| Title: | Machine learning based quantification of VOC contribution in surface ozone prediction |
| Author(s): | Kalbande R; Kumar B; Maji S; Yadav R; Atey K; Rathore DS; Beig G; |
| Address: | "Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India; Mohanlal Sukhadia University, Udaipur, India. Electronic address: riteshkalbande.jrf@tropmet.res.in. Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India. Electronic address: bipink@tropmet.res.in. Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India. Electronic address: sujit.cat@tropmet.res.in. Indian Institute of Tropical Meteorology, Ministry of Earth Sciences, Pune, India; NUS Environmental Research Insitute, National University of Singapore, Singapore. Electronic address: ravi.yadav@tropmet.res.in. Indian Institute of Science Education and Research, Pune, India. Electronic address: kaustubh.atey@students.iiserpune.ac.in. Mohanlal Sukhadia University, Udaipur, India. Electronic address: dsrathoremlsu@gmail.com. National Institute of Advanced Studies, Indian Institute of Science Campus, Bangalore, India. Electronic address: beig@nias.res.in" |
| DOI: | 10.1016/j.chemosphere.2023.138474 |
| ISSN/ISBN: | 1879-1298 (Electronic) 0045-6535 (Linking) |
| Abstract: | "The prediction of surface ozone is essential attributing to its impact on human and environmental health. Volatile organic compounds (VOCs) are crucial in driving ozone concentration; particularly in urban areas where VOC limited regimes are prominent. The limited measurements of VOCs, however, hinder assessing the VOC-ozone relationship. This work applies machine learning (ML) algorithms for temporal forecasting of surface ozone over a metropolitan city in India. The availability of continuous VOCs measurement data along with meteorology and other pollutants during 2014-2016 makes it possible to deduce the influence of various input parameters on surface ozone prediction. After evaluating the best ML model for ozone prediction, simulations were carried out using varied input combinations. The combination with isoprene, meteorology, NO(x,) and CO (Isop + MNC) was the best with RMSE 4.41 ppbv and MAPE 6.77%. A season-wise comparison of simulations having all data, only meteorological data and Isop + MNC as input showed that Isop + MNC simulation gives the best results during the summer season (RMSE: 5.86 ppbv, MAPE: 7.05%). This shows the increased ability of the model to capture ozone peaks (high ozone during summer) relatively better when isoprene data is used. The overall results highlight that using all available data doesn't necessarily give best prediction results; also critical thinking is essential when evaluating the model results" |
| Keywords: | Humans *Ozone/analysis *Air Pollutants/analysis *Volatile Organic Compounds/analysis Environmental Monitoring/methods Machine Learning China Isoprene Meteorology Ozone VOCs; |
| Notes: | "MedlineKalbande, Ritesh Kumar, Bipin Maji, Sujit Yadav, Ravi Atey, Kaustubh Rathore, Devendra Singh Beig, Gufran eng England 2023/03/24 Chemosphere. 2023 Jun; 326:138474. doi: 10.1016/j.chemosphere.2023.138474. Epub 2023 Mar 21" |
