PM2.5 concentration modeling and prediction by using temperature-based deep belief network

Improved PM2.5 prediction with spatio-temporal feature extraction and chemical components: The RCG-attention model

Deep learning models are widely used for PM2.5 prediction. However, neglecting temporal and spatial characteristics leads to low prediction accuracy. In this work, a new deep learning model (RCG - Attention model) was developed, which combines the residual neural network (ResNet) and the convolution gated recurrent network (ConvGRU) and is applied to extract the spatio - temporal features for predicting PM2.5 concentration over the subsequent 24 h. The ResNet extracts the spatial distribution features of pollutants, and the ConvGRU extracts temporal features. The spatial and temporal features are fused by the multi - head attention mechanism to obtain multi - dimensional features. These features are finally fed into a series of fully connected layers to predict the future results. Incorporating these chemical components enhances the scientific validity of the dataset and strengthens the inherent logical connections among variables. The Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and R - squared (R2) results indicate that the prediction performance of the RCG - Attention model surpasses that of other baseline models. The model demonstrates superior prediction performance across multiple monitoring stations, suggesting robust generalization capabilities and adaptability for various regions in one city. The SHAP results show that PM10, NO2, RH, NO3-, OC and NH4+ are significant influencing features. The RCG - Attention model provides a comprehensive solution for PM2.5 concentration prediction by integrating spatial and temporal feature extraction with chemical components.

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.

Daily PM2.5 concentration prediction based on variational modal decomposition and deep learning for multi-site temporal and spatial fusion of meteorological factors

Air pollution, particularly PM2.5, has long been a critical concern for the atmospheric environment. Accurately predicting daily PM2.5 concentrations is crucial for both environmental protection and public health. This study introduces a new hybrid model within the "Decomposition-Prediction-Integration" (DPI) framework, which combines variational modal decomposition (VMD), causal convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and attention mechanism (AM), named as VCBA, for spatio-temporal fusion of multi-site data to forecast daily PM2.5 concentrations in a city. The approach involves integrating air quality data from the target site with data from neighboring sites, applying mathematical techniques for dimensionality reduction, decomposing PM2.5 concentration data using VMD, and utilizing Causal CNN and BiLSTM models with an attention mechanism to enhance performance. The final prediction results are obtained through linear aggregation. Experimental results demonstrate that the VCBA model performs exceptionally well in predicting daily PM2.5 concentrations at various stations in Taiyuan City, Shanxi Province, China. Evaluation metrics such as RMSE, MAE, and R2 are reported as 2.556, 1.998, and 0.973, respectively. Compared to traditional methods, this approach offers higher prediction accuracy and stronger spatio-temporal modeling capabilities, providing an effective solution for accurate PM2.5 daily concentration prediction.

Spatio-temporal fusion of meteorological factors for multi-site PM2.5 prediction: A deep learning and time-variant graph approach

In the field of environmental science, traditional methods for predicting PM2.5 concentrations primarily focus on singular temporal or spatial dimensions. This approach presents certain limitations when it comes to deeply mining the joint influence of multiple monitoring sites and their inherent connections with meteorological factors. To address this issue, we introduce an innovative deep-learning-based multi-graph model using Beijing as the study case. This model consists of two key modules: firstly, the 'Meteorological Factor Spatio-Temporal Feature Extraction Module'. This module deeply integrates spatio-temporal features of hourly meteorological data by employing Graph Convolutional Networks (GCN) and Long Short-Term Memory (LSTM) for spatial and temporal encoding respectively. Subsequently, through an attention mechanism, it retrieves a feature tensor associated with air pollutants. Secondly, these features are amalgamated with PM2.5 concentration values, allowing the 'PM2.5 Concentration Prediction Module' to predict with enhanced accuracy the joint influence across multiple monitoring sites. Our model exhibits significant advantages over traditional methods in processing the joint impact of multiple sites and their associated meteorological factors. By providing new perspectives and tools for the in-depth understanding of urban air pollutant distribution and optimization of air quality management, this model propels us towards a more comprehensive approach in tackling air pollution issues.

