Development of a daily PM10 and PM2.5 prediction system using a deep long short-term memory neural network model

被引:46
|
作者
Kim, Hyun S. [1 ]
Park, Inyoung [2 ]
Song, Chul H. [1 ]
Lee, Kyunghwa [1 ]
Yun, Jae W. [2 ]
Kim, Hong K. [2 ]
Jeon, Moongu [2 ]
Lee, Jiwon [2 ]
Han, Kyung M. [1 ]
机构
[1] GIST, Sch Earth Sci & Environm Engn, Gwangju 61005, South Korea
[2] GIST, Sch Elect Engn & Comp Sci, Gwangju 61005, South Korea
关键词
AEROSOL OPTICAL DEPTH; OZONE CONCENTRATION; PARTICULATE MATTER; HUMAN HEALTH; RECURRENT; DISTRIBUTIONS; ASSIMILATION; RETRIEVALS; EMISSIONS; POLLUTION;
D O I
10.5194/acp-19-12935-2019
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
A deep recurrent neural network system based on a long short-term memory (LSTM) model was developed for daily PM10 and PM2.5 predictions in South Korea. The structural and learnable parameters of the newly developed system were optimized from iterative model training. Independent variables were obtained from ground-based observations over 2.3 years. The performance of the particulate matter (PM) prediction LSTM was then evaluated by comparisons with ground PM observations and with the PM concentrations predicted from two sets of 3-D chemistry-transport model (CTM) simulations (with and without data assimilation for initial conditions). The comparisons showed, in general, better performance with the LSTM than with the 3-D CTM simulations. For example, in terms of IOAs (index of agreements), the PM prediction IOAs were enhanced from 0.36-0.78 with the 3-D CTM simulations to 0.62-0.79 with the LSTM-based model. The deep LSTM-based PM prediction system developed at observation sites is expected to be further integrated with 3-D CTM-based prediction systems in the future. In addition to this, further possible applications of the deep LSTM-based system are discussed, together with some limitations of the current system.
引用
收藏
页码:12935 / 12951
页数:17
相关论文
共 50 条
  • [1] PM2.5/PM10 ratio prediction based on a long short-term memory neural network in Wuhan, China
    Wu, Xueling
    Wang, Ying
    He, Siyuan
    Wu, Zhongfang
    [J]. GEOSCIENTIFIC MODEL DEVELOPMENT, 2020, 13 (03) : 1499 - 1511
  • [2] Short-term effects of PM2.5, PM10 and PM2.5-10 on daily mortality in the Netherlands
    Janssen, N. A. H.
    Fischer, P.
    Marra, M.
    Ameling, C.
    Cassee, F. R.
    [J]. SCIENCE OF THE TOTAL ENVIRONMENT, 2013, 463 : 20 - 26
  • [3] Long Short-Term Memory Deep Neural Network Model for PM2.5 Forecasting in the Bangkok Urban Area
    Thaweephol, Kankamon
    Wiwatwattana, Nuwee
    [J]. 2019 17TH INTERNATIONAL CONFERENCE ON ICT AND KNOWLEDGE ENGINEERING (ICT&KE), 2019, : 22 - 27
  • [4] Seminal Stacked Long Short-Term Memory (SS-LSTM) Model for Forecasting Particulate Matter (PM2.5 and PM10)
    Muruganandam, Narendran Sobanapuram
    Arumugam, Umamakeswari
    [J]. ATMOSPHERE, 2022, 13 (10)
  • [5] Recursive neural network model for analysis and forecast of PM10 and PM2.5
    Biancofiore, Fabio
    Busilacchio, Marcella
    Verdecchia, Marco
    Tomassetti, Barbara
    Aruffo, Eleonora
    Bianco, Sebastiano
    Di Tommaso, Sinibaldo
    Colangeli, Carlo
    Rosatelli, Gianluigi
    Di Carlo, Piero
    [J]. ATMOSPHERIC POLLUTION RESEARCH, 2017, 8 (04) : 652 - 659
  • [6] An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting
    Bai, Yun
    Zeng, Bo
    Li, Chuan
    Zhang, Jin
    [J]. CHEMOSPHERE, 2019, 222 : 286 - 294
  • [7] Air Quality Prediction (PM2.5 and PM10) at the Upper Hunter Town - Muswellbrook using the Long-Short-Term Memory Method
    Delgado, Alexi
    Maque Acuna, Ramiro Ricardo
    Carbajal, Chiara
    [J]. INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (04) : 318 - 322
  • [8] Long Short-Term Memory based PM2.5 Concentration Prediction Method
    Jiang, Nan
    Zheng, Xiuping
    Sun, Li'e
    Zheng, Hui
    Zheng, Qinghe
    [J]. ENGINEERING LETTERS, 2021, 29 (02) : 765 - 774
  • [9] PM2.5 Forecast in Korea using the Long Short-Term Memory (LSTM) Model
    Ho, Chang-Hoi
    Park, Ingyu
    Kim, Jinwon
    Lee, Jae-Bum
    [J]. ASIA-PACIFIC JOURNAL OF ATMOSPHERIC SCIENCES, 2023, 59 (05) : 563 - 576
  • [10] PM2.5 Forecast in Korea using the Long Short-Term Memory (LSTM) Model
    Chang-Hoi Ho
    Ingyu Park
    Jinwon Kim
    Jae-Bum Lee
    [J]. Asia-Pacific Journal of Atmospheric Sciences, 2023, 59 : 563 - 576