Articles | Volume 19, issue 20
Atmos. Chem. Phys., 19, 12935–12951, 2019
Atmos. Chem. Phys., 19, 12935–12951, 2019

Research article 18 Oct 2019

Research article | 18 Oct 2019

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

Hyun S. Kim et al.

Related authors

Concentration Trajectory Route of Air pollution with an Integrated Lagrangian model (C-TRAIL Model v1.0) derived from the Community Multiscale Air Quality Model (CMAQ Model v5.2)
Arman Pouyaei, Yunsoo Choi, Jia Jung, Bavand Sadeghi, and Chul Han Song
Geosci. Model Dev., 13, 3489–3505,,, 2020
Short summary
The impacts of uncertainties in emissions on aerosol data assimilation and short-term PM2.5 predictions in CMAQ v5.2.1 over East Asia
Sojin Lee, Chul Han Song, Kyung Man Han, Daven K. Henze, Kyunghwa Lee, Jinhyeok Yu, Jung-Hun Woo, Jia Jung, Yunsoo Choi, Pablo E. Saide, and Gregory R. Carmichael
Geosci. Model Dev. Discuss.,,, 2020
Revised manuscript not accepted
Development of Korean Air Quality Prediction System version 1 (KAQPS v1) with focuses on practical issues
Kyunghwa Lee, Jinhyeok Yu, Sojin Lee, Mieun Park, Hun Hong, Soon Young Park, Myungje Choi, Jhoon Kim, Younha Kim, Jung-Hun Woo, Sang-Woo Kim, and Chul H. Song
Geosci. Model Dev., 13, 1055–1073,,, 2020
Short summary
GOCI Yonsei aerosol retrieval version 2 products: an improved algorithm and error analysis with uncertainty estimation from 5-year validation over East Asia
Myungje Choi, Jhoon Kim, Jaehwa Lee, Mijin Kim, Young-Je Park, Brent Holben, Thomas F. Eck, Zhengqiang Li, and Chul H. Song
Atmos. Meas. Tech., 11, 385–408,,, 2018
Short summary
GOCI Yonsei Aerosol Retrieval (YAER) algorithm and validation during the DRAGON-NE Asia 2012 campaign
Myungje Choi, Jhoon Kim, Jaehwa Lee, Mijin Kim, Young-Je Park, Ukkyo Jeong, Woogyung Kim, Hyunkee Hong, Brent Holben, Thomas F. Eck, Chul H. Song, Jae-Hyun Lim, and Chang-Keun Song
Atmos. Meas. Tech., 9, 1377–1398,,, 2016
Short summary

Related subject area

Subject: Aerosols | Research Activity: Atmospheric Modelling | Altitude Range: Troposphere | Science Focus: Physics (physical properties and processes)
Drivers of the fungal spore bioaerosol budget: observational analysis and global modeling
Ruud H. H. Janssen, Colette L. Heald, Allison L. Steiner, Anne E. Perring, J. Alex Huffman, Ellis S. Robinson, Cynthia H. Twohy, and Luke D. Ziemba
Atmos. Chem. Phys., 21, 4381–4401,,, 2021
Short summary
Improving the sectional Model for Simulating Aerosol Interactions and Chemistry (MOSAIC) aerosols of the Weather Research and Forecasting-Chemistry (WRF-Chem) model with the revised Gridpoint Statistical Interpolation system and multi-wavelength aerosol optical measurements: the dust aerosol observation campaign at Kashi, near the Taklimakan Desert, northwestern China
Wenyuan Chang, Ying Zhang, Zhengqiang Li, Jie Chen, and Kaitao Li
Atmos. Chem. Phys., 21, 4403–4430,,, 2021
Short summary
A revised mineral dust emission scheme in GEOS-Chem: improvements in dust simulations over China
Rong Tian, Xiaoyan Ma, and Jianqi Zhao
Atmos. Chem. Phys., 21, 4319–4337,,, 2021
Short summary
Quantifying the range of the dust direct radiative effect due to source mineralogy uncertainty
Longlei Li, Natalie M. Mahowald, Ron L. Miller, Carlos Pérez García-Pando, Martina Klose, Douglas S. Hamilton, Maria Gonçalves Ageitos, Paul Ginoux, Yves Balkanski, Robert O. Green, Olga Kalashnikova, Jasper F. Kok, Vincenzo Obiso, David Paynter, and David R. Thompson
Atmos. Chem. Phys., 21, 3973–4005,,, 2021
Short summary
Technical note: The enhancement limit of coagulation scavenging of small charged particles
Naser G. A. Mahfouz and Neil M. Donahue
Atmos. Chem. Phys., 21, 3827–3832,,, 2021
Short summary

Cited articles

Abdul-Wahab, S. A. and Al-Alawi, S. M.: Assessment and prediction of tropospheric ozone concentration levels using artificial neural networks, Environ. Modell. Softw., 17, 219–228, 2002. 
Amarasinghe, K., Marino, D. L., and Manic, M: Deep neural networks for energy load forecasting, Proceedings of the 26th IEEE International Symposium on Industrial Electronics, 19–21 June, Scotland, UK, 1483–1488, 2017. 
Ayinde, B. O., Inanc, T., and Zurada, J. M.: On Correlation of Features Extracted by Deep Neural Networks, arXiv:1901.10900v1, 2019. 
Bengio, Y., Simard, P., and Frasconi, P.: Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Networ., 5, 157–166, 1994. 
Berge, E., Huang, H.-C., Chang, J., and Liu, T.-H.: A study of importance of initial conditions for photochemical oxidant modeling, J. Geophys. Res.-Atmos., 106, 1347–1363, 2001. 
Short summary
In this study, 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. In general, the accuracies of the LSTM-based predictions were superior to the 3-D CTM-based predictions. Based on this, we concluded that the LSTM-based system could be applied to daily operational PM forecasts in South Korea. We expect that similar AI systems can be applied to the predictions of other atmospheric pollutants.
Final-revised paper