A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019
<p>Surface ozone concentrations increased in many regions of China from 2015 to 2019. While the central role of meteorology in modulating ozone pollution is widely acknowledged, its quantitative contribution remains highly uncertain. Here, we use a data-driven machine learning approach to asse...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2022-06-01
|
| Series: | Atmospheric Chemistry and Physics |
| Online Access: | https://acp.copernicus.org/articles/22/8385/2022/acp-22-8385-2022.pdf |
| _version_ | 1811332922409484288 |
|---|---|
| author | X. Weng G. L. Forster G. L. Forster P. Nowack P. Nowack P. Nowack P. Nowack |
| author_facet | X. Weng G. L. Forster G. L. Forster P. Nowack P. Nowack P. Nowack P. Nowack |
| author_sort | X. Weng |
| collection | DOAJ |
| description | <p>Surface ozone concentrations increased in many regions of
China from 2015 to 2019. While the central role of meteorology in modulating
ozone pollution is widely acknowledged, its quantitative contribution
remains highly uncertain. Here, we use a data-driven machine learning
approach to assess the impacts of meteorology on surface ozone variations in
China for the period 2015–2019, considering the months of highest ozone pollution
from April to October. To quantify the importance of various meteorological
driver variables, we apply nonlinear random forest regression (RFR) and
linear ridge regression (RR) to learn about the relationship between
meteorological variability and surface ozone in China, and contrast the
results to those obtained with the widely used multiple linear regression
(MLR) and stepwise MLR. We show that RFR outperforms the three linear
methods when predicting ozone using local meteorological predictor
variables, as evident from its higher coefficients of determination
(<span class="inline-formula"><i>R</i><sup>2</sup></span>) with observations (0.5–0.6 across China) when compared to the
linear methods (typically <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.4–0.5). This refers to the importance of
nonlinear relationships between local meteorological factors and ozone,
which are not captured by linear regression algorithms. In addition, we find
that including nonlocal meteorological predictors can further improve the
modelling skill of RR, particularly for southern China where the averaged
<span class="inline-formula"><i>R</i><sup>2</sup></span> increases from 0.47 to 0.6. Moreover, this improved RR shows a
higher averaged meteorological contribution to the increased trend of ozone
pollution in that region, pointing towards an elevated importance of
large-scale meteorological phenomena for ozone pollution in southern China.
Overall, RFR and RR are in close agreement concerning the leading
meteorological drivers behind regional ozone pollution. In line with
expectations, our analysis underlines that hot and dry weather conditions
with high sunlight intensity are strongly related to high ozone pollution
across China, thus further validating our novel approach. In contrast to
previous studies, we also highlight surface solar radiation as a key
meteorological variable to be considered in future analyses. By comparing
our meteorology based predictions with observed ozone values between 2015
and 2019, we estimate that almost half of the 2015–2019 ozone trends across
China might have been caused by meteorological variability. These insights
are of particular importance given possible increases in the frequency and
intensity of weather extremes such as heatwaves under climate change.</p> |
| first_indexed | 2024-04-13T16:44:20Z |
| format | Article |
| id | doaj.art-09c8b1233115481c99f05060083b1b67 |
| institution | Directory Open Access Journal |
| issn | 1680-7316 1680-7324 |
| language | English |
| last_indexed | 2024-04-13T16:44:20Z |
| publishDate | 2022-06-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Atmospheric Chemistry and Physics |
| spelling | doaj.art-09c8b1233115481c99f05060083b1b672022-12-22T02:39:08ZengCopernicus PublicationsAtmospheric Chemistry and Physics1680-73161680-73242022-06-01228385840210.5194/acp-22-8385-2022A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019X. Weng0G. L. Forster1G. L. Forster2P. Nowack3P. Nowack4P. Nowack5P. Nowack6School of Environmental Sciences, University of East Anglia, Norwich, NR47 TJ, UKSchool of Environmental Sciences, University of East Anglia, Norwich, NR47 TJ, UKNational Centre for Atmospheric Science, University of East Anglia, Norwich, NR47 TJ, UKSchool of Environmental Sciences, University of East Anglia, Norwich, NR47 TJ, UKGrantham Institute – Climate Change and the