A novel spatiotemporal convolutional long short-term neural network for air pollution prediction

Probing the capacity of a spatiotemporal deep learning model for short-term PM2.5 forecasts in a coastal urban area

Accurate forecast of fine particulate matter (PM2.5) is crucial for city air pollution control, yet remains challenging due to the complex urban atmospheric chemical and physical processes. Recently deep learning has been routinely applied for better urban PM2.5 forecasts. However, their capacity to represent the spatiotemporal urban atmospheric processes remains underexplored, especially compared with traditional approaches such as chemistry-transport models (CTMs) and shallow statistical methods other than deep learning. Here we probe such urban-scale representation capacity of a spatiotemporal deep learning (STDL) model for 24-hour short-term PM2.5 forecasts at six urban stations in Rizhao, a coastal city in China. Compared with two operational CTMs and three statistical models, the STDL model shows its superiority with improvements in all five evaluation metrics, notably in root mean square error (RMSE) for forecasts at lead times within 12 h with reductions of 49.8 % and 47.8 % respectively. This demonstrates the STDL model's capacity to represent nonlinear small-scale phenomena such as street-level emissions and urban meteorology that are in general not well represented in either CTMs or shallow statistical models. This gain of small-scale representation in forecast performance decreases at increasing lead times, leading to similar RMSEs to the statistical methods (linear shallow representations) at about 12 h and to the CTMs (mesoscale representations) at 24 h. The STDL model performs especially well in winter, when complex urban physical and chemical processes dominate the frequent severe air pollution, and in moisture conditions fostering hygroscopic growth of particles. The DL-based PM2.5 forecasts align with observed trends under various humidity and wind conditions. Such investigation into the potential and limitations of deep learning representation for urban PM2.5 forecasting could hopefully inspire further fusion of distinct representations from CTMs and deep networks to break the conventional limits of short-term PM2.5 forecasts.

Short-term air quality prediction based on EMD-transformer-BiLSTM

Actual acquired air quality time series data are highly volatile and nonstationary, and accurately predicting nonlinear time series data containing complex noise is an ongoing challenge. This paper proposes an air quality prediction method based on empirical mode decomposition (EMD), a transformer and a bidirectional long short-term memory neural network (BiLSTM), which is good at addressing the ultrashort-term prediction of nonlinear time-series data and shows good performance for application to the air quality dataset of Patna, India (6:00 am on October 3, 2015-0:00 pm on July 1, 2020). The AQI sequence is first decomposed into intrinsic mode functions (IMFs) via EMD and subsequently predicted separately via the improved transformer algorithm based on BiLSTM, where linear prediction is performed for IMFs with simple trends. Finally, the predicted values of each IMF are integrated using BiLSTM to obtain the predicted AQI values. This paper predicts the AQI in Patna with a time window of 5 h, and the RMSE, MAE and MAPE are as low as 5.6853, 2.8230 and 2.23%, respectively. Moreover, the scalability of the proposed model is validated on air quality datasets from several other cities, and the results prove that the proposed hybrid model has high performance and broad application prospects in real-time air quality prediction.

Hybrid deep learning based prediction for water quality of plain watershed

Establishing a highly reliable and accurate water quality prediction model is critical for effective water environment management. However, enhancing the performance of these predictive models continues to pose challenges, especially in the plain watershed with complex hydraulic conditions. This study aims to evaluate the efficacy of three traditional machine learning models versus three deep learning models in predicting the water quality of plain river networks and to develop a novel hybrid deep learning model to further improve prediction accuracy. The performance of the proposed model was assessed under various input feature sets and data temporal frequencies. The findings indicated that deep learning models outperformed traditional machine learning models in handling complex time series data. Long Short-Term Memory (LSTM) models improved the R2 by approximately 29% and lowered the Root Mean Square Error (RMSE) by about 48.6% on average. The hybrid Bayes-LSTM-GRU (Gated Recurrent Unit) model significantly enhanced prediction accuracy, reducing the average RMSE by 18.1% compared to the single LSTM model. Models trained on feature-selected datasets exhibited superior performance compared to those trained on original datasets. Higher temporal frequencies of input data generally provide more useful information. However, in datasets with numerous abrupt changes, increasing the temporal interval proves beneficial. Overall, the proposed hybrid deep learning model demonstrates an efficient and cost-effective method for improving water quality prediction performance, showing significant potential for application in managing water quality in plain watershed.

Elevating hourly PM2.5 forecasting in Istanbul, Türkiye: Leveraging ERA5 reanalysis and genetic algorithms in a comparative machine learning model analysis

Rapid urbanization and industrialization have intensified air pollution, posing severe health risks and necessitating accurate PM2.5 predictions for effective urban air quality management. This study distinguishes itself by utilizing high-resolution ERA5 reanalysis data for a grid-based spatial analysis of Istanbul, Türkiye, a densely populated city with diverse pollutant sources. It assesses the predictive accuracy of advanced machine learning (ML) models-Multiple Linear Regression (MLR), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting (LGB), Random Forest (RF), and Nonlinear Autoregressive with Exogenous Inputs (NARX). Notably, it introduces genetic algorithm optimization for the NARX model to enhance its performance. The models were trained on hourly PM2.5 concentrations from twenty monitoring stations across 2020-2021. Istanbul was divided into seven regions based on ERA5 grid distributions to examine PM2.5 spatial variability. Seventeen input variables from ERA5, including meteorological, land cover, and vegetation parameters, were analyzed using the Neighborhood Component Analysis (NCA) method to identify the most predictive variables. Comparative analysis showed that while all models provided valuable insights (RF > LGB > XGB > MLR), the NARX model outperformed them, particularly with the complex dataset used. The NARX model achieved a high R-value (0.89), low RMSE (5.24 μg/m³), and low MAE (2.94 μg/m³). It performed best in autumn and winter, with the highest accuracy in Region-1 (R-value 0.94) and the lowest in Region-5 (R-value 0.75). This study's success in a complex urban setting with limited monitoring underscores the robustness of the NARX model and the methodology's potential for global application in similar urban contexts. By addressing temporal and spatial variability in air quality predictions, this research sets a new benchmark and highlights the importance of advanced data analysis techniques for developing targeted pollution control strategies and public health policies.

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.

Airborne particulate matter measurement and prediction with machine learning techniques

Air quality is a fundamental component of a healthy environment for human beings. Monitoring networks for air pollution have been established in numerous industrial zones. The data collected by the pervasive monitoring devices can be utilized not only for determining the current environmental condition, but also for forecasting it in the near future. This paper considers the applications of different machine learning methods for the prediction of the two most widely used quantities. Particulate matter (PM) with a diameter of 2.5 and 10 µm, respectively. The data are collected via a proprietary monitoring station, designated as the Ecolumn. The Ecolumn monitors a number of key parameters, including temperature, pressure, humidity, PM 1.0, PM 2.5, and PM 10, in a timely manner. The data were employed in the development of multiple models based on selected machine learning methods. The decision tree, random forest, recurrent neural network, and long short-term memory models were employed. Experiments were conducted with varying hyperparameters and network architectures. Different time scales (10 min, 1 h, and 24 h) were examined. The most optimal results were observed for the Long Short-Term Memory algorithm when utilizing the shortest available time spans (shortest averaging times). The decision tree and random forest algorithms demonstrated unexpectedly high performance for long averaging times, exhibiting only a slight decline in accuracy compared to neural networks for shorter averaging times. Recommendations for the potential applicability of the tested methods were formulated.