PEPNet: A barotropic primitive equations-based network for wind speed prediction

In wind speed prediction technologies, deep learning-based methods have achieved promising advantages. However, most existing methods focus on learning implicit knowledge in a data-driven manner but neglect some explicit knowledge from the physical theory of meteorological dynamics, failing to make stable and long-term predictions. In this paper, we explore introducing explicit physical knowledge into neural networks and propose Physical Equations Predictive Network (PEPNet) for multi-step wind speed predictions. In PEPNet, a new neural block called the Augmented Neural Barotropic Equations (ANBE) block is designed as its key component, which aims to capture the wind dynamics by combining barotropic primitive equations and deep neural networks. Specifically, the ANBE block adopts a two-branch structure to model wind dynamics, where one branch is physic-based and the other is data-driven-based. The physic-based branch constructs temporal partial derivatives of meteorological elements (including u-component wind, v-component wind, and geopotential height) in a new Neural Barotropic Equations Unit (NBEU). The NBEU is developed based on the barotropic primitive equations mode in numerical weather prediction (NWP). Besides, considering that the barotropic primitive mode is a crude assumption of atmospheric motion, another data-driven-based branch is developed in the ANBE block, which aims at capturing meteorological dynamics beyond barotropic primitive equations. Finally, the PEPNet follows a time-variant structure to enhance the model's capability to capture wind dynamics over time. To evaluate the predictive performance of PEPNet, we have conducted several experiments on two real-world datasets. Experimental results show that the proposed method outperforms the state-of-the-art techniques and achieve optimal performance.

The importance of data splitting in combined NOx concentration modelling

The polluted air breathed every day by those living in large conurbations poses a significant risk to their health. Through effective modelling (prediction) of concentrations of pollutants and identification of the factors influencing them, it should be possible to obtain advance information on dangers and to plan and implement measures to reduce them. This work describes two different modelling approaches: based on the NO_x concentration of the previous hour (C&RT models); and based on meteorological factors, traffic flow, and past (up to two previous hours) NO_x and NO₂ concentrations (CA models). For each approach, three alternative machine learning methods were applied: artificial neutral network (ANN), random forest (RF), and support vector regression (SVR). The best fits were obtained for the models using ANN and RF (MAPE values in the range 18.3-18.5 %). Poorer fits were found for the SVR models (MAPE equal to 23.4 % for the C&RT approach and 29.3 % for CA). No significant preferences were identified between the C&RT and CA approaches (based on various goodness-of-fit measures). The choice should be determined by the purposes for which the forecast is to be used.

WDMNet: Modeling diverse variations of regional wind speed for multi-step predictions

Regional wind speed prediction plays an important role in the development of wind power, which is usually recorded in the form of two orthogonal components, namely U-wind and V-wind. The regional wind speed has the characteristics of diverse variations, which are reflected in three aspects: (1) The spatially diverse variations of regional wind speed indicate that wind speed has different dynamic patterns at different positions; (2) The distinct variations between U-wind and V-wind denote that U-wind and V-wind at the same position exhibit different dynamic patterns; (3) The non-stationary variations of wind speed represent that the intermittent and chaotic nature of wind speed. In this paper, we propose a novel framework named Wind Dynamics Modeling Network (WDMNet) to model the diverse variations of regional wind speed and make accurate multi-step predictions. To jointly capture the spatially diverse variations and the distinct variations between U-wind and V-wind, WDMNet leverages a new neural block called Involution Gated Recurrent Unit Partial Differential Equation (Inv-GRU-PDE) as its key component. The block adopts involution to model spatially diverse variations and separately constructs hidden driven PDEs of U-wind and V-wind. The construction of PDEs in this block is achieved by a new Involution PDE (InvPDE) layers. Besides, a deep data-driven model is also introduced in Inv-GRU-PDE block as the complement to the constructed hidden PDEs for sufficiently modeling regional wind dynamics. Finally, to effectively capture the non-stationary variations of wind speed, WDMNet follows a time-variant structure for multi-step predictions. Comprehensive experiments have been conducted on two real-world datasets. Experimental results demonstrate the effectiveness and superiority of the proposed method over state-of-the-art techniques.

