Integrated Predictor Based on Decomposition Mechanism for PM2.5 Long-Term Prediction

It is crucial to predict PM2.5 concentration for early warning regarding and the control of air pollution. However, accurate PM2.5 prediction has been challenging, especially in long-term prediction. PM2.5 monitoring data comprise a complex time series that contains multiple components with different characteristics; therefore, it is difficult to obtain an accurate prediction by a single model. In this study, an integrated predictor is proposed, in which the original data are decomposed into three components, that is, trend, period, and residual components, and then different sub-predictors including autoregressive integrated moving average (ARIMA) and two gated recurrent units are used to separately predict the different components. Finally, all the predictions from the sub-predictors are combined in fusion node to obtain the final prediction for the original data. The results of predicting the PM2.5 time series for Beijing, China showed that the proposed predictor can effectively improve prediction accuracy for long-term prediction.

[1]  Feng Ding,et al.  Novel data filtering based parameter identification for multiple-input multiple-output systems using the auxiliary model , 2016, Autom..

[2]  F. Ding.  Hierarchical multi-innovation stochastic gradient algorithm for Hammerstein nonlinear system modeling , 2013 .

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

[4]  J. Chu,et al.  Gradient-based and least-squares-based iterative algorithms for Hammerstein systems using the hierarchical identification principle , 2013 .

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  Feng Ding,et al.  State filtering and parameter estimation for linear systems with d-step state-delay , 2014, IET Signal Process..

[7]  Yegang Chen.  Prediction algorithm of PM2.5 mass concentration based on adaptive BP neural network , 2018, Computing.

[8]  Qinyao Liu,et al.  Partially coupled gradient estimation algorithm for multivariable equation-error autoregressive moving average systems using the data filtering technique , 2019 .

[9]  Irma J. Terpenning,et al.  STL : A Seasonal-Trend Decomposition Procedure Based on Loess , 1990 .

[10]  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.

[11]  Jianqiang Pan,et al.  A filtering based multi-innovation extended stochastic gradient algorithm for multivariable control systems , 2017 .

[12]  H. Akaike.  A new look at the statistical model identification , 1974 .

[13]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[14]  Feng Ding,et al.  New gradient based identification methods for multivariate pseudo-linear systems using the multi-innovation and the data filtering , 2017, J. Frankl. Inst..

[15]  Xiuhua Lu,et al.  The Prediction of PM2.5 Value Based on ARMA and Improved BP Neural Network Model , 2016, 2016 International Conference on Intelligent Networking and Collaborative Systems (INCoS).

[16]  Yuanxi Yang,et al.  Analysis of seasonal signals and long-term trends in the height time series of IGS sites in China , 2016, Science China Earth Sciences.

[17]  Guo-Wei Wei,et al.  Feature functional theory–binding predictor (FFT–BP) for the blind prediction of binding free energies , 2017, Theoretical Chemistry Accounts.

[18]  Jing Chen,et al.  Hierarchical identification for multivariate Hammerstein systems by using the modified Kalman filter , 2017 .

[19]  VAR Model of PM2.5, Weather and Traffic in Los Angeles-Long Beach Area , 2009, 2009 International Conference on Environmental Science and Information Application Technology.

[20]  Feng Ding,et al.  Decomposition based fast least squares algorithm for output error systems , 2013, Signal Process..

[21]  Feng Ding,et al.  Recursive parameter estimation algorithm for multivariate output-error systems , 2018, J. Frankl. Inst..

[22]  Feng Ding,et al.  Hierarchical Least Squares Identification for Linear SISO Systems With Dual-Rate Sampled-Data , 2011, IEEE Transactions on Automatic Control.

[23]  Feng Ding,et al.  Filtering-Based Multistage Recursive Identification Algorithm for an Input Nonlinear Output-Error Autoregressive System by Using the Key Term Separation Technique , 2017, Circuits Syst. Signal Process..

[24]  Suya You,et al.  Scene Labeling using Gated Recurrent Units with Explicit Long Range Conditioning , 2016 .

