Variational Bayesian Network with Information Interpretability Filtering for Air Quality Forecasting

Air quality plays a vital role in people’s health, and air quality forecasting can assist in decision making for government planning and sustainable development. In contrast, it is challenging to multi-step forecast accurately due to its complex and nonlinear caused by both temporal and spatial dimensions. Deep models, with their ability to model strong nonlinearities, have become the primary methods for air quality forecasting. However, because of the lack of mechanism-based analysis, uninterpretability forecasting makes decisions risky, especially when the government makes decisions. This paper proposes an interpretable variational Bayesian deep learning model with information self-screening for PM2.5 forecasting. Firstly, based on factors related to PM2.5 concentration, e.g., temperature, humidity, wind speed, spatial distribution, etc., an interpretable multivariate data screening structure for PM2.5 forecasting was established to catch as much helpful information as possible. Secondly, the self-screening layer was implanted in the deep learning network to optimize the selection of input variables. Further, following implantation of the screening layer, a variational Bayesian gated recurrent unit (GRU) network was constructed to overcome the complex distribution of PM2.5 and achieve accurate multi-step forecasting. The high accuracy of the proposed method is verified by PM2.5 data in Beijing, China, which provides an effective way, with multiple factors for PM2.5 forecasting determined using deep learning technology.

[1]  Liangliang Cheng,et al.  Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR , 2023, Archives of Environmental Protection.

[2]  P. Chakrabarti,et al.  Deep Spatio-Temporal Graph Network with Self-Optimization for Air Quality Prediction , 2023, Entropy.

[3]  Jie Xie,et al.  Investigation of nearby monitoring station for hourly PM2.5 forecasting using parallel multi-input 1D-CNN-biLSTM , 2022, Expert Syst. Appl..

[4]  Tingli Su,et al.  A Variational Bayesian Deep Network with Data Self-Screening Layer for Massive Time-Series Data Forecasting , 2022, Entropy.

[5]  Ling Xu Separable Newton Recursive Estimation Method Through System Responses Based on Dynamically Discrete Measurements with Increasing Data Length , 2022, International Journal of Control, Automation and Systems.

[6]  Carolina Marchant,et al.  Machine Learning Models to Predict Critical Episodes of Environmental Pollution for PM2.5 and PM10 in Talca, Chile , 2022, Mathematics.

[7]  Hu Senlin,et al.  Including the feature of appropriate adjacent sites improves the PM2.5 concentration prediction with long short-term memory neural network model , 2022, Sustainable Cities and Society.

[8]  G. Ciulla,et al.  An intelligent way to predict the building thermal needs: ANNs and optimization , 2021, Expert Syst. Appl..

[9]  F. Ding,et al.  Separable Synchronous Multi-Innovation Gradient-Based Iterative Signal Modeling From On-Line Measurements , 2022, IEEE Transactions on Instrumentation and Measurement.

[10]  Meihang Li,et al.  Iterative identification methods for a class of bilinear systems by using the particle filtering technique , 2021, International Journal of Adaptive Control and Signal Processing.

[11]  Ling Xu Separable Multi-innovation Newton Iterative Modeling Algorithm for Multi-frequency Signals Based on the Sliding Measurement Window , 2021, Circuits, Systems, and Signal Processing.

[12]  Md. Habibur Rahman,et al.  Forecasting PM2.5 Concentration Using a Single-Dense Layer BiLSTM Method , 2021, Electronics.

[13]  Patricio Perez,et al.  Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks , 2021, Urban Climate.

[14]  Korra Sathya Babu,et al.  Temporal convolutional denoising autoencoder network for air pollution prediction with missing values , 2021, Urban Climate.

[15]  Xue-bo Jin,et al.  Modeling and Analysis of Data-Driven Systems through Computational Neuroscience Wavelet-Deep Optimized Model for Nonlinear Multicomponent Data Forecasting , 2021, Comput. Intell. Neurosci..

[16]  M. Orozco-Alzate,et al.  Hourly Ozone and PM2.5 Prediction Using Meteorological Data – Alternatives for Cities with Limited Pollutant Information , 2021, Aerosol and Air Quality Research.

[17]  Erfu Yang,et al.  Hierarchical gradient- and least squares-based iterative algorithms for input nonlinear output-error systems using the key term separation , 2021, J. Frankl. Inst..

[18]  Baowei Wang,et al.  An air quality forecasting model based on improved convnet and RNN , 2021, Soft Computing.

[19]  Jinxiu Zhu,et al.  An Improved Attention-Based Integrated Deep Neural Network for PM2.5 Concentration Prediction , 2021, Applied Sciences.

[20]  Guangyuan Xing,et al.  A Decomposition-Ensemble Approach with Denoising Strategy for PM2.5 Concentration Forecasting , 2021, Discrete Dynamics in Nature and Society.

[21]  Dingming Wu,et al.  A Hybrid Method Based on Extreme Learning Machine and Wavelet Transform Denoising for Stock Prediction , 2021, Entropy.

[22]  Tingli Su,et al.  Deep-Learning Forecasting Method for Electric Power Load via Attention-Based Encoder-Decoder with Bayesian Optimization , 2021, Energies.

[23]  Feng Ding,et al.  Hierarchical recursive signal modeling for multifrequency signals based on discrete measured data , 2021, International Journal of Adaptive Control and Signal Processing.

[24]  Mahadi Hasan,et al.  Potential of ARIMA-ANN, ARIMA-SVM, DT and CatBoost for Atmospheric PM2.5 Forecasting in Bangladesh , 2021 .