Quantifying the impacts of Canadian wildfires on regional air pollution networks

Wildfire smoke greatly impacts regional atmospheric systems, causing changes in the behavior of pollution. However, the impacts of wildfire smoke on pollution behavior are not easily quantifiable due to the complex nature of atmospheric systems. Air pollution correlation networks have been used to quantify air pollution behavior during ambient conditions. However, it is unknown how extreme pollution events impact these networks. Therefore, we propose a multidimensional air pollution correlation network framework to quantify the impacts of wildfires on air pollution behavior. The impacts are quantified by comparing two time periods, one during the 2023 Canadian wildfires and one during normal conditions with two complex network types for each period. In this study, the value network represents PM2.5 concentrations and the rate network represents the rate of change of PM2.5 concentrations. Wildfires' impacts on air pollution behavior are captured by structural changes in the networks. The wildfires caused a discontinuous phase transition during percolation in both network types which represents non-random organization of the most significant spatiotemporal correlations. Additionally, wildfires caused changes to the connectivity of stations leading to more interconnected networks with different influential stations. During the wildfire period, highly polluted areas are more likely to form connections in the network, quantified by an 86 % and 19 % increase in the connectivity of the value and rate networks respectively compared to the normal period. In this study, we create novel understandings of the impacts of wildfires on air pollution correlation networks, show how our method can create important insights into air pollution patterns, and discuss potential applications of our methodologies. This study aims to enhance capabilities for wildfire smoke exposure mitigation and response strategies.

Time-sensitive prediction of NO2 concentration in China using an ensemble machine learning model from multi-source data

Nitrogen dioxide (NO2) poses a critical potential risk to environmental quality and public health. A reliable machine learning (ML) forecasting framework will be useful to provide valuable information to support government decision-making. Based on the data from 1609 air quality monitors across China from 2014-2020, this study designed an ensemble ML model by integrating multiple types of spatial-temporal variables and three sub-models for time-sensitive prediction over a wide range. The ensemble ML model incorporates a residual connection to the gated recurrent unit (GRU) network and adopts the advantage of Transformer, extreme gradient boosting (XGBoost) and GRU with residual connection network, resulting in a 4.1%±1.0% lower root mean square error over XGBoost for the test results. The ensemble model shows great prediction performance, with coefficient of determination of 0.91, 0.86, and 0.77 for 1-hr, 3-hr, and 24-hr averages for the test results, respectively. In particular, this model has achieved excellent performance with low spatial uncertainty in Central, East, and North China, the major site-dense zones. Through the interpretability analysis based on the Shapley value for different temporal resolutions, we found that the contribution of atmospheric chemical processes is more important for hourly predictions compared with the daily scale predictions, while the impact of meteorological conditions would be ever-prominent for the latter. Compared with existing models for different spatiotemporal scales, the present model can be implemented at any air quality monitoring station across China to facilitate achieving rapid and dependable forecast of NO2, which will help developing effective control policies.

Improved prediction of hourly PM2.5 concentrations with a long short-term memory and spatio-temporal causal convolutional network deep learning model

Accurate prediction of particulate matter with aerodynamic diameter ≤ 2.5 μm (PM2.5) is important for environmental management and human health protection. In recent years, many efforts have been devoted to develop air quality predictions using the machine learning and deep learning techniques. In this study, we propose a deep learning model for short-term PM2.5 predictions. The salient feature of the proposed model is that the convolution in the model architecture is causal, where the output of a time step is only convolved with components of the same or earlier time step from the previous layer. The model also weighs the spatial correlation between multiple monitoring stations. Through temporal and spatial correlation analysis, relevant information is screened from the monitoring stations with a strong relationship with the target station. Information from the target and related sites is then taken as input and fed into the model. A case study is conducted in Nanjing, China from January 1, 2020 to December 31, 2020. Using historical air quality and meteorological data from nine monitoring stations, the model predicts PM2.5 concentrations for the next hour. The experimental results show that the predicted PM2.5 concentrations are consistent with observation, with correlation coefficient (R2) and Root Mean Squared Error (RMSE) of our model are 0.92 and 6.75 μg/m3. Additionally, to better understand the factors affecting PM2.5 levels in different seasons, a machine learning algorithm based on Principal Component Analysis (PCA) is used to analyze the correlations between PM2.5 and its influencing factors. By identifying the main factors affecting PM2.5 and optimizing the input of the predictive model, the application of PCA in the model further improves the prediction accuracy, with decrease of up to 17.2 % in RMSE and 38.6 % in mean absolute error (MAE). The deep learning model established in this study provide a valuable tool for air quality management and public health protection.

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.

Climate modulation of external forcing factors on air quality change in Eastern China: Implications for PM2.5 seasonal prediction

Meteorological conditions significantly influence the frequency and duration of air pollution events, making the prediction of seasonal variations of PM2.5 concentration crucial for air quality control. This study analyzed the spatiotemporal variations of PM2.5 concentration anomalies over the past 39 years (1980-2018) in winter (November to January) over eastern China based on the empirical orthogonal function (EOF) method. Regression analysis is conducted on external forcing factors such as sea ice, sea temperature, and snow cover in the pre-autumn (September to October) using the time series of the first three modes. Nine key factors were selected, which further led to establishing a model for predicting winter PM2.5 concentration in eastern China using the long short-term memory deep learning algorithm (LSTM). Independent verification revealed that the predicted and observed PM2.5 concentration distributions were consistent, with the absolute value of deviation within 15 μg·m-3 between 2016 and 2018. The correlation coefficients between the predicted and observed values were between 0.42 and 0.93 over eight key cities in the past 10 years (2009-2018). The contribution rates of the nine factors to PM2.5 concentration were calculated to explore their impact on PM2.5 concentration during winter. The Arctic sea ice (ASI) was found to be the key contributor to the winter PM2.5 concentration in eastern China. The predictors can be monitored in real time; hence, the model provides a real-time predictive tool, improving the prospects of predicting seasonal PM2.5 pollution, especially in vulnerable regions such as eastern China.

Using neural networks and remote sensing for spatio-temporal prediction of air pollution during the COVID-19 pandemic

The study aims to monitor air pollution in Iranian metropolises using remote sensing, specifically focusing on pollutants such as O3, CH4, NO2, CO2, SO2, CO, and suspended particles (aerosols) in 2001 and 2019. Sentinel 5 satellite images are utilized to prepare maps of each pollutant. The relationship between these pollutants and land surface temperature (LST) is determined using linear regression analysis. Additionally, the study estimates air pollution levels in 2040 using Markov and Cellular Automata (CA)-Markov chains. Furthermore, three neural network models, namely multilayer perceptron (MLP), radial basis function (RBF), and long short-term memory (LSTM), are employed for predicting contamination levels. The results of the research indicate an increase in pollution levels from 2010 to 2019. It is observed that temperature has a strong correlation with contamination levels (R2 = 0.87). The neural network models, particularly RBF and LSTM, demonstrate higher accuracy in predicting pollution with an R2 value of 0.90. The findings highlight the significance of managing industrial towns to minimize pollution, as these areas exhibit both high pollution levels and temperatures. So, the study emphasizes the importance of monitoring air pollution and its correlation with temperature. Remote sensing techniques and advanced prediction models can provide valuable insights for effective pollution management and decision-making processes.

