Welcome to Francis Academic Press

Academic Journal of Computing & Information Science, 2021, 4(5); doi: 10.25236/AJCIS.2021.040502.

AQI prediction based on CEEMD-WOA-Elman neural network


Kexin Yan1, Jiaxun Liang2

Corresponding Author:
Kexin Yan

1School of Mathematics and Statistics, Ningbo University, Ningbo, Zhejiang, 315211, China

2School of Quality and Technical Supervision, Hebei University, Baoding, Hebei, 071002, China


Aiming at the problem of predicting AQI, this paper proposes a hybrid prediction model. The specific method is to use Complementary Ensemble Empirical Mode Decomposition (CEEMD) to preprocess the non-stationary sequence, and then use the Elman neural network optimized by WOA to predict. The construction of CEEMD-WOA-Elman model mainly includes four parts: preprocessing, optimization, prediction, and evaluation. In order to evaluate the effectiveness and generalization ability of the model, we introduced four evaluation indicators to comprehensively evaluate the prediction model proposed in this paper. The analysis results show that compared with other models, the hybrid prediction model proposed in this paper has higher prediction accuracy and the predicted results obtained are more excellent.


complementary ensemble empirical mode decomposition, whale optimization algorithm, Elman neural network, air quality index prediction, CEEMD-WOA-Elman hybrid model

Cite This Paper

Kexin Yan, Jiaxun Liang. AQI prediction based on CEEMD-WOA-Elman neural network. Academic Journal of Computing & Information Science (2021), Vol. 4, Issue 5: 8-15. https://doi.org/10.25236/AJCIS.2021.040502.


[1] Giuseppe Nunnari et al. Modelling SO2 concentration at a point with statistical approaches [J]. Environmental Modelling and Software, 2003, 19(10): 887-905.

[2] Guo X, Liu S. Forecasting China's SO2 emissions by the nonlinear grey Bernoulli self-memory model (NGBSM) [C]// IEEE International Conference on Grey Systems & Intelligent Services. IEEE, 2015:80-85.

[3] ZHANG XiLai, ZHAO JianHui, CAI Bo. Prediction Model with Dynamic Adjustment for Single Time Series of PM2.5 [J]. Journal of Automation, 2018, 44(10): 1790-1798.

[4] Binkowski, Francis S. Models-3 Community Multiscale Air Quality (CMAQ) model aerosol component 1. Model description [J]. Journal of Geophysical Research: Atmospheres, 2003, 108(D6):-.

[5] Choi M W, Lee J H, Woo J W, et al. Comparison of PM2.5 Chemical Components over East Asia Simulated by the WRF-Chem and WRF/CMAQ Models: On the Models Prediction Inconsistency [J]. Atmosphere, 2019.

[6] Hagihara Y, Itahashi S, Yumimoto K , et al. Comparison of simulated and observed signals over East Asia using WRF-Chem model, A-Train data, and satellite simulators [J]. American Geophysical Union, 2011.

[7] YEH J R, SHIEH J S, HUANG N E. Complementary ensemble empirical mode decomposition: a novel noise enhanced data analysis method [J]. Advances in Adaptive Data Analysis, 2010, 2(2): 135-156.

[8] Jeffrey L. Elman. Finding structure in time [J]. 1990, 14(2): 179-211.

[9] Seyedali Mirjalili and Andrew Lewis. The Whale Optimization Algorithm [J]. Advances in Engineering Software, 2016, 95: 51-67.