IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v14y2022i10p6120-d818190.html
   My bibliography  Save this article

Band-Sensitive Calibration of Low-Cost PM2.5 Sensors by LSTM Model with Dynamically Weighted Loss Function

Author

Listed:
  • Jewan Ryu

    (Department of Civil and Environmental Engineering, Korean Advanced Institute of Science and Technology, Daejeon 34141, Korea)

  • Heekyung Park

    (Department of Civil and Environmental Engineering, Korean Advanced Institute of Science and Technology, Daejeon 34141, Korea)

Abstract

Particulate matter has become one of the major issues in environmental sustainability, and its accurate measurement has grown in importance recently. Low-cost sensors (LCS) have been widely used to measure particulate concentration, but concerns about their accuracy remain. Previous research has shown that LCS data can be successfully calibrated using various machine learning algorithms. In this study, for better calibration, dynamic weight was introduced to the loss function of the LSTM model to amplify the loss, especially in a specific band. Our results showed that the dynamically weighted loss function resulted in better calibration in the specific band, where the model accepts the loss more sensitively than outside of the band. It was also confirmed that the dynamically weighted loss function can improve the calibration of the LSTM model in terms of both overall performance and local performance in bands. In a test case, the overall calibration performance was improved by about 12.57%, from 3.50 to 3.06, in terms of RMSE. The local calibration performance in the band improved from 4.25 to 3.77. Such improvements were achieved by varying coefficients of the dynamic weight. The results from different bands also indicated that having more data in a band will guarantee better improvement.

Suggested Citation

  • Jewan Ryu & Heekyung Park, 2022. "Band-Sensitive Calibration of Low-Cost PM2.5 Sensors by LSTM Model with Dynamically Weighted Loss Function," Sustainability, MDPI, vol. 14(10), pages 1-17, May.
    • Handle: RePEc:gam:jsusta:v:14:y:2022:i:10:p:6120-:d:818190
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/14/10/6120/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/2071-1050/14/10/6120/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Hyungkeun Kim & Kyungmo Kang & Taeyeon Kim, 2018. "Measurement of Particulate Matter (PM2.5) and Health Risk Assessment of Cooking-Generated Particles in the Kitchen and Living Rooms of Apartment Houses," Sustainability, MDPI, vol. 10(3), pages 1-13, March.
    2. Sergio Trilles & Ana Belen Vicente & Pablo Juan & Francisco Ramos & Sergi Meseguer & Laura Serra, 2019. "Reliability Validation of a Low-Cost Particulate Matter IoT Sensor in Indoor and Outdoor Environments Using a Reference Sampler," Sustainability, MDPI, vol. 11(24), pages 1-14, December.
    3. Hojin Jung, 2020. "The Impact of Ambient Fine Particulate Matter on Consumer Expenditures," Sustainability, MDPI, vol. 12(5), pages 1-13, March.
    4. Marius Bodor, 2021. "A Study on Indoor Particulate Matter Variation in Time Based on Count and Sizes and in Relation to Meteorological Conditions," Sustainability, MDPI, vol. 13(15), pages 1-9, July.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Yucheng He & Sanika Ravindra Nishandar & Rufus David Edwards & Marko Princevac, 2023. "Air Quality Modeling of Cooking Stove Emissions and Exposure Assessment in Rural Areas," Sustainability, MDPI, vol. 15(7), pages 1-14, March.
    2. Moses Kirimi & James K. Gitau & Ruth Mendum & Catherine Muthuri & Mary Njenga, 2023. "Cleaner Cooking with Charcoal in Kibera Informal Settlement in Nairobi, Kenya, and Its Implications for Livelihoods and the Environment," Energies, MDPI, vol. 16(19), pages 1-17, September.
    3. Monika Załuska & Katarzyna Gładyszewska-Fiedoruk, 2020. "Regression Model of PM2.5 Concentration in a Single-Family House," Sustainability, MDPI, vol. 12(15), pages 1-15, July.
    4. Vinh Van Tran & Duckshin Park & Young-Chul Lee, 2020. "Indoor Air Pollution, Related Human Diseases, and Recent Trends in the Control and Improvement of Indoor Air Quality," IJERPH, MDPI, vol. 17(8), pages 1-27, April.
    5. Muzeyyen Anil Senyel Kurkcuoglu & Beyda Nur Zengin, 2021. "Spatio-Temporal Modelling of the Change of Residential-Induced PM10 Pollution through Substitution of Coal with Natural Gas in Domestic Heating," Sustainability, MDPI, vol. 13(19), pages 1-17, September.
    6. Nikola Zaric & Velibor Spalevic & Nikola Bulatovic & Nikola Pavlicevic & Branislav Dudic, 2021. "Measurement of Air Pollution Parameters in Montenegro Using the Ecomar System," IJERPH, MDPI, vol. 18(12), pages 1-21, June.
    7. Ju-Hee Kim & Hyo-Jin Kim & Seung-Hoon Yoo, 2018. "Public Value of Enforcing the PM 2.5 Concentration Reduction Policy in South Korean Urban Areas," Sustainability, MDPI, vol. 10(4), pages 1-14, April.
    8. Marius Bodor & Alina Ceoromila & Vasile Bașliu, 2022. "Morphological and Chemical Characterization of Particulate Matter from an Indoor Measuring Campaign," Sustainability, MDPI, vol. 14(18), pages 1-10, September.
    9. Hyo-Jin Kim & Ju-Hee Kim & Seung-Hoon Yoo, 2018. "Do People Place More Value on Natural Gas Than Coal for Power Generation to Abate Particulate Matter Emissions? Evidence from South Korea," Sustainability, MDPI, vol. 10(6), pages 1-10, May.
    10. Hyungkeun Kim & Kyungmo Kang & Taeyeon Kim, 2020. "Effect of Occupant Activity on Indoor Particle Concentrations in Korean Residential Buildings," Sustainability, MDPI, vol. 12(21), pages 1-19, November.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:14:y:2022:i:10:p:6120-:d:818190. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.