Abstract
Neural network models were presented for prediction of indoor concentrations of particulate matters (PMs). Indoor PM concentrations are generally determined by the outdoor concentration, the indoor generation rate, and the air change rate of a building. In this study, indoor PM2.5 and PM10 concentrations were modelled in a single office room installed with a portable air purifier (AP) and a heat recovery ventilator (HRV), using three different neural network models with various input variables. The relative importance of individual input variables indicated that as opposed to PM10, PM2.5 is more affected by outdoor origin than indoor source. This is generally consistent with previous findings explaining that the main source of PM2.5 is outdoor environment, whereas that for PM10 is indoor human activities. The simplified models can be easily applied in practice based on the CO2 concentration measured in a room and the outdoor PM concentration data acquired from public data.
Similar content being viewed by others
References
W. M. Valenti, HAART is cost-effective and improves outcomes, AIDS Read, 11(5) (2001) 260–262.
N. E. Klepeis et al., The national human activity pattern survey (NHAPS): a resource for assessing exposure to environmental pollutants, J. Expo. Anal. Environ. Epidemiol, 11(3) (2001) 231–252.
J. O. Anderson, J. G. Thundiyil and A. Stolbach, Clearing the air: a review of the effects of particulate matter air pollution on human health, J. Med. Toxicol, 8(2) (2012) 166–175.
C. Monn et al., Particulate matter less than 10 µm (PM10) and fine particles less than 25 µm (PM25): relationships between indoor, outdoor and personal concentrations, Sci. Total Environ., 208(1-2) (1997) 15–21.
N. R. Martins and G. Carrilho da Graça, Impact of PM25 in indoor urban environments: a review, Sustain. Cities Soc., 42 (2018) 259–275.
K. Vimalanathan and T. Ramesh Babu, The effect of indoor office environment on the work performance, health and well-being of office workers, J. Environ. Heal. Sci. Eng., 12(1) (2014) 113.
C. He, Contribution from indoor sources to particle number and mass concentrations in residential houses, Atmos. Environ., 38(21) (2004) 3405–3415.
C. M. Long, H. H. Suh and P. Koutrakis, Characterization of indoor particle sources using continuous mass and size monitors, J. Air Waste Manage. Assoc., 50(7) (2000) 1236–1250.
M. Braniš, P. Řezáčová and M. Domasová, The effect of outdoor air and indoor human activity on mass concentrations of PM10, PM25, and PM1 in a classroom, Environ. Res., 99(2) (2005) 143–149.
M. Elbayoumi et al., Multivariate methods for indoor PM10 and PM25 modelling in naturally ventilated schools buildings, Atmos. Environ., 94 (2014) 11–21.
J. Al-Hubail and A.-S. Al-Temeemi, Assessment of school building air quality in a desert climate, Build. Environ., 94 (2015) 569–579.
T. Hussein et al., Characterization, fate, and re-suspension of aerosol particles (03–10 µm): the effects of occupancy and carpet use, Aerosol Air Qual. Res., 15(6) (2015) 2367–2377.
G. Sangiorgi et al., Indoor airborne particle sources and semi-volatile partitioning effect of outdoor fine PM in offices, Atmos. Environ., 65 (2013) 205–214.
C. He, L. Morawska and L. Taplin, Particle emission characteristics of office printers, Environ. Sci. Technol., 41(17) (2007) 6039–6045.
M. Wensing et al., Ultra-fine particles release from hardcopy devices: sources, real-room measurements and efficiency of filter accessories, Sci. Total Environ., 407(1) (2008) 418–427.
A. J. Koivisto et al., Impact of particle emissions of new laser printers on modeled office room, Atmos. Environ., 44(17) (2010) 2140–2146.
D. Licina, Y. Tian and W. W. Nazaroff, Emission rates and the personal cloud effect associated with particle release from the perihuman environment, Indoor Air, 27(4) (2017) 791–802.