Time series prediction of the chemical components of PM2.5 based on a deep learning model

Modeling-based prediction methods enable rapid, reagent-free air pollution detection based on inexpensive multi-source data than traditional chemical reaction-based detection methods in order to quickly understand the air pollution situation. In this study, a convolutional neural network (CNN) and long and short-term memory (LSTM) neural networks are integrated to create a CNN-LSTM time series prediction model to predict the concentration of PM2.5 and its chemical components (i.e., heavy metals, carbon component, and water-soluble ions) using meteorological data and air pollutants (PM2.5, SO2, NO2, CO, and O3). In the integrated CNN-LSTM model, the CNN uses convolutional and pooling layers to extract features from the data, whereas the powerful nonlinear mapping and learning capabilities of LSTM enable the time series prediction of air pollution. The experimental results showed that the CNN-LSTM exhibited good generalization ability in the prediction of As, Cd, Cr, Cu, Ni, and Zn, with a mean R2 above 0.9. Mean R2 predicted for PM2.5, Pb, Ti, EC, OC, SO42-, and NO3- ranged from 0.85 to 0.9. Shapley value showed that PM2.5, NO2, SO2, and CO had a greater influence on the predicted heavy metal results of the model. Regarding water-soluble ions, the predicted results were dominantly influenced by PM2.5, CO, and humidity. The prediction of the carbon fraction was affected mainly by the PM2.5 concentration. Additionally, several input variables for various components were eliminated without affecting the prediction accuracy of the model, with R2 between 0.70 and 0.84, thereby maximizing modeling efficiency and lowering operational costs. The fully trained model prediction results showed that most predicted components of PM2.5 were lower during January to March 2020 than those in 2018 and 2019. This study provides insight into improving the accuracy of modeling-based detection methods and promotes the development of integrated air pollution monitoring toward a more sustainable direction.

Dioxin emission prediction from a full-scale municipal solid waste incinerator: Deep learning model in time-series input

The immeasurability of real-time dioxin emissions is the principal limitation to controlling and reducing dioxin emissions in municipal solid waste incineration (MSWI). Existing methods for dioxin emissions prediction are based on machine learning with inadequate dioxin datasets. In this study, the deep learning models are trained through larger online dioxin emissions data from a waste incinerator to predict real-time dioxin emissions. First, data are collected and the operating data are preprocessed. Then, the dioxin emission prediction performance of the machine learning and deep learning models, including long short-term memory (LSTM) and convolutional neural networks (CNN), with normal input and time-series input are compared. We evaluate the applicability of each model and find that the performance of the deep learning models (LSTM and CNN) has improved by 36.5% and 30.4%, respectively, in terms of the mean square error (MSE) with the time-series input. Moreover, through feature analysis, we find that temperature, airflow, and time dimension are considerable for dioxin prediction. The results are meaningful for optimizing the control of dioxins from MSWI.

Multistation collaborative prediction of air pollutants based on the CNN-BiLSTM model

The development of industry has led to serious air pollution problems. It is very important to establish high-precision and high-performance air quality prediction models and take corresponding control measures. In this paper, based on 4 years of air quality and meteorological data from Tianjin, China, the relationships between various meteorological factors and air pollutant concentrations are analyzed. A hybrid deep learning model consisting of a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) is proposed to predict pollutant concentrations. In addition, a Bayesian optimization algorithm is applied to obtain the optimal combination of hyperparameters for the proposed deep learning model, which enhances the generalization ability of the model. Furthermore, based on air quality data from multiple stations in the region, a multistation collaborative prediction method is designed, and the concept of a strongly correlated station (SCS) is defined. The predictive model is modified using the idea of SCS and is used to predict the pollutant concentration in Tianjin. The coefficient of determination R2 of PM2.5, PM10, SO2, NO2, CO, and O3 are 0.89, 0.84, 0.69, 0.83, 0.92, and 0.84, respectively. The results show that our model is capable of dealing with air pollutant prediction with satisfactory accuracy.

Dynamic graph neural network with adaptive edge attributes for air quality prediction: A case study in China

Air quality prediction is a typical Spatiotemporal modeling problem, which always uses different components to handle spatial and temporal dependencies in complex systems separately. Previous models based on time series analysis and recurrent neural network (RNN) methods have only modeled time series while ignoring spatial information. Previous graph convolution neural networks (GCNs) based methods usually require providing spatial correlation graph structure of observation sites in advance. The correlations among these sites and their strengths are usually calculated using prior information. However, due to the limitations of human cognition, limited prior information cannot reflect the real station-related structure or bring more effective information for accurate prediction. To this end, we propose a novel Dynamic Graph Neural Network with Adaptive Edge Attributes (DGN-AEA) on the message passing network, which generates the adaptive bidirected dynamic graph by learning the edge attributes as model parameters. Unlike prior information to establish edges, our method can obtain adaptive edge information through end-to-end training without any prior information. Thus reducing the complexity of the problem. Besides, the hidden structural information between the stations can be obtained as model by-products, which can help make some subsequent decision-making analyses. Experimental results show that our model received state-of-the-art performance than other baselines.

Cooperative simultaneous inversion of satellite-based real-time PM2.5 and ozone levels using an improved deep learning model with attention mechanism

Ground-level fine particulate matter (PM_2.5) and ozone (O₃) are air pollutants that can pose severe health risks. Surface PM_2.5 and O₃ concentrations can be monitored from satellites, but most retrieval methods retrieve PM_2.5 or O₃ separately and disregard the shared information between the two air pollutants, for example due to common emission sources. Using surface observations across China spanning 2014-2021, we found a strong relationship between PM_2.5 and O₃ with distinct spatiotemporal characteristics. Thus, in this study, we propose a new deep learning model called the Simultaneous Ozone and PM_2.5 inversion deep neural Network (SOPiNet), which allows for daily real-time monitoring and full coverage of PM_2.5 and O₃ simultaneously at a spatial resolution of 5 km. SOPiNet employs the multi-head attention mechanism to better capture the temporal variations in PM_2.5 and O₃ based on previous days' conditions. Applying SOPiNet to MODIS data over China in 2022, using 2019-2021 to construct the network, we found that simultaneous retrievals of PM_2.5 and O₃ improved the performance compared with retrieving them independently: the temporal R² increased from 0.66 to 0.72 for PM_2.5, and from 0.79 to 0.82 for O₃. The results suggest that near-real time satellite-based air quality monitoring can be improved by simultaneous retrieval of different but related pollutants. The codes of SOPiNet and its user guide are freely available online at https://github.com/RegiusQuant/ESIDLM.

