PM_2.5 concentration.

A new hybrid prediction model of PM2.5 concentration based on secondary decomposition and optimized extreme learning machine

As air pollution worsens, the prediction of PM_2.5 concentration becomes increasingly important for public health. This paper proposes a new hybrid prediction model of PM_2.5 concentration based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), amplitude-aware permutation entropy (AAPE), variational mode decomposition improved by marine predators algorithm (MPA-VMD), and extreme learning machine optimized by chimp optimization algorithm (ChOA-ELM), named CEEMDAN-AAPE-MPA-VMD-ChOA-ELM. Firstly, CEEMDAN is used to decompose the original data, and AAPE is used to quantify the complexity of all IMF components. Secondly, MPA-VMD is used to decompose the IMF component with the maximum AAPE. Lastly, ChOA-ELM is used to predict all IMF components, and all prediction results are reconstructed to obtain the final prediction results. The proposed model combines the advantages of secondary decomposition technique, feature analysis, and optimization algorithm, which can predict PM_2.5 concentration accurately. PM_2.5 concentrations at hourly intervals collected from March 1, 2021, to March 31, 2021, in Shanghai and Shenyang, China, are used for experimental study and DM test. The experimental results in Shanghai show that the RMSE, MAE, MAPE, and R² of the proposed model are 1.0676, 0.7685, 0.0181, and 0.9980 respectively, which is better than all comparison models at 90% confidence level. In Shenyang, the RMSE, MAE, MAPE, and R² of the proposed model are 1.4399, 1.1258, 0.0389, and 0.9976, respectively, which is better than all comparison models at 95% confidence level.

Two-stage deep learning hybrid framework based on multi-factor multi-scale and intelligent optimization for air pollutant prediction and early warning

Effective prediction of air pollution concentrations is of great importance to both the physical and mental health of citizens and urban pollution control. As one of the main components of air pollutants, accurate prediction of PM_2.5 can provide a reference for air pollution control and pollution warning. This study proposes an air pollutant prediction and early warning framework, which innovatively combines feature extraction techniques, feature selection methods and intelligent optimization algorithms. First, the PM_2.5 sequence is decomposed into several subsequences using the complete ensemble empirical mode decomposition with adaptive noise, and then the new components of the subsequences with different complexity are reconstructed using fuzzy entropy. Then, the Max-Relevance and Min-Redundancy method is used to select the influencing factors of the different reconstructed components. Then, a two-stage deep learning hybrid framework is constructed to model the prediction and nonlinear integration of the reconstructed components using a long short-term memory artificial neural network optimized by the gray wolf optimization algorithm. Finally, based on the proposed hybrid prediction framework, effective prediction and early warning of air pollutants are achieved. In an empirical study in three cities in China, the prediction accuracy, warning accuracy and prediction stability of the proposed hybrid framework outperformed the other comparative models. The analysis results indicate that the developed hybrid framework can be used as an effective tool for air pollutant prediction and early warning.

Short-term prediction of urban PM2.5 based on a hybrid modified variational mode decomposition and support vector regression model

PM_2.5 (particulate matter with a size/diameter ≤ 2.5 μm) is an important air pollutant that affects human health, especially in urban environments. However, as time-series data of PM_2.5 are non-linear and non-stationary, it is difficult to predict future PM_2.5 distribution and behavior. Therefore, in this paper, we propose a hybrid short-term urban PM_2.5 prediction model based on variational mode decomposition modified by the correntropy criterion, the state transition simulated annealing (STASA) algorithm, and a support vector regression model to overcome the disadvantages of traditional forecasting techniques which consider different environmental factors. Two experiments were performed with the model to assess its effectiveness and predictive ability: in experiment I, we verified the performance of STASA on benchmark functions, while in experiment II, we used PM_2.5 data from different epochs and regions of Beijing to verify its forecasting performance. The experimental results showed that the proposed model is robust and can achieve satisfactory prediction results under different conditions compared with current forecasting techniques.

Double decomposition and optimal combination ensemble learning approach for interval-valued AQI forecasting using streaming data

To forecast possible future environmental risks, numerous models are developed to predict the hourly values or daily averages of air pollutant concentrations using streaming data (a kind of big data collected from the Internet). On the one hand, real-time hourly data is massive and redundant, making it difficult to process. On the other hand, daily averages cannot reflect the fluctuations of air pollutant concentrations throughout the day. Therefore, a double decomposition and optimal combination ensemble learning approach is proposed for interval-valued AQI (air quality index) forecasting in this paper. In the first decomposition, considering the strong seasonal representation of AQI, the original data of each year is decomposed into four seasonal subseries on the basis of the Chinese calendar. Subsequently, we reconstruct the data of the same season in different years to get a new seasonal series to reduce the interference of seasonal changes on AQI forecasting. In the second decomposition, due to the nonlinearity and irregularity of interval-valued AQI time series, BEMD (bivariate empirical mode decomposition) is employed to decompose the interval-valued signals into a finite number of complex-valued IMF (intrinsic mode function) components and one complex-valued residue component with different frequencies to reduce the complexity of interval times series. Interval multilayer perceptron (iMLP) is utilized to model the lower bound and the upper bound simultaneously of the total components to obtain the corresponding forecasting results, which are merged to produce the final interval-valued output by an optimal combination ensemble method. Empirical study results show that the proposed model with different datasets and different forecasting horizons is significantly better than other considered models for its superior forecasting performances.