C. Y. H. Chao, T. C. W. Tung and J. Burnett, Influence of different indoor activities on the indoor particulate levels in residential buildings, Indoor Built Environ., 7(2) (1998) 110–121.
T. Li et al., Household concentrations and personal exposure of PM25 among urban residents using different cooking fuels, Sci. Total Environ., 548–549 (2016) 6–12.
T. Thatcher, Deposition, resuspension, and penetration of particles within a residence, Atmos. Environ., 29(13) (1995) 1487–1497.
F. Chen, S. C. M. Yu and A. C. K. Lai, Modeling particle distribution and deposition in indoor environments with a new drift-flux model, Atmos. Environ., 40(2) (2006) 357–367.
R. Goyal and M. Khare, Indoor air quality modeling for PM10, PM25, and PM10 in naturally ventilated classrooms of an urban Indian school building, Environ. Monit. Assess., 176(1-4) (2011) 501–516.
D. T. Tran et al., Indoor particle dynamics in schools: determination of air exchange rate, size-resolved particle deposition rate and penetration factor in real-life conditions, Indoor Built Environ., 26(10) (2017) 1335–1350.
T. Hussein and M. Kulmala, Indoor aerosol modeling: basic principles and practical applications, Water, Air, Soil Pollut. Focus, 8(1) (2008) 23–34.
W. Wei et al., Machine learning and statistical models for predicting indoor air quality, Indoor Air, 29(5) (2019) 704–726.
A. Challoner, F. Pilla and L. Gill, Prediction of indoor air exposure from outdoor air quality using an artificial neural network model for inner city commercial buildings, Int. J. Environ. Res. Public Health, 12(12) (2015) 15233–15253.
M. Elbayoumi, N. A. Ramli and N. F. Fitri Md. Yusof, Development and comparison of regression models and feedforward backpropagation neural network models to predict seasonal indoor PM25-10 and PM25 concentrations in naturally ventilated schools, Atmos. Pollut. Res., 6(6) (2015) 1013–1023.
O. M. Ibrahim, A comparison of methods for assessing the relative importance of input variables in artificial neural networks, The J. Applied Sciences Research, 9(11) (2013) 5692–5700.
A. R. Ferro, R. J. Kopperud and L. M. Hildemann, Elevated personal exposure to particulate matter from human activities in a residence, J. Expo. Sci. Environ. Epidemiol., 14(S1) (2004) S34–S40.
A. G. Alam et al., Uncertainties in neural network model based on carbon dioxide concentration for occupancy estimation, J. Mech. Sci. Technol., 31(5) (2017) 2573–2580.
H. Rahman and H. Han, Occupancy estimation based on indoor CO2 concentration: comparison of neural network and bayesian methods, Int. J. Air-Conditioning Refrig., 25(3) (2017) 1750021.
Acknowledgments
This work was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2016R1D1A1 B01009625) and by Global scholarship of Kookmin University.
Author information
Authors and Affiliations
Corresponding author
Additional information
Muhammad Hatta received his M.S. degree in Mechanical Engineering from Kookmin University in 2020. He joined the TEE (Thermal Environmental Engineering) Lab in Kookmin University after he received his M.E. degree from University of Riau, Indonesia in 2017. Currently, he is working for an IoT company in South Korea. His main research interest lies in developing a predictive model for industrial machinery using machine learning.
Hwataik Han received B.S. and M.S. from Seoul National University and Ph.D. degree from University of Minnesota in 1988. Currently, he is a Professor in Kookmin University. He is a registered PE at Minnesota State Board of AELSLAGID. He served as the President of SAREK in 2014 and the Editorin-Chief of KACA (Korea Air Cleaning Association) since 2005. He organized the Indoor Air 2020 Conference as the President. Now, he is a fellow of ASHRAE and of SAREK.
Rights and permissions
About this article
Cite this article
Hatta, M., Han, H. Predicting indoor PM2.5/PM10 concentrations using simplified neural network models. J Mech Sci Technol 35, 3249–3257 (2021). https://doi.org/10.1007/s12206-021-0645-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-021-0645-6