A nested machine learning approach to short-term PM2.5 prediction in metropolitan areas using PM2.5 data from different sensor networks

Many predictive models for ambient PM_2.5 concentrations rely on ground observations from a single monitoring network consisting of sparsely distributed sensors. Integrating data from multiple sensor networks for short-term PM_2.5 prediction remains largely unexplored. This paper presents a machine learning approach to predict ambient PM_2.5 concentration levels at any unmonitored location several hours ahead using PM_2.5 observations from nearby monitoring sites from two sensor networks and the location's social and environmental properties. Specifically, this approach first applies a Graph Neural Network and Long Short-Term Memory (GNN-LSTM) network to time series of daily observations from a regulatory monitoring network to make predictions of PM_2.5. This network produces feature vectors to store aggregated daily observations as well as dependency characteristics to predict daily PM_2.5. The daily feature vectors are then set as the precondition of the hourly level learning process. The hourly level learning again uses a GNN-LSTM network based on daily dependency information and hourly observations from a low-cost sensor network to produce spatiotemporal feature vectors capturing the combined dependency described by daily and hourly observations. Finally, the spatiotemporal feature vectors from the hourly learning process and social-environmental data are merged and used as the input to a single-layer Fully Connected (FC) network to output the predicted hourly PM_2.5 concentrations. To demonstrate the benefits of this novel prediction approach, we have conducted a case study using data collected from two sensor networks in Denver, CO, during 2021. Results show that the utilization of data from two sensor networks improves the overall performance of predicting fine-level, short-term PM_2.5 concentrations compared to other baseline models.

72-hour real-time forecasting of ambient PM2.5 by hybrid graph deep neural network with aggregated neighborhood spatiotemporal information

The observation-based air pollution forecasting method has high computational efficiency over traditional numerical models, but a poor ability in long-term (after 6 h) forecasting due to a lack of detailed representation of atmospheric processes associated with the pollution transport. To address such limitation, here we propose a novel real-time air pollution forecasting model that applies a hybrid graph deep neural network (GNN_LSTM) to dynamically capture the spatiotemporal correlations among neighborhood monitoring sites to better represent the physical mechanism of pollutant transport across the space with the graph structure which is established with features (angle, wind speed, and wind direction) of neighborhood sites to quantify their interactions. Such design substantially improves the model performance in 72-hour PM_2.5 forecasting over the whole Beijing-Tianjin-Hebei region (overall R² increases from 0.6 to 0.79), particularly for polluted episodes (PM_2.5 concentration > 55 µg/m³) with pronounced regional transport to be captured by GNN_LSTM model. The inclusion of the AOD feature further enhances the model performance in predicting PM_2.5 over the sites where the AOD can inform additional aloft PM_2.5 pollution features related to regional transport. The importance of neighborhood site (particularly for those in the upwind flow pathway of the target area) features for long-term PM_2.5 forecast is demonstrated by the increased performance in predicting PM_2.5 in the target city (Beijing) with the inclusion of additional 128 neighborhood sites. Moreover, the newly developed GNN_LSTM model also implies the "source"-receptor relationship, as impacts from distanced sites associated with regional transport grow along with the forecasting time (from 0% to 38% in 72 h) following the wind flow. Such results suggest the great potential of GNN_LSTM in long-term air quality forecasting and air pollution prevention.

Real time image-based air quality forecasts using a 3D-CNN approach with an attention mechanism

This study presented an image-based deep learning method to improve the recognition of air quality from images and produce accurate multiple horizon forecasts. The proposed model was designed to incorporate a three-dimensional convolutional neural network (3D-CNN) and the gated recurrent unit (GRU) with an attention mechanism. This study included two novelties; (i) the 3D-CNN model structure was built to extract the hidden features of multiple dimensional datasets and recognize the relevant environmental variables. The GRU was fused to extract the temporal features and improve the structure of fully connected layers. (ii) An attention mechanism was incorporated into this hybrid model to adjust the influence of features and avoid random fluctuations in particulate matter values. The feasibility and reliability of the proposed method were verified through the site images of the Shanghai scenery dataset with relevant air quality monitoring data. Results showed that the proposed method has the highest forecasting accuracy over other state of art methods. The proposed model can provide multi-horizon predictions based on efficient feature extraction and good denoising ability, which is helpful in giving reliable early warning guidelines against air pollutants.

Evolution of neural network to deep learning in prediction of air, water pollution and its Indian context

The scenario of developed and developing countries nowadays is disturbed due to modern living style which affects environment, wildlife and natural habitat. Environmental quality has become or is a subject of major concern as it is responsible for health hazard of mankind and animals. Measurements and prediction of hazardous parameters in different fields of environment is a recent research topic for safety and betterment of people as well as nature. Pollution in nature is an after-effect of civilization. To combat the damage already happened, some processes should be evolved for measurement and prediction of pollution in various fields. Researchers of all over the world are active to find out ways of predicting such hazard. In this paper, application of neural network and deep learning algorithms is chosen for air pollution and water pollution cases. The purpose of this review is to reveal how family of neural network algorithms has applied on these two pollution parameters. In this paper, importance is given on algorithm, and datasets used for air and water pollution as well as the predicted parameters have also been noted for ease of future development. One major concern of this paper is Indian context of air and water pollution research, and the research potential presents in this area using Indian dataset. Another aspect for including both air and water pollutions in one review paper is to generate an idea of artificial neural network and deep learning techniques which can be cross applicable for future purpose.

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.

A hybrid deep learning framework for air quality prediction with spatial autocorrelation during the COVID-19 pandemic

China implemented a strict lockdown policy to prevent the spread of COVID-19 in the worst-affected regions, including Wuhan and Shanghai. This study aims to investigate impact of these lockdowns on air quality index (AQI) using a deep learning framework. In addition to historical pollutant concentrations and meteorological factors, we incorporate social and spatio-temporal influences in the framework. In particular, spatial autocorrelation (SAC), which combines temporal autocorrelation with spatial correlation, is adopted to reflect the influence of neighbouring cities and historical data. Our deep learning analysis obtained the estimates of the lockdown effects as - 25.88 in Wuhan and - 20.47 in Shanghai. The corresponding prediction errors are reduced by about 47% for Wuhan and by 67% for Shanghai, which enables much more reliable AQI forecasts for both cities.

Assessing the Spatiotemporal Characteristics, Factor Importance, and Health Impacts of Air Pollution in Seoul by Integrating Machine Learning into Land-Use Regression Modeling at High Spatiotemporal Resolutions

Previous studies have characterized spatial patterns of air pollution with land-use regression (LUR) models. However, the spatiotemporal characteristics of air pollution, the contribution of various factors to them, and the resultant health impacts have yet to be evaluated comprehensively. This study integrates machine learning (random forest) into LUR modeling (LURF) with intensive evaluations to develop high spatiotemporal resolution prediction models to estimate daily and diurnal PM2.5 and NO2 in Seoul, South Korea, at the spatial resolution of 500 m for a year (2019) and to then evaluate the contribution of driving factors and quantify the resultant premature mortality. Our results show that incorporating the random forest algorithm into our LUR model improves the model performance. Meteorological conditions have a great influence on daily models, while land-use factors play important roles in diurnal models. Our health assessment using dynamic population data estimates that PM2.5 and NO2 pollution, when combined, causes a total of 11,183 (95% CI: 5837-16,354) premature mortalities in Seoul in 2019, of which 64.9% are due to PM2.5, while the remaining are attributable to NO2. The air pollution-attributable health impacts in Seoul are largely caused by cardiovascular diseases including stroke. This study pinpoints the significant spatiotemporal variations and health impact of PM2.5 and NO2 in Seoul, providing essential data for epidemiological research and air quality management.

