A balanced social LSTM for PM2.5 concentration prediction based on local spatiotemporal correlation

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.

Smart solutions for urban health risk assessment: A PM2.5 monitoring system incorporating spatiotemporal long-short term graph convolutional network

Current spatial-temporal early warning systems aim to predict outdoor air quality in urban areas either at short or long temporal horizons. These systems implemented architectures without considering the geographical distribution of each air quality monitoring station, increasing the uncertainty of the forecasting framework. This study developed an integrated spatiotemporal forecasting architecture incorporating an extensive air quality PM_2.5 monitoring network and simultaneously forecasts PM_2.5 concentrations at all locations, allowing the monitoring of the health risk associated with exposure to these levels. First, this study uses a graph convolutional layer to incorporate the spatial relationship of the neighboring stations at their current state with real-time measurements. Then, it is coupled to a deep learning temporal model to form the long- and short-term time-series graph convolutional network (LSTGraphNet) model, anticipating high pollutant concentration events. This work tested the proposed model with a case study of an existing ambient air quality monitoring network in South Korea. LSTGraphNet model showed prediction performances of PM_2.5 at multiple monitoring stations with a mean absolute error (MAE) of 1.82 μg/m³, 4.46 μg/m³, and 4.87 μg/m³ for forecasting horizons of one, three, and 6 h ahead, respectively. Compared to conventional sequential models, this architecture was superior among the state-of-the-art baselines, where the MAE decreased to 41%, respectively. The results of the study showed that the proposed architecture was superior to conventional sequential models and could be used as a tool for decision-making in smart cities by revealing hotspots of higher and lower PM_2.5 concentrations in the long term.

VAR-tree model based spatio-temporal characterization and prediction of O3 concentration in China

Ozone (O₃) pollution in the atmosphere is getting worse in many cities. In order to improve the accuracy of O₃ prediction and obtain the spatial distribution of O₃ concentration over a continuous period of time, this paper proposes a VAR-XGBoost model based on Vector autoregression (VAR), Kriging method and XGBoost (Extreme Gradient Boosting). China is used as an example and its spatial distribution of O₃ is simulated. In this paper, the O₃ concentration data of the monitoring sites in China are obtained, and then a spatial prediction method of O₃ mass concentration based on the VAR-XGBoost model is established, and finnally its influencing factors are analyzed. This paper concludes that O₃ features the highest correlation with PM_2.5 and the lowest correlation with SO₂. Among the measurement factors, wind speed and temperature are the most important factors affecting O₃ pollution, which are positively correlated to O₃ pollution. In addition, precipitation is negatively correlated with 8-hour ozone concentration. In this paper, the performance of the VAR-XGBoost model is evaluated based on the ten-fold cross-validation method of sample, site and time, and a comparison with the results of XGBoost, CatBoost (categorical boosting), ExtraTrees, GBDT (gradient boosting decision tree), AdaBoost (adaptive boosting), RF (random forest), Decision tree, and LightGBM (light gradient boosting machine) models is conducted. The result shows that the prediction accuracy of the VAR-XGBoost model is better than other models. The seasonal and annual average R² reaches 0.94 (spring), 0.93 (summer), 0.92 (autumn), 0.93 (winter), and 0.95 (average from 2016 to 2021). The data show that the applicability of the VAR-XGBoost model in simulating the spatial distribution of O₃ concentrations in China performs well. The spatial distribution of O₃ concentrations in the Chinese region shows an obvious feature of high in the east and low in the west, and the spatial distribution is strongly influenced by topographical factors. The mean concentration is clearly low in winter and high in summer within a season. The results of this study can provide a scientific basis for the prevention and control of regional O₃ pollution in China, and can also provide new ideas for the acquisition of data on the spatial distribution of O₃ concentrations within cities.

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 .

