Academic Journal of Environment & Earth Science, 2021, 3(2); doi: 10.25236/AJEE.2021.030208.
Jiaxun Liang1, Kexin Yan2
1School of Quality and Technical Supervision, Hebei University, Baoding, Hebei, 071002, China
2School of Mathematics and Statistics, Ningbo University, Ningbo, Zhejiang, 315211, China
At present, air pollution is still the biggest environmental health problem we are facing. Although the content of PM2.5 is small, it has a great impact on air quality and human health. In order to accurately predict PM2.5, this paper proposed the CEEMD-SSA-KELM model. We preprocessed the data, predicted PM2.5, compared and evaluated the fitting effect. We decomposed the obtained non-stationary, non-linear original data series into several smoother components on different scales by CEEMD for individual prediction as data pre-processing. After preprocessing, the obtained component data were respectively used as the input variables of SSA-KELM, and the final predicted value was obtained after processing each predicted value sequence. In the evaluation section we have selected four evaluation metrics to evaluate the model and compare it with different models. From the results of the analysis and comparison, we can see that the model proposed in this paper has better fitting effect, higher accuracy of fitting, and stronger stability.
complementary ensemble empirical mode decomposition, sparrow search algorithm, kernel extreme learning machine, CEEMD-SSA-KELM hybrid model, PM2.5 prediction
Jiaxun Liang, Kexin Yan. PM2.5 prediction based on CEEMD-SSA-KELM. Academic Journal of Environment & Earth Science (2021) Vol. 3 Issue 2: 40-47. https://doi.org/10.25236/AJEE.2021.030208.
 Mahajan S, Chen L J, Tsai T C. Short-Term PM2.5 Forecasting Using Exponential Smoothing Method: A Comparative Analysis [J]. Sensors, 2018, 18(10).
 Jia Yang Li and Yang Zhao and Shen Kai Shi. The Multivariate Gray Model approach to predict the Concentration of Atmospheric Fine PM2.5 [J]. Advanced Materials Research, 2014, 3248(955-959): 2362-2365.
 Pohlmann, J. T., Leitner, D. W. A Comparison of Ordinary Least Squares and Logistic Regression. Ohio Journal of Science. 103(5), 118-125 (2003). 41.
 Huang C J, Kuo P H. A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities [J]. Sensors, 2018, 18(7): 2220.
 Kow P Y, Wang Y S, Zhou Y, et al. Seamless integration of convolutional and back-propagation neural networks for regional multi-step-ahead PM2.5 forecasting [J]. Journal of Cleaner Production, 2020: 121285.
 Chae S, Shin J, Kwon S, et al. PM10 and PM2.5 real-time prediction models using an interpolated convolutional neural network [J]. Scientific Reports.
 HUANG N E, SHEN Z, LONG S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society of London Series A, 1998, 454(1971): 903-995.
 WU Z H, HUANG N E. Ensemble empirical mode decomposition: a noise-assisted data analysis method [J]. Advances in Adaptive Data Analysis, 2009, 1(1): 1-41.
 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.
 Xue J, Shen B. A novel swarm intelligence optimization approach: sparrow search algorithm [J]. Systems science & control engineering, 2020, 8(1): 22-34.
 Huang Guangbin, Zhu Qinyu, Siew Cheekheong. Extreme learning machine: theory and applications [J]. Neurocomputing, 2006, 70(1/2 /3): 489-501.