Multi-step forecast of PM2.5 and PM10 concentrations using convolutional neural network integrated with spatial-temporal attention and residual learning

Accurate and reliable forecasting of PM_2.5 and PM₁₀ concentrations is important to the public to reasonably avoid air pollution and for the governmental policy responses. However, the prediction of PM_2.5 and PM₁₀ concentrations has great uncertainty and instability because of the dynamics of atmospheric flows, making it difficult for a single model to efficiently extract the spatial-temporal dependences. This paper reports a robust forecasting system to achieve accurate multi-step ahead forecasting of PM_2.5 and PM₁₀ concentrations. First, correlation analysis is adopted to screen the spatial information on pollution and meteorology that may facilitate the prediction of concentrations in a target city. Then, a spatial-temporal attention mechanism is used to assign weights to original inputs from both space and time dimensions to enhance the essential information. Subsequently, the residual-based convolutional neural network with feature extraction capabilities is employed to model the refined inputs. Finally, five accuracy metrics and two additional statistical tests are applied to comprehensively assess the performance of the proposed forecasting system. In addition, experimental studies of three major cities in the Yangtze River Delta urban agglomeration region indicate that the forecasting system outperforms various prevalent baseline models in terms of accuracy and stability. Quantitatively, the proposed STA-ResCNN model reduces root mean square error by 5.595 %-15.247 % and 6.827 %-16.906 % for the average of 1-4 h ahead predictions in three major cities of PM_2.5 and PM₁₀, respectively, compared to baseline models. The applicability and generalization of the proposed forecasting system are further verified by the extended applications in the other 23 cities in the entire region. The results prove that the forecasting system is promising in the early warning, regional prevention, and control of air pollution.

Comparison of machine learning and deep learning techniques for the prediction of air pollution: a case study from China

The adverse effect of air pollution has always been a problem for human health. The presence of a high level of air pollutants can cause severe illnesses such as emphysema, chronic obstructive pulmonary disease (COPD), or asthma. Air quality prediction helps us to undertake practical action plans for controlling air pollution. The Air Quality Index (AQI) reflects the degree of concentration of pollutants in a locality. The average AQI was calculated for the various cities in China to understand the annual trends. Furthermore, the air quality index has been predicted for ten major cities across China using five different deep learning techniques, namely, Recurrent Neural Network (RNN), Bidirectional Gated Recurrent unit (Bi-GRU), Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network BiLSTM (CNN-BiLSTM), and Convolutional BiLSTM (Conv1D-BiLSTM). The performance of these models has been compared with a machine learning model, eXtreme Gradient Boosting (XGBoost) to discover the most efficient deep learning model. The results suggest that the machine learning model, XGBoost, outperforms the deep learning models. While Conv1D-BiLSTM and CNN-BiLSTM perform well among the deep learning models in the estimation of the air quality index (AQI), RNN and Bi-GRU are the least performing ones. Thus, both XGBoost and neural network models are capable of capturing the non-linearity present in the dataset with reliable accuracy.

Prediction of Ammonia Concentration in a Pig House Based on Machine Learning Models and Environmental Parameters

Accurately predicting the air quality in a piggery and taking control measures in advance are important issues for pig farm production and local environmental management. In this experiment, the NH₃ concentration in a semi-automatic piggery was studied. First, the random forest algorithm (RF) and Pearson correlation analysis were combined to analyze the environmental parameters, and nine input schemes for the model feature parameters were identified. Three kinds of deep learning and three kinds of conventional machine learning algorithms were applied to the prediction of NH₃ in the piggery. Through comparative experiments, appropriate environmental parameters (CO₂, H₂O, P, and outdoor temperature) and superior algorithms (LSTM and RNN) were selected. On this basis, the PSO algorithm was used to optimize the hyperparameters of the algorithms, and their prediction performance was also evaluated. The results showed that the R² values of PSO-LSTM and PSO-RNN were 0.9487 and 0.9458, respectively. These models had good accuracy when predicting NH₃ concentration in the piggery 0.5 h, 1 h, 1.5 h, and 2 h in advance. This study can provide a reference for the prediction of air concentrations in pig house environments.

Prediction of ground-level ozone by SOM-NARX hybrid neural network based on the correlation of predictors

Current approaches to ozone prediction using hybrid neural networks are numerous but not perfect. Decomposition algorithms ignore the correlation between predictors and ozone, and feature extraction methods rarely select appropriate predictors in terms of correlation, especially for VOCs. Therefore, this study proposes a hybrid neural network model SOM-NARX based on the correlation of predictors. The model is based on MIC to filter predictors, using SOM to make predictors as feature sequences and using NARX networks to make predictions. Data from the JCDZURI site were used for training, testing, and validation. The results show that the correlation of the predictors, classification numbers of SOM, neuron numbers, and delay steps can affect prediction accuracy. Model comparison shows that the SOM-NARX model has 13.82, 10.60, 6.58% and 12.05, 9.44, 68.14% RMSE, MAE, and MAEP in winter and summer, which is smaller than CNN-LSTM, CNN-BiLSTM, CNN-GRU, SOM-LSTM, SOM-BiLSTM, and SOM-GRU.

Forecasting of Beijing PM2.5 with a hybrid ARIMA model based on integrated AIC and improved GS fixed-order methods and seasonal decomposition

Accurate particulate matter 2.5 (PM_2.5) prediction plays a crucial role in the accurate management of air pollution and prevention of respiratory diseases. However, PM_2.5, as a nonlinear time series with great volatility, is difficult to achieve accurate prediction. In this paper, a hybrid autoregressive integrated moving average (ARIMA) model is proposed based on the Augmented Dickey-Fuller test (ADF root test) of annual PM_2.5 data, thus demonstrating the necessity of first-order difference. The new method of using integrated akaike information criterion (AIC) and improved grid search (GS) methods is proposed to avoid the bias caused by using AIC alone to determine the order because the data are not exactly normally distributed. The comprehensive evaluation coefficient (CEC) is used to select the optimal parameter structure of the prediction model by considering multiple evaluation perspectives. The entropy value of the decomposed series is obtained by using range entropy A (RangeEn_A), and the series is reconstructed according to the entropy value, and finally the reconstructed series is predicted. We used Beijing PM_2.5 data for validation and the results showed that the new hybrid ARIMA model improved values of RMSE 99.23%, MAE 99.20%, R² 118.61%, TIC 99.28%, NMAE 98.71%, NMSE 99.97%, OPC 43.13%, MOPC 98.43% and CEC 99.25% compared with the traditional ARIMA model. The results show that the method does greatly improve the prediction performance and provides a convincing tool for policy formulation and governance.