Soil Heavy Metal Content Prediction Based on a Deep Belief Network and Random Forest Model

In order to extract useful information from X-ray fluorescence (XRF) spectra and establish a high-accuracy prediction model of soil heavy metal contents, a hybrid model combining a deep belief network (DBN) with a tree-based model was proposed. The DBN was first introduced into feature extraction of XRF spectral data, which can obtain deep layer features of spectra. Owing to the strong regression ability of the tree-based model, it can offset the deficiency of DBN in prediction ability so it was used for predicting heavy metal contents based on the extracted features. In order to further improve the performance of the model, the parameters of model can be optimized according to the prediction error, which was completed by sparrow search algorithm and the gird search. The hybrid model was applied to predict the contents of As and Pb based on spectral data of overlapping peaks. It can be obtained that R² of As and Pb reached 0.9884 and 0.9358, the mean square error of As and Pb are as low as 0.0011 and 0.0058, which outperform other commonly used models. That proved the combination of DBN and tree-based model can obtain more accurate prediction results.

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.

Recognition and Analysis of Sports on Mental Health Based on Deep Learning

This paper presents the purpose of sport recognition of mental health for users and analyzes and studies the recognition of mental health by sports based on deep learning. The recognition model of sport mental health state composed of data layer, logic layer and display layer is built. After fusing human health data with deep learning algorithm, the feature of human health mutual information is extracted, the feature into the recognition model of mental health state is inputted, and the recognition results of sport mental health mode after forward and reverse operation are outputted. The recognition data of sports on mental health status are obtained, which correspond to the link flowing through during multi-level transmission, calibrate the multi-level transmission point, and fuse and process the recognition information of sports on mental health status. The experimental results show that the loss value of the research method when analyzing the effect of sports on mental health enhancement is the smallest, the output result is reliable, can effectively improve the body mass index (BMI) of the human body, has the most controllable amount of data, and has good performance.

24-Hour prediction of PM2.5 concentrations by combining empirical mode decomposition and bidirectional long short-term memory neural network

Accurate prediction of the future PM_2.5 concentration is crucial to human health and ecological environmental protection. Nowadays, deep learning methods show advantages in the prediction of PM_2.5 concentration, but few of the studies can achieve accurate prediction of short term (within 6 h) concentration and also catch longer term (6-24 h) change trends. To address this issue, this study constructs a novel hybrid prediction model by combining the empirical mode decomposition (EMD) method, sample entropy (SE) index and bidirectional long and short-term memory neural network (BiLSTM) to predict 0-24 h PM_2.5 concentrations. The experimental results show that the hybrid model has good performance on PM_2.5 prediction with R² = 0.987, RMSE = 2.77 μg/m³ at T + 1 moment and R² = 0.904, RMSE = 7.51 μg/m³ at T + 6 moment. The novel model improves the accuracy on short-term (within 6 h) prediction of PM_2.5 concentrations by at least 50% compared with other single deep learning models. Moreover, it well catches the variation trend of PM_2.5 concentrations after 6 h till 24 h.

Estimation of Ground PM2.5 Concentrations in Pakistan Using Convolutional Neural Network and Multi-Pollutant Satellite Images

During the last few decades, worsening air quality has been diagnosed in many cities around the world. The accurately prediction of air pollutants, particularly, particulate matter 2.5 (PM2.5) is extremely important for environmental management. A Convolutional Neural Network (CNN) P-CNN model is presented in this paper, which uses seven different pollutant satellite images, such as Aerosol index (AER AI), Methane (CH4), Carbon monoxide (CO), Formaldehyde (HCHO), Nitrogen dioxide (NO2), Ozone (O3) and Sulfur dioxide (SO2), as auxiliary variables to estimate daily average PM2.5 concentrations. This study estimates daily average of PM2.5 concentrations in various cities of Pakistan (Islamabad, Lahore, Peshawar and Karachi) by using satellite images. The dataset contains a total of 2562 images from May-2019 to April-2020. We compare and analyze AlexNet, VGG16, ResNet50 and P-CNN model on every dataset. The accuracy of machine learning models was checked with Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The results show that P-CNN is more accurate than other approaches in estimating PM2.5 concentrations from satellite images. This study presents robust model using satellite images, useful for estimating PM2.5 concentrations.