[25]  Kin Keung Lai,et al.  An improved grey neural network model for predicting transportation disruptions , 2016, Expert Syst. Appl..

[26]  Yong Liu,et al.  Six-decade temporal change and seasonal decomposition of climate variables in Lake Dianchi watershed (China): stable trend or abrupt shift? , 2014, Theoretical and Applied Climatology.

[27]  Pei-Chann Chang,et al.  A Deep Recurrent Neural Network for Air Quality Classification , 2018, J. Inf. Hiding Multim. Signal Process..

[28]  Ping-Huan Kuo,et al.  A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities , 2018, Sensors.

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

[30]  F. Ding.  Two-stage least squares based iterative estimation algorithm for CARARMA system modeling ☆ , 2013 .

[31]  Zheng Haiming,et al.  Study on Prediction of Atmospheric PM2.5 Based on RBF Neural Network , 2013, 2013 Fourth International Conference on Digital Manufacturing & Automation.

[32]  Yves Rybarczyk,et al.  Machine Learning Approaches for Outdoor Air Quality Modelling: A Systematic Review , 2018, Applied Sciences.

[33]  Feng Ding,et al.  Gradient based and least-squares based iterative identification methods for OE and OEMA systems , 2010, Digit. Signal Process..

[34]  Feng Ding,et al.  An efficient hierarchical identification method for general dual-rate sampled-data systems , 2014, Autom..

[35]  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.

[36]  Weijie Ren,et al.  Prediction of Air Pollution Concentration Based on mRMR and Echo State Network , 2019, Applied Sciences.

[37]  Feng Ding,et al.  Combined state and least squares parameter estimation algorithms for dynamic systems , 2014 .

[38]  F. Ding,et al.  Partially‐coupled least squares based iterative parameter estimation for multi‐variable output‐error‐like autoregressive moving average systems , 2019, IET Control Theory & Applications.

[39]  Jiangshe Zhang,et al.  Prediction of Air Pollutants Concentration Based on an Extreme Learning Machine: The Case of Hong Kong , 2017, International journal of environmental research and public health.

[40]  Feng Ding,et al.  The filtering‐based maximum likelihood iterative estimation algorithms for a special class of nonlinear systems with autoregressive moving average noise using the hierarchical identification principle , 2019, International Journal of Adaptive Control and Signal Processing.

[41]  Hong Huang,et al.  Relevance analysis and short-term prediction of PM2.5 concentrations in Beijing based on multi-source data , 2017 .

[42]  Tong Wang,et al.  Using gated recurrence units neural network for prediction of melt spinning properties , 2017, 2017 11th Asian Control Conference (ASCC).

[43]  Erfu Yang,et al.  State filtering‐based least squares parameter estimation for bilinear systems using the hierarchical identification principle , 2018, IET Control Theory & Applications.

[44]  A. Luati,et al.  Global and local statistical properties of fixed-length nonparametric smoothers , 2002 .

[45]  Feng Ding,et al.  Maximum Likelihood Recursive Identification for the Multivariate Equation-Error Autoregressive Moving Average Systems Using the Data Filtering , 2019, IEEE Access.

[46]  Feng Ding,et al.  Decomposition based least squares iterative identification algorithm for multivariate pseudo-linear ARMA systems using the data filtering , 2017, J. Frankl. Inst..

[47]  Y. Liu,et al.  Gradient-based and least-squares-based iterative estimation algorithms for multi-input multi-output systems , 2012, J. Syst. Control. Eng..

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

[49]  Ling Xu,et al.  Highly computationally efficient state filter based on the delta operator , 2019, International Journal of Adaptive Control and Signal Processing.

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

[51]  Jesús Rojo,et al.  Modeling pollen time series using seasonal-trend decomposition procedure based on LOESS smoothing , 2017, International Journal of Biometeorology.

[52]  Feng Ding,et al.  States based iterative parameter estimation for a state space model with multi-state delays using decomposition , 2015, Signal Process..

[53]  C. Galán,et al.  Impact of land cover changes and climate on the main airborne pollen types in Southern Spain. , 2016, The Science of the total environment.

[54]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.