Machine learning and deep learning modeling and simulation for predicting PM2.5 concentrations

Particulate matter (PM) pollution greatly endanger human physical and mental health, and it is of great practical significance to predict PM concentrations accurately. This study measured one-year monitoring data of six main meteorological parameters and PM2.5 concentrations independently at two monitoring sites in central China's Hunan Province. These datasets were then employed to train, validate, and evaluate the proposed extreme gradient boosting (XGBoost) machine learning model and the fully connected neural network deep learning model, respectively. The performances of the two models were compared, analyzed, and optimized through model parameter tuning. The XGBoost model had better prediction ability with R² higher than 0.761 in the complete test dataset. When the complete dataset was divided into stratified sub-sets by daytime-nighttime periods, the value of R² increased to 0.856 in the nighttime test dataset. The feature importance and influential mechanism of meteorological variables on PM2.5 concentrations were analyzed and discussed.

Deep learning hybrid predictions for the amount of municipal solid waste: A case study in Shanghai

It is crucial to precisely estimate the municipal solid waste (MSW) amount for its sustainable management. Owing to learning complicated and abstract features between the factors and target, deep learning has recently emerged as one of the useful tools with potential to predict the MSW amount. Therefore, this study aimed to design an MSW amount predicted system in Shanghai, consisting of Attention (A), one-dimensional convolutional neural network (C), and long short-term memory (L), to investigate the relationship between exogenous series (24 socioeconomics factors and past MSW amount) and target (MSW amount). The role of Attention, 1D-CNN, LSTM played on the MSW predicted amount also have investigated. The results show that attention is crucial for decoding the encoding information, which would improve performance between predicted and known MSW amount (R² in A-L-C, L-A-C, L-C-A was 89.45%, 90.77%, and 95.31%, respectively.). CNN modules appear to be positioned similarly across the MSW predicted system. Finally, R² in L-A-C, A-L-C, and A-C-L was 85.44%, 91.61%, and 89.45%, which suggested that LSTM as an intermediary between CNN and Attention modules seems a wise measure to predict the MSW amount based on the correlation efficiency. In addition, some socioeconomic factors including the average number of people in households and budget revenue may be chosen for the decision-making of MSW management in Shanghai city in the future, according to the weight of neurons in fully connected layers by the visual technology.

Evaluation of data preprocessing and feature selection process for prediction of hourly PM10 concentration using long short-term memory models

Studies have confirmed that PM₁₀, defined as respirable particles with diameters of 10 μm and smaller, has adverse effects on human health and the environment. Various estimation methods are employed to determine the PM₁₀ concentration using historical data on controlling PM₁₀ air pollution, early warning, and protecting public health and the environment. The present study analyses different Long Short-Term Memory (LSTM) models that can predict hourly PM₁₀ concentration. In parallel, the study also investigates the effectiveness of the data preprocessing and feature selection (DPFS) process on the prediction accuracy of the LSTM models. For this purpose, three different LSTM models, namely Vanilla, Bi-Directional, and Stacked, were developed. Then, a comprehensive data preprocessing stage is used to eliminate missing and erroneous data and outliers from real-world raw data, and a feature selection process is applied to extract unnecessary features. The LSTM models consider three air quality parameters, including SO₂, O₃, and CO, and three meteorological factors, including relative humidity, wind direction, and wind speed. The prediction performances of the LSTM models are compared using the RMSE, MAE and R² performance index according to whether DPFS is used in the models or not. As a result, when the DPFS process was applied, the proposed LSTM models achieved high prediction performance and can be used to predict hourly PM₁₀ concentrations. Overall, the DPFS process significantly enhanced the developed LSTM models' prediction performance. Furthermore, the proposed model might be a useful tool for city administrators to make decisions and improve air quality management efforts.

COVID-19 lockdowns and air quality: Evidence from grey spatiotemporal forecasts

This paper proposes a novel grey spatiotemporal model and quantitatively analyzes the spillover and momentum effects of the COVID-19 lockdown policy on the concentration of PM2.5 (particulate matter of diameter less than 2.5 μm) in Wuhan during the COVID-19 pandemic lockdown from 23 January to 8 April 2020 inclusive, and the post-pandemic period from 9 April 2020 to 17 October 2020 inclusive. The results suggest that the stringent lockdowns lead to a reduction in PM2.5 emissions arising from a momentum effect (9.57-18.67%) and a spillover effect (7.07-27.60%).

An integrated 3D CNN-GRU deep learning method for short-term prediction of PM2.5 concentration in urban environment

This study proposes a new model for the spatiotemporal prediction of PM_2.5 concentration at hourly and daily time intervals. It has been constructed on a combination of three-dimensional convolutional neural network and gated recurrent unit (3D CNN-GRU). The performance of the proposed model is boosted by learning spatial patterns from similar air quality (AQ) stations while maintaining long-term temporal dependencies with simultaneous learning and prediction for all stations over different time intervals. 3D CNN-GRU model was applied to air pollution observations, especially PM_2.5 level, collected from several AQ stations across the city of Tehran, the capital of Iran, from 2016 to 2019. It could achieve promising results compared to the methods such as LSTM, GRU, ANN, SVR, and ARIMA, which are recently introduced in the literature; it estimates 84% (R² = 0.84) and 78% (R² = 0.78) of PM_2.5 concentration variations for the next hour and the following day, respectively.

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

Accurate and fine-grained prediction of PM2.5 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-PM2.5, 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-PM2.5 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-PM2.5 decreased by 27.05%, 10.38% and 3.56% on average, respectively. (2) For all stations, ST-CCN-PM2.5 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-PM2.5 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 PM2.5 concentration prediction. The effects of CO and temperature on PM2.5 prediction are moderately significant. Friedman test under different resampling further confirms the advantage of ST-CCN-PM2.5. The ST-CCN-PM2.5 provides a promising direction for fine-grained PM2.5 prediction.

Research on PM2.5 Concentration Prediction Based on the CE-AGA-LSTM Model

The PM2.5 index is an important basis for measuring the degree of air pollution. The accurate prediction of PM2.5 concentration has an important guiding role in air pollution prevention and control. The Pearson Correlation Coefficient (PCC) is a common index used to mine the correlation between meteorological factors and other air pollutants. However, this index cannot be used to mine non-linear correlations, nor can it quantitatively analyze the weight of each related attribute. In order to accurately explore the correlation between meteorological factors and other air pollutants and to achieve an accurate prediction of PM2.5 concentration, this paper proposes a short- and long-time memory (LSTM) network prediction model based on Copula entropy (CE) and the adaptive genetic algorithm (AGA). By calculating CE, the correlation between multiple meteorological factors and various atmospheric pollutants and PM2.5 was analyzed. The correlation of influencing factors was sorted according to the size of the correlation coefficients. The contribution rate of meteorological factors and atmospheric pollutants to PM2.5 concentration was determined, used as the weight of each influencing factor and predicted as the input data of the prediction model. In this paper, a long- and short-term memory network (LSTM) suitable for time series data was selected as the prediction model, while the selection of model parameters was taken into account, and the relevant parameters were sought by an adaptive genetic algorithm (AGA). The air pollutant data and meteorological data of Beijing from 1 January 2016 to 31 December 2016 were selected, and MAE and RMSE were used as evaluation indexes. By comparing the experimental results of the CE-AGA-LSTM with those of other eight prediction models (LR, SVM, RF, ARMA, ST-LSTM, LSTM, CE-LSTM and CE-RNN), we found that among the models, the CE-AGA-LSTM model provided the lowest MAE and RMSE values, i.e., 14.5 and 21.88, respectively. At the same time, the loss rate and accuracy of the CE-AGA-LSTM model were evaluated, and the experimental results verified the validity of the model.