A new cross-domain prediction model of air pollutant concentration based on secure federated learning and optimized LSTM neural network

As air pollution worsens, the fast prediction of air pollutant concentration becomes increasingly important for public health. This paper proposes a new cross-domain prediction model of air pollutant concentration based on federated learning (FL), differential privacy laplace mechanism (DPLA) and long and short-term memory network optimized by sparrow search algorithm (SSA-LSTM), named FL-DPLA-SSA-LSTM. Firstly, with FL, SSA-LSTM is used as local training model for each city and predicts air pollutant concentration. Secondly, DPLA is used to add noise to the local model parameters, which can protect local data security. Then, the global model is updated by using the federated averaging algorithm (FedAvg). Lastly, FL is used to share global model for all cities, which can safely and quickly cross-domain predict air pollutant concentration. For data set, it is taken from hourly air pollutants and meteorological data from 12 cities in the Fenhe River and Weihe River Plains in China in 2020. The experimental results show that the prediction performance of the proposed model is significantly better than all comparison models. FedAvg updating with local model parameters with DPLA noise has little effect on the performance of the global model and even exceeds that of the global model. The calculation time of FL-DPLA-SSA-LSTM model is reduced by 99.95% compared with that of not using FL-DPLA machine learning model. It is proved that the model is high sharing and high safety, which greatly improves the training efficiency and has better generalization ability. It is significant for joint air pollution prevention and control and environmental protection.

Predicting Groundwater Indicator Concentration Based on Long Short-Term Memory Neural Network: A Case Study

Prediction of groundwater quality is an essential step for sustainable utilization of water resources. Most of the related research in the study area focuses on water distribution and rational utilization of resources but lacks results on groundwater quality prediction. Therefore, this paper introduces a prediction model of groundwater quality based on a long short-term memory (LSTM) neural network. Based on groundwater monitoring data from October 2000 to October 2014, five indicators were screened as research objects: TDS, fluoride, nitrate, phosphate, and metasilicate. Considering the seasonality of water quality time series data, the LSTM neural network model was used to predict the groundwater index concentrations in the dry and rainy periods. The results suggest the model has high accuracy and can be used to predict groundwater quality. The mean absolute errors (MAEs) of these parameters are, respectively, 0.21, 0.20, 0.17, 0.17, and 0.20. The root mean square errors (RMSEs) are 0.31, 0.29, 0.28, 0.27, and 0.31, respectively. People can be given early warnings and take measures according to the forecast situation. It provides a reference for groundwater management and sustainable utilization in the study area in the future and also provides a new idea for coastal cities with similar hydrogeological conditions.

A Spatial-Temporal Causal Convolution Network Framework for Accurate and Fine-Grained PM2.5 Concentration Prediction

Accurate and fine-grained prediction of PM_2.5 concentration is of great significance for air quality control and human physical and mental health. Traditional approaches, such as time series, recurrent neural networks (RNNs) or graph convolutional networks (GCNs), cannot effectively integrate spatial-temporal and meteorological factors and manage dynamic edge relationships among scattered monitoring stations. In this paper, a spatial-temporal causal convolution network framework, ST-CCN-PM_2.5, is proposed. Both the spatial effects of multi-source air pollutants and meteorological factors are considered via spatial attention mechanism. Time-dependent features in causal convolution networks are extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-PM_2.5 are tuned by Bayesian optimization. Haikou air monitoring station data are employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results include the following points: (1) For a single station, the RMSE, MAE and R² values of ST-CCN-PM_2.5 decreased by 27.05%, 10.38% and 3.56% on average, respectively. (2) For all stations, ST-CCN-PM_2.5 achieve the best performance in win-tie-loss experiments. The numbers of winning stations are 68, 63, and 64 out of 95 stations in RMSE (MSE), MAE, and R², respectively. In addition, the mean MSE, RMSE and MAE of ST-CCN-PM_2.5 are 4.94, 2.17 and 1.31, respectively, and the R² value is 0.92. (3) Shapley analysis shows wind speed is the most influencing factor in fine-grained PM_2.5 concentration prediction. The effects of CO and temperature on PM_2.5 prediction are moderately significant. Friedman test under different resampling further confirms the advantage of ST-CCN-PM_2.5. The ST-CCN-PM_2.5 provides a promising direction for fine-grained PM_2.5 prediction.