[25]  Jiachen Zhao,et al.  Attention-based parallel networks (APNet) for PM2.5 spatiotemporal prediction. , 2021, The Science of the total environment.

[26]  Cheng Pan,et al.  Prediction intervals estimation of solar generation based on gated recurrent unit and kernel density estimation , 2020, Neurocomputing.

[27]  Jiansheng Qian,et al.  A deep learning-based PM2.5 concentration estimator , 2021, Displays.

[28]  Wenjing Mao,et al.  A Novel Recursive Model Based on a Convolutional Long Short-Term Memory Neural Network for Air Pollution Prediction , 2021, Remote. Sens..

[29]  Meihang Li,et al.  Maximum likelihood hierarchical least squares‐based iterative identification for dual‐rate stochastic systems , 2020, International Journal of Adaptive Control and Signal Processing.

[30]  F. Ding,et al.  Auxiliary model multiinnovation stochastic gradient parameter estimation methods for nonlinear sandwich systems , 2020, International Journal of Robust and Nonlinear Control.

[31]  Quan Yu,et al.  PM2.5 concentration prediction based on pseudo-F statistic feature selection algorithm and support vector regression , 2020, IOP Conference Series: Earth and Environmental Science.

[32]  D. Urda,et al.  A permutation entropy-based EMD–ANN forecasting ensemble approach for wind speed prediction , 2020, Neural Computing and Applications.

[33]  Ha Yoon Song,et al.  An Analysis of Correlation between Personality and Visiting Place using Spearman's Rank Correlation Coefficient , 2020, KSII Trans. Internet Inf. Syst..

[34]  Li-Chiu Chang,et al.  Explore spatio-temporal PM2.5 features in northern Taiwan using machine learning techniques. , 2020, The Science of the total environment.

[35]  Li Hong,et al.  An Air Quality Prediction Model Based on a Noise Reduction Self-Coding Deep Network , 2020 .

[36]  Omar I. Awad,et al.  NOx emissions prediction based on mutual information and back propagation neural network using correlation quantitative analysis , 2020 .

[37]  Danlu Chen,et al.  Influence of meteorological conditions on PM2.5 concentrations across China: A review of methodology and mechanism. , 2020, Environment international.

[38]  Tingli Su,et al.  Deep Hybrid Model Based on EMD with Classification by Frequency Characteristics for Long-Term Air Quality Prediction , 2020, Mathematics.

[39]  Ling Xu,et al.  A Recursive Parameter Estimation Algorithm for Modeling Signals with Multi-frequencies , 2020, Circuits Syst. Signal Process..

[40]  Xiao Zhang,et al.  Hierarchical parameter and state estimation for bilinear systems , 2020, Int. J. Syst. Sci..

[41]  Y. Miao,et al.  Prediction of Potentially High PM2.5 Concentrations in Chengdu, China , 2020 .

[42]  Jun Ma,et al.  Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China. , 2020, The Science of the total environment.

[43]  Xiaoli Li,et al.  Atmospheric PM2.5Concentration Prediction Based on Time Series and Interactive Multiple Model Approach , 2019, Advances in Meteorology.

[44]  Feng Ding,et al.  Decomposition- and Gradient-Based Iterative Identification Algorithms for Multivariable Systems Using the Multi-innovation Theory , 2019, Circuits Syst. Signal Process..

[45]  Feng Ding,et al.  State estimation for bilinear systems through minimizing the covariance matrix of the state estimation errors , 2019, International Journal of Adaptive Control and Signal Processing.

[46]  Feng Ding,et al.  Hierarchical Principle-Based Iterative Parameter Estimation Algorithm for Dual-Frequency Signals , 2019, Circuits Syst. Signal Process..

[47]  Baozhen Wang,et al.  Research on prediction of environmental aerosol and PM2.5 based on artificial neural network , 2018, Neural Computing and Applications.

[48]  Yan Tian,et al.  LSTM-based traffic flow prediction with missing data , 2018, Neurocomputing.

[49]  Guojie Song,et al.  A Deep Spatial-Temporal Ensemble Model for Air Quality Prediction , 2018, Neurocomputing.

[50]  Alexis K.H. Lau,et al.  Time Series Forecasting of Air Quality Based On Regional Numerical Modeling in Hong Kong , 2018 .

[51]  K. Gui,et al.  Heavy pollution episodes, transport pathways and potential sources of PM2.5 during the winter of 2013 in Chengdu (China). , 2017, The Science of the total environment.

[52]  Tao Liu,et al.  The washout effects of rainfall on atmospheric particulate pollution in two Chinese cities. , 2016, Environmental pollution.

[53]  F. Ding Coupled-least-squares identification for multivariable systems , 2013 .

[54]  Chia-Nan Ko,et al.  Short-term load forecasting using lifting scheme and ARIMA models , 2011, Expert Syst. Appl..

[55]  P. X. Liu,et al.  Multiinnovation Least-Squares Identification for System Modeling , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[56]  Feng Ding,et al.  Partially Coupled Stochastic Gradient Identification Methods for Non-Uniformly Sampled Systems , 2010, IEEE Transactions on Automatic Control.

[57]  Feng Ding,et al.  Performance analysis of multi-innovation gradient type identification methods , 2007, Autom..

[58]  Feng Ding,et al.  Performance analysis of estimation algorithms of nonstationary ARMA processes , 2006, IEEE Transactions on Signal Processing.

[59]  Feng Ding,et al.  Parameter estimation of dual-rate stochastic systems by using an output error method , 2005, IEEE Trans. Autom. Control..

[60]  Feng Ding,et al.  Combined parameter and output estimation of dual-rate systems using an auxiliary model , 2004, Autom..

[61]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.