A deep learning approach for Spatio-Temporal forecasting of new cases and new hospital admissions of COVID-19 spread in Reggio Emilia, Northern Italy

Background

Since February 2020, the COVID-19 epidemic has rapidly spread throughout Italy. Some studies showed an association of environmental factors, such as PM₁₀, PM_2.5, NO₂, temperature, relative humidity, wind speed, solar radiation and mobility with the spread of the epidemic.

In this work, we aimed to predict via Deep Learning the real-time transmission of SARS-CoV-2 in the province of Reggio Emilia, Northern Italy, in a grid with a small resolution (12 km × 12 km), including satellite information.

Methods

We focused on the Province of Reggio Emilia, which was severely hit by the first wave of the epidemic. The outcomes included new SARS-CoV-2 infections and COVID-19 hospital admissions. Pollution, meteorological and mobility data were analyzed. The spatial simulation domain included the Province of Reggio Emilia in a grid of 40 cells of (12 km)². We implemented a ConvLSTM, which is a spatio-temporal deep learning approach, to perform a 7-day moving average to forecast the 7th day after. We used as training and validation set the new daily infections and hospital admissions from August 2020 to March 2021. Finally, we assessed the models in terms of Mean Absolute Error (MAE) compared with Mean Observed Value (MOV) and Root Mean Squared Error (RMSE) on data from April to September 2021. We tested the performance of different combinations of input variables to find the best forecast model.

Findings

Daily new cases of infection, mobility and wind speed resulted in being strongly predictive of new COVID-19 hospital admissions (MAE = 2.72 in the Province of Reggio Emilia; MAE = 0.62 in Reggio Emilia city), whereas daily new cases, mobility, solar radiation and PM_2.5 turned out to be the best predictors to forecast new infections, with appropriate time lags.

Interpretation

ConvLSTM achieved good performances in forecasting new SARS-CoV-2 infections and new COVID-19 hospital admissions. The spatio-temporal representation allows borrowing strength from data neighboring to forecast at the level of the square cell (12 km)², getting accurate predictions also at the county level, which is paramount to help optimise the real-time allocation of health care resources during an epidemic emergency.

Modelling and investigating the impacts of climatic variables on ozone concentration in Malaysia using correlation analysis with random forest, decision tree regression, linear regression, and support vector regression

Climate change is generally known to impact ozone concentration globally. However, the intensity varies across regions and countries. Therefore, local studies are essential to accurately assess the correlation of climate change and ozone concentration in different countries. This study investigates the effects of climatic variables on ozone concentration in Malaysia in order to understand the nexus between climate change and ozone concentration. The selected data was obtained from ten (10) air monitoring stations strategically mounted in urban-industrial and residential areas with significant emissions of pollutants. Correlation analysis and four machine learning algorithms (random forest, decision tree regression, linear regression, and support vector regression) were used to analyze ozone and meteorological dataset in the study area. The analysis was carried out during the southwest monsoon due to the rise of ozone in the dry season. The results show a very strong correlation between temperature and ozone. Wind speed also exhibits a moderate to strong correlation with ozone, while relative humidity is negatively correlated. The highest correlation values were obtained at Bukit Rambai, Nilai, Jaya II Perai, Ipoh, Klang and Petaling Jaya. These locations have high industries and are well urbanized. The four machine learning algorithms exhibit high predictive performances, generally ascertaining the predictive accuracy of the climatic variables. The random forest outperformed other algorithms with a very high R² of 0.970, low RMSE of 2.737 and MAE of 1.824, followed by linear regression, support vector regression and decision tree regression, respectively. This study's outcome indicates a linkage between temperature and wind speed with ozone concentration in the study area. An increase of these variables will likely increase the ozone concentration posing threats to lives and the environment. Therefore, this study provides data-driven insights for decision-makers and other stakeholders in ensuring good air quality for sustainable cities and communities. It also serves as a guide for the government for necessary climate actions to reduce the effect of climate change on air pollution and enabling sustainable cities in accordance with the UN's SDGs 13 and 11, respectively.

A BP Neural Network Algorithm for Multimedia Data Monitoring of Air Particulate Matter

In order to study a BP neural network algorithm for air particulate matter data monitoring, firstly, the monitoring data collected by particle sensor using the light scattering method are proposed. Then, based on the improved BP neural network method, the mapping relationship between the actual measured value of the sensor, weather and other influencing factors, and the standard value of the monitoring station is established, and the calibration model of air particulate matter is realized. Finally, through theoretical analysis and experimental comparison, the results show that the model based on BP neural network algorithm has good accuracy and generalization ability in the evaluation of air particulate index, which makes it possible to scientifically and accurately refine the evaluation and management of urban air particulate index. The experimental results show that the air particle calibration model based on the light scattering method and improved BP neural network algorithm is practical and effective.

An air quality index prediction model based on CNN-ILSTM

Air quality index (AQI) is an essential measure of air pollution evaluation, which describes the air pollution degree and its impact on health, so the accurate prediction of AQI is significant. This paper presents an AQI prediction model based on Convolution Neural Networks (CNN) and Improved Long Short-Term Memory (ILSTM), named CNN-ILSTM. ILSTM deletes the output gate in LSTM and improves its input gate and forget gate, and introduces a Conversion Information Module (CIM) to prevent supersaturation in the learning process. ILSTM realizes efficient learning of historical data, improves prediction accuracy, and reduces the training time. CNN extracts the eigenvalues of input data effectively. This paper uses air quality data from 00:00 on January 1, 2017, to 23:00 on June 30, 2021, in Shijiazhuang City, Hebei Province, China, as experimental data sets, and compares this model with eight prediction models: SVR, RFR, MLP, LSTM, GRU, ILSTM, CNN-LSTM, and CNN-GRU to prove the validity and accuracy of CNN-ILSTM prediction model. The experimental results show the MAE of CNN-ILSTM is 8.4134, MSE is 202.1923, R² is 0.9601, and the training time is 85.3 s. In this experiment, the performance of this model performs better than other models.

