Open Access

ARTICLE

A Self-Organizing Memory Neural Network for Aerosol Concentration Prediction

by Qiang Liu¹, Yanyun Zou², Xiaodong Liu⁴

1 School of Computer, Hunan University of Technology, Zhuzhou, China.
2 Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science & Technology, Nanjing, China.
3 School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing, China.
4 School of Computing, Edinburgh Napier University, UK.

* Corresponding Author: Qiang Liu. Email: .

Computer Modeling in Engineering & Sciences 2019, 119(3), 617-637. https://doi.org/10.32604/cmes.2019.06272

Abstract

Haze-fog, which is an atmospheric aerosol caused by natural or man-made factors, seriously affects the physical and mental health of human beings. PM_2.5 (a particulate matter whose diameter is smaller than or equal to 2.5 microns) is the chief culprit causing aerosol. To forecast the condition of PM_2.5, this paper adopts the related the meteorological data and air pollutes data to predict the concentration of PM_2.5. Since the meteorological data and air pollutes data are typical time series data, it is reasonable to adopt a machine learning method called Single Hidden-Layer Long Short-Term Memory Neural Network (SSHL-LSTMNN) containing memory capability to implement the prediction. However, the number of neurons in the hidden layer is difficult to decide unless manual testing is operated. In order to decide the best structure of the neural network and improve the accuracy of prediction, this paper employs a self-organizing algorithm, which uses Information Processing Capability (IPC) to adjust the number of the hidden neurons automatically during a learning phase. In a word, to predict PM_2.5 concentration accurately, this paper proposes the SSHL-LSTMNN to predict PM_2.5 concentration. In the experiment, not only the hourly precise prediction but also the daily longer-term prediction is taken into account. At last, the experimental results reflect that SSHL-LSTMNN performs the best.

---

Keywords

---

Citations