Forecasting Fine Particulate Matter Concentrations by In-Depth Learning Model According to Random Forest and Bilateral Long- and Short-Term Memory Neural Networks

Accurate prediction of fine particulate matter concentration in the future is important for human health due to the necessity of an early warning system. Generally, deep learning methods, when widely used, perform better in forecasting the concentration of PM2.5. However, the source information is limited, and the dynamic process is uncertain. The method of predicting short-term (3 h) and long-term trends has not been achieved. In order to deal with the issue, the research employed a novel mixed forecasting model by coupling the random forest (RF) variable selection and bidirectional long- and short-term memory (BiLSTM) neural net in order to forecast concentrations of PM2.5/0~12 h. Consequently, the average absolute percentage error of 1, 6, and 12 h shows that the PM2.5 concentration prediction is 3.73, 9.33, and 12.68 μg/m3 for Beijing, 1.33, 3.38, and 4.60 μg/m3 for Guangzhou, 1.37, 4.19, and 6.35 μg/m3 for Xi’an, and 2.20, 7.75, and 10.07 μg/m3 for Shenyang, respectively. Moreover, the results show that the suggested mixed model is an advanced method that can offer high accuracy of PM2.5 concentrations from 1 to 12 h post.

Fine-Grained Individual Air Quality Index (IAQI) Prediction Based on Spatial-Temporal Causal Convolution Network: A Case Study of Shanghai

Accurate and fine-grained individual air quality index (IAQI) prediction is the basis of air quality index (AQI), which is of great significance for air quality control and human health. Traditional approaches, such as time series, recurrent neural network or graph convolutional network, cannot effectively integrate spatial-temporal and meteorological factors and manage the dynamic edge relationship among scattered monitoring stations. In this paper, a ST-CCN-IAQI model is proposed based on spatial-temporal causal convolution networks. Both the spatial effects of multi-source air pollutants and meteorological factors were considered via spatial attention mechanism. Time-dependent features in the causal convolution network were extracted by stacked dilated convolution and time attention. All the hyper-parameters in ST-CCN-IAQI were tuned by Bayesian optimization. Shanghai air monitoring station data were employed with a series of baselines (AR, MA, ARMA, ANN, SVR, GRU, LSTM and ST-GCN). Final results showed that: (1) For a single station, the RMSE and MAE values of ST-CCN-IAQI were 9.873 and 7.469, decreasing by 24.95% and 16.87% on average, respectively. R2 was 0.917, with an average 5.69% improvement; (2) For all nine stations, the mean RMSE and MAE of ST-CCN-IAQI were 9.849 and 7.527, respectively, and the R2 value was 0.906. (3) Shapley analysis showed PM10, humidity and NO2 were the most influencing factors in ST-CCN-IAQI. The Friedman test, under different resampling, further confirmed the advantage of ST-CCN-IAQI. The ST-CCN-IAQI provides a promising direction for fine-grained IAQI prediction.

Spatio-Temporal Characteristics of PM2.5 Concentrations in China Based on Multiple Sources of Data and LUR-GBM during 2016–2021

Fine particulate matter (PM2.5) has a continuing impact on the environment, climate change and human health. In order to improve the accuracy of PM2.5 estimation and obtain a continuous spatial distribution of PM2.5 concentration, this paper proposes a LUR-GBM model based on land-use regression (LUR), the Kriging method and LightGBM (light gradient boosting machine). Firstly, this study modelled the spatial distribution of PM2.5 in the Chinese region by obtaining PM2.5 concentration data from monitoring stations in the Chinese study region and established a PM2.5 mass concentration estimation method based on the LUR-GBM model by combining data on land use type, meteorology, topography, vegetation index, population density, traffic and pollution sources. Secondly, the performance of the LUR-GBM model was evaluated by a ten-fold cross-validation method based on samples, stations and time. Finally, the results of the model proposed in this paper are compared with those of the back propagation neural network (BPNN), deep neural network (DNN), random forest (RF), XGBoost and LightGBM models. The results show that the prediction accuracy of the LUR-GBM model is better than other models, with the R2 of the model reaching 0.964 (spring), 0.91 (summer), 0.967 (autumn), 0.98 (winter) and 0.976 (average for 2016–2021) for each season and annual average, respectively. It can be seen that the LUR-GBM model has good applicability in simulating the spatial distribution of PM2.5 concentrations in China. The spatial distribution of PM2.5 concentrations in the Chinese region shows a clear characteristic of high in the east and low in the west, and the spatial distribution is strongly influenced by topographical factors. The seasonal variation in mean concentration values is marked by low summer and high winter values. The results of this study can provide a scientific basis for the prevention and control of regional PM2.5 pollution in China and can also provide new ideas for the acquisition of data on the spatial distribution of PM2.5 concentrations within cities.