A Hybrid Spatiotemporal Deep Model Based on CNN and LSTM for Air Pollution Prediction

Nowadays, air pollution is an important problem with negative impacts on human health and on the environment. The air pollution forecast can provide important information to all affected sides, and allows appropriate measures to be taken. In order to address the problems of filling in the missing values in the time series used for air pollution forecasts, the automation of the allocation of optimal subset of input variables, the dependency of the air quality at a particular location on the conditions of the surrounding environment, as well as automation of the model’s optimization, this paper proposes a deep spatiotemporal model based on a 2D convolutional neural network and a long short-term memory network for predicting air pollution. The model utilizes the automatic selection of input variables and the optimization of hyperparameters by a genetic algorithm. A hybrid strategy for missing value imputation is used based on a combination of linear interpolation and a strategy of using the average between the previous value and the average value for the same time in other years. In order to determine the best architecture of the spatiotemporal model, the architecture hyperparameters are optimized by a genetic algorithm with a modified crossover operator for solutions with variable lengths. Additionally, the trained models are included in various ensembles in order to further improve the prediction performance—these include ensembles of models with the same architecture comprising the best architecture obtained by the evolutionary optimization, and ensembles of diverse models comprising the k best models of the evolutionary optimization. The experimental results for the Beijing Multi-Site Air-Quality Data Set show that the proposed spatiotemporal model for air pollution forecasting provides good and consistent prediction results. The comparison of the suggested model with other deep NN models shows satisfactory results, with the best performance according to MAE, based on the experimental results for the station at Wanliu (16.753 ± 0.384). Most of the model architectures obtained by the optimization of the model hyperparameters using the genetic algorithm have one convolutional layer with a small number of kernels and a small kernel size; the convolutional layers are followed by a max-pooling layer, and one or two LSTM layers are utilized with dropout regularization applied to the LSTM layer using small values of p (0.1, 0.2 and 0.3). The utilization of ensembles from the k best trained models further improves the prediction results and surpasses other deep learning models, according to MAE and RMSE metrics. The used hybrid strategy for missing value imputation enhances the results, especially for data with clear seasonality, and produces better MAE compared to the strategy using average values for the same hour of the same day and month in other years. The experimental results also reveal that random searching is a simple and effective strategy for selecting the input variables. Furthermore, the inclusion of spatial information in the model’s input data, based on the local neighborhood data, significantly improves the predictive results obtained with the model. The results obtained demonstrate the benefits of including spatial information from as many surrounding stations as possible, as well as using as much historical information as possible.

Regional Prediction of Ozone and Fine Particulate Matter Using Diffusion Convolutional Recurrent Neural Network

Accurate air quality forecasts can provide data-driven supports for governmental departments to control air pollution and further protect the health of residents. However, existing air quality forecasting models mainly focus on site-specific time series forecasts at a local level, and rarely consider the spatiotemporal relationships among regional monitoring stations. As a novelty, we construct a diffusion convolutional recurrent neural network (DCRNN) model that fully considers the influence of geographic distance and dominant wind direction on the regional variations in air quality through different combinations of directed and undirected graphs. The hourly fine particulate matter (PM_2.5) and ozone data from 123 air quality monitoring stations in the Yangtze River Delta, China are used to evaluate the performance of the DCRNN model in the regional prediction of PM_2.5 and ozone concentrations. Results show that the proposed DCRNN model outperforms the baseline models in prediction accuracy. Compared with the undirected graph model, the directed graph model considering the effects of wind direction performs better in 24 h predictions of pollutant concentrations. In addition, more accurate forecasts of both PM_2.5 and ozone are found at a regional level where monitoring stations are distributed densely rather than sparsely. Therefore, the proposed model can assist environmental researchers to further improve the technologies of air quality forecasts and could also serve as tools for environmental policymakers to implement pollution control measures.

Attention-Based Distributed Deep Learning Model for Air Quality Forecasting

Air quality forecasting has become an essential factor in facilitating sustainable development worldwide. Several countries have implemented monitoring stations to collect air pollution particle data and meteorological information using parameters such as hourly timespans. This research focuses on unravelling a new framework for air quality prediction worldwide and features Busan, South Korea as its model city. The paper proposes the application of an attention-based convolutional BiLSTM autoencoder model. The proposed deep learning model has been trained on a distributed framework, referred to data parallelism, to forecast the intensity of particle pollution (PM2.5 and PM10). The algorithm automatically learns the intrinsic correlation among the particle pollution in different locations. Each location’s meteorological and traffic data is extensively exploited to improve the model’s performance. The model has been trained using air quality particle data and car traffic information. The traffic information is obtained by a device which counts cars passing a specific area through the YOLO algorithm, and then sends the data to a stacked deep autoencoder to be encoded alongside the meteorological data before the final prediction. In addition, multiple one-dimensional CNN layers are used to obtain the local spatial features jointly with a stacked attention-based BiLSTM layer to figure out how air quality particles are correlated in space and time. The evaluation of the new attention-based convolutional BiLSTM autoencoder model was derived from data collected and retrieved from comprehensive experiments conducted in South Korea. The results not only show that the framework outperforms the previous models both on short- and long-term predictions but also indicate that traffic information can improve the accuracy of air quality forecasting. For instance, during PM2.5 prediction, the proposed attention-based model obtained the lowest MAE (5.02 and 22.59, respectively, for short-term and long-term prediction), RMSE (7.48 and 28.02) and SMAPE (17.98 and 39.81) among all the models, which indicates strong accuracy between observed and predicted values. It was also found that the newly proposed model had the lowest average training time compared to the baseline algorithms. Furthermore, the proposed framework was successfully deployed in a cloud server in order to provide future air quality information in real time and when needed.

Self-Powered Wireless Sensor Matrix for Air Pollution Detection with a Neural Predictor

Predicting the status of particulate air pollution is extremely important in terms of preventing possible vascular and lung diseases, improving people’s quality of life and, of course, actively counteracting pollution magnification. Hence, there is great interest in developing methods for pollution prediction. In recent years, the importance of methods based on classical and more advanced neural networks is increasing. However, it is not so simple to determine a good and universal method due to the complexity and multiplicity of measurement data. This paper presents an approach based on Deep Learning networks, which does not use Bayesian sub-predictors. These sub-predictors are used to marginalize the importance of some data part from multisensory platforms. In other words—to filter out noise and mismeasurements before the actual processing with neural networks. The presented results shows the applied data feature extraction method, which is embedded in the proposed algorithm, allows for such feature clustering. It allows for more effective prediction of future air pollution levels (accuracy—92.13%). The prediction results shows that, besides using standard measurements of temperature, humidity, wind parameters and illumination, it is possible to improve the performance of the predictor by including the measurement of traffic noise (Accuracy—94.61%).

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

Reliable prediction for the concentration of PM_2.5 has become a hot topic in pollution prevention. However, the prediction for PM_2.5 concentration remains a challenge, one of the reasons is that current prediction methods do not consider the relevance of PM_2.5 concentration among surrounding areas. In this paper, we propose the assumption that the PM_2.5 concentration has spatial interaction, which includes two parts: 1) The PM_2.5 concentrations observed by adjacent stations usually present relevant trends; 2) Stations with higher PM_2.5 concentration tend to show higher influences on neighboring areas. Based on the spatial interaction assumption, we propose a balanced social long short-term memory (BS-LSTM) neural network for the prediction of PM_2.5 concentration. BS-LSTM is composed of two kernel components: a social-LSTM based prediction model and a new balanced mean squared error (B-MSE) based loss function. On the one hand, to capture the spatiotemporal correlation of the PM_2.5 concentration among adjacent stations, we develop a social-LSTM based model which has advantages in describing the trend information of neighboring locations. On the other hand, considering the unbalanced influence caused by various local pollution levels, we design a new B-MSE loss function to assign different attention to the observation stations. In the experiments, we evaluate the proposed method on two real-world PM_2.5 datasets. The results indicate that BS-LSTM is promising, especially in the case of heavy pollution.