Title: An improvement of PM_2.5 concentration prediction using optimised deep LSTM

Authors: Tong-Hyok Choe; Chung-Song Ho

Addresses: Faculty of Global Environmental Science, Kim Il Sung University, Pyongyang, 999093, Democratic People's Republic of Korea ' Institute of Advanced Science, Kim Il Sung University, Pyongyang, 999093, Democratic People's Republic of Korea

Abstract: Air pollution poses a serious threat to human health and the environment worldwide, of which particulate matter (PM_2.5), receives an increasing attention with deeper recognition of human health risk. In this paper, we proposed a method for optimising the deep long short term memory (LSTM) model to improve the quality of PM_2.5 concentration prediction and used it for PM_2.5 concentration prediction. The parameters of the optimised deep LSTM model were determined by using the genetic algorithm, and were applied to predict PM_2.5 concentration, thus achieving better results than when the genetic algorithm was not used. The predicted PM_2.5 concentration results of the optimised deep LSTM model were compared with the recurrent neural network (RNN) and gated recurrent unit (GRU) models, respectively, showing that the LSTM model had improved performance. This method would possibly contribute to enrich noble solutions in the aspect of air-pollution prediction.

Keywords: air quality; air pollution; PM_2.5 prediction; deep LSTM; long short term memory; neural networks; GA; genetic algorithm; optimise; environment.

DOI: 10.1504/IJEP.2021.126976

International Journal of Environment and Pollution, 2021 Vol.69 No.3/4, pp.249 - 260

Received: 22 Nov 2020
Accepted: 15 Dec 2021
Published online: 15 Nov 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article