Particulate matter estimation using satellite datasets: a machine learning approach.

Autor: Verma S; Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, 221105, Uttar Pradesh, India., Sharma A; Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, 221105, Uttar Pradesh, India.; Department of Civil Engineering, Indian Institute of Technology Bombay, Mumbai, India., Payra S; Department of Remote Sensing, Birla Institute of Technology Mesra, Ranchi, India. spayra@gmail.com., Chaudhary N; Institute of Environment and Sustainable Development, Banaras Hindu University, Varanasi, 221105, Uttar Pradesh, India., Mishra M; Space Applications Centre, Indian Space Research Organization (ISRO), Ahmedabad, India.
Jazyk: angličtina
Zdroj: Environmental science and pollution research international [Environ Sci Pollut Res Int] 2024 Dec; Vol. 31 (58), pp. 66372-66387. Date of Electronic Publication: 2024 Dec 03.
DOI: 10.1007/s11356-024-35564-0
Abstrakt: In the present work, it is the first time an interpretable machine learning model has been developed for the estimation of Particulate Matter 10 µm (PM 10 ) concentrations over India using Aerosol Optical Depth (AOD) from two different satellites, i.e. INSAT-3D and Moderate Resolution Imaging Spectroradiometer (MODIS) for the period of 7 years (2014 to 2020). Ground datasets of AOD are taken from the Aerosol Robotic Network (AERONET) for the validation of satellite-retrieved AOD. The observation of particulate matter (PM) data is acquired from the Central Pollution Control Board (CPCB) station across India. Analysis has been performed on a monthly basis for the given time period. The result shows that AOD products of MODIS exhibit good correlation with AERONET AOD whereas INSAT-3D AOD is not well correlated with AERONET AOD. However, after applying an error envelope and threshold-based filtering technique, we have found that INSAT-3D shows significant correlation with ground-level AOD with approximate correlation of 0.66 for Jaipur and 0.57 for Kanpur exhibiting almost similar performance as MODIS-derived AOD. Satellite AOD data together with ground PM concentration data is used to train the machine learning model (random forest) for the estimation of the PM distribution across India for the year 2020. An encouraging correlation of R-squared (R 2 ) value 0.78 has been observed between the estimated and observed PM 10 concentrations. The model demonstrates effective training, mitigating huge overestimation and underestimation. However, despite closely tracking the trends of estimated PM 10 with observed PM 10 , few instances of overestimation persist. This suggests the need for an expanded training dataset to further refine and enhance the model's accuracy. Finally, the machine learning model used for PM 10 estimation is found to be optimal for a calibrated satellite AOD product.
Competing Interests: Declarations. Ethics approval: All authors have read, understood, and have complied as applicable with the statement on “Ethical responsibilities of Authors” as found in the Instructions for Authors. Consent to participate: Not applicable. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests.
(© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)
Databáze: MEDLINE
Externí odkaz: