Large-scale spatiotemporal deep learning predicting urban residential indoor PM2.5 concentration

被引:2
|
作者
Dai, Hui [1 ]
Liu, Yumeng [1 ]
Wang, Jianghao [4 ]
Ren, Jun [5 ]
Gao, Yao [5 ]
Dong, Zhaomin [3 ]
Zhao, Bin [1 ,2 ]
机构
[1] Tsinghua Univ, Sch Architecture, Dept Bldg Sci, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Beijing Key Lab Indoor Air Qual Evaluat & Control, Beijing 100084, Peoples R China
[3] Beihang Univ, Sch Space & Environm, Beijing 100191, Peoples R China
[4] Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China
[5] Shenzhen Inst Bldg Res Co Ltd, Shenzhen, Peoples R China
基金
美国国家科学基金会;
关键词
Indoor PM 2.5; Bayesian neural network; Low-cost sensor; Human exposure; Health effect; BAYESIAN NEURAL-NETWORK; FINE PARTICULATE MATTER; AIR-QUALITY; EXPOSURE; BUILDINGS; PARTICLES; OCCUPANTS; CHINA;
D O I
10.1016/j.envint.2023.108343
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Indoor PM2.5 pollution is one of the leading causes of death and disease worldwide. As monitoring indoor PM2.5 concentrations on a large scale is challenging, it is urgent to assess population-level exposure and related health risks to develop an easy-to-use and generalized model to predict indoor PM2.5 concentrations and spatiotemporal variations at the global level. Existing machine learning models of indoor PM2.5 are prone to deliver single-point predictions, and their input strategies are not widely applicable. Here, we developed a Bayesian neural network (BNN) model for predicting the distribution of daily average urban residential PM2.5 concentration based on multiple data sources available from nationwide comprehensive sensor-monitoring records in China. The BNN model showed good performance with a 10-fold cross-validation R2 of 0.70, mean-absolute-error of 9.45 mu g/m3, root-mean-square error of 13.3 mu g/m3, and 95 % prediction interval coverage of 85 %. To demonstrate the application process, this model was applied to predict indoor PM2.5 concentrations on a large spatiotemporal scale. Our modeled population-weighted annual indoor PM2.5 concentration for China in 2019 was 22.8 mu g/m3, far exceeding the WHO standard. The validity of the model at the population level can be further bolstered, making it valuable for assessing and managing indoor air pollution-related health risks.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Indoor residential and outdoor sources of PM2.5 and PM10 in Nicosia, Cyprus
    Yichen Wang
    Petros Koutrakis
    Antonis Michanikou
    Panayiotis Kouis
    Andrie G. Panayiotou
    Paraskevi Kinni
    Filippos Tymvios
    Andreas Chrysanthou
    Marina Neophytou
    Petros Mouzourides
    Chrysanthos Savvides
    Emily Vasiliadou
    Ilias Papasavvas
    Theodoros Christophides
    Rozalia Nicolaou
    Panayiotis Avraamides
    Choong-Min Kang
    Stefania I. Papatheodorou
    Nicos Middleton
    Panayiotis K. Yiallouros
    Souzana Achilleos
    Air Quality, Atmosphere & Health, 2024, 17 : 485 - 499
  • [42] PM2.5 forecasting for an urban area based on deep learning and decomposition method
    Zaini, Nur'atiah
    Ean, Lee Woen
    Ahmed, Ali Najah
    Malek, Marlinda Abdul
    Chow, Ming Fai
    SCIENTIFIC REPORTS, 2022, 12 (01)
  • [43] Indoor residential and outdoor sources of PM2.5 and PM10 in Nicosia, Cyprus
    Wang, Yichen
    Koutrakis, Petros
    Michanikou, Antonis
    Kouis, Panayiotis
    Panayiotou, Andrie G.
    Kinni, Paraskevi
    Tymvios, Filippos
    Chrysanthou, Andreas
    Neophytou, Marina
    Mouzourides, Petros
    Savvides, Chrysanthos
    Vasiliadou, Emily
    Papasavvas, Ilias
    Christophides, Theodoros
    Nicolaou, Rozalia
    Avraamides, Panayiotis
    Kang, Choong-Min
    Papatheodorou, Stefania I.
    Middleton, Nicos
    Yiallouros, Panayiotis K.
    Achilleos, Souzana
    AIR QUALITY ATMOSPHERE AND HEALTH, 2024, 17 (03): : 485 - 499
  • [44] Residential indoor PM10 and PM2.5 in Hong kong and the elemental composition
    Chao, CY
    Wong, KK
    ATMOSPHERIC ENVIRONMENT, 2002, 36 (02) : 265 - 277
  • [45] ADF: An Anomaly Detection Framework for Large-Scale PM2.5 Sensing Systems
    Chen, Ling-Jyh
    Ho, Yao-Hua
    Hsieh, Hsin-Hung
    Huang, Shih-Ting
    Lee, Hu-Cheng
    Mahajan, Sachit
    IEEE INTERNET OF THINGS JOURNAL, 2018, 5 (02): : 559 - 570
  • [46] PM2.5 forecasting for an urban area based on deep learning and decomposition method
    Nur’atiah Zaini
    Lee Woen Ean
    Ali Najah Ahmed
    Marlinda Abdul Malek
    Ming Fai Chow
    Scientific Reports, 12
  • [47] Personal exposure and indoor PM2.5 concentrations in an urban population
    Mohammadyan, M
    Ashmore, M
    INDOOR AND BUILT ENVIRONMENT, 2005, 14 (3-4) : 313 - 320
  • [48] Spatial Concentration of Carbon Components in Indoor PM2.5 of School Classrooms in a Large City of Korea
    Heo, Sujeong
    Kwoun, Jiyou
    Lee, Sumin
    Kim, Doyoon
    Lee, Taejung
    Jo, Youngmin
    APPLIED SCIENCES-BASEL, 2021, 11 (16):
  • [49] Impact of Urban Neighborhood Morphology on PM2.5 Concentration Distribution at Different Scale Buffers
    Wang, Zhen
    Hu, Kexin
    Wang, Zheyu
    Yang, Bo
    Chen, Zhiyu
    LAND, 2025, 14 (01)
  • [50] Analysis of spatiotemporal PM2.5 concentration patterns in Changwon, Korea, using low-cost PM2.5 sensors
    Song, Bonggeun
    Park, Kyunghun
    Kim, Taehyeung
    Seo, Gyeongho
    URBAN CLIMATE, 2022, 46