Atmospheric visibility prediction by using the DBN deep learning model and principal component analysis

Measuring and predicting atmospheric visibility is important scientific research that has practical significance for urban air pollution control and public transport safety. We propose a deep learning model that uses principal component analysis and a deep belief network (DBN) to effectively predict atmospheric visibility in short- and long-term sequences. First, using a visibility meter, particle spectrometer, and ground meteorological station data from 2016 to 2019, the principal component analysis method was adopted to determine the influence of atmospheric meteorological and environmental parameters on atmospheric visibility, and an input dataset applicable to atmospheric visibility prediction was constructed. On the basis of deep belief network theory, network structure parameters, including data preprocessing, the number of hidden layers, the number of nodes, and activation and weight functions, are simulated and analyzed. A deep belief network model suitable for atmospheric visibility prediction is established, where a double hidden layer is adopted with the node numbers 70 and 50, and the Z-score method is used for normalization processing with the tanh activation function and Adam optimizer. The average accuracy of atmospheric visibility prediction by the deep belief network reached 0.84, and the coefficient of determination reached 0.96; these results are significantly superior to those of the back propagation (BP) neural network and convolutional neural network (CNN), thus verifying the feasibility and effectiveness of the established deep belief network for predicting atmospheric visibility. Finally, a deep belief network model based on time series is used to predict the short- and long-term trends of atmospheric visibility. The results show that the model has good visibility prediction results within 3 days and has an accuracy rate of 0.79. Covering the visibility change evaluations of different weather conditions, the model demonstrates good practicability. The established deep learning network model provides an effective and feasible technical solution for the prediction of atmospheric meteorology and environmental parameters, which enjoys a wide range of application prospects in highway transportation, navigation, sea and air, meteorology, and environmental research.

Quality Prediction of Fused Deposition Molding Parts Based on Improved Deep Belief Network

Tensile strength, warping degree, and surface roughness are important indicators to evaluate the quality of fused deposition modeling (FDM) parts, and their accurate and stable prediction is helpful to the development of FDM technology. Thus, a quality prediction method of FDM parts based on an optimized deep belief network was proposed. To determine the combination of process parameters that have the greatest influence on the quality of FDM parts, the correlation analysis method was used to screen the key quality factors that affect the quality of FDM parts. Then, we use 10-fold cross-validation and grid search (GS) to determine the optimal hyperparameter combination of the sparse constrained deep belief network (SDBN), propose an adaptive cuckoo search (ACS) algorithm to optimize the weights and biases of the SDBN, and complete the construction of prediction model based on the above work. The results show that compared with DBN, LSTM, RBFNN, and BPNN, the ACS-SDBN model designed in this article can map the complex nonlinear relationship between FDM part quality characteristics and process parameters more effectively, and the CV verification accuracy of the model can reach more than 95.92%. The prediction accuracy can reach more than 96.67%, and the model has higher accuracy and stability.

Design of a Spark Big Data Framework for PM2.5 Air Pollution Forecasting

In recent years, with rapid economic development, air pollution has become extremely serious, causing many negative effects on health, environment and medical costs. PM_2.5 is one of the main components of air pollution. Therefore, it is necessary to know the PM_2.5 air quality in advance for health. Many studies on air quality are based on the government’s official air quality monitoring stations, which cannot be widely deployed due to high cost constraints. Furthermore, the update frequency of government monitoring stations is once an hour, and it is hard to capture short-term PM_2.5 concentration peaks with little warning. Nevertheless, dealing with short-term data with many stations, the volume of data is huge and is calculated, analyzed and predicted in a complex way. This alleviates the high computational requirements of the original predictor, thus making Spark suitable for the considered problem. This study proposes a PM_2.5 instant prediction architecture based on the Spark big data framework to handle the huge data from the LASS community. The Spark big data framework proposed in this study is divided into three modules. It collects real time PM_2.5 data and performs ensemble learning through three machine learning algorithms (Linear Regression, Random Forest, Gradient Boosting Decision Tree) to predict the PM_2.5 concentration value in the next 30 to 180 min with accompanying visualization graph. The experimental results show that our proposed Spark big data ensemble prediction model in next 30-min prediction has the best performance (R² up to 0.96), and the ensemble model has better performance than any single machine learning model. Taiwan has been suffering from a situation of relatively poor air pollution quality for a long time. Air pollutant monitoring data from LASS community can provide a wide broader monitoring, however the data is large and difficult to integrate or analyze. The proposed Spark big data framework system can provide short-term PM_2.5 forecasts and help the decision-maker to take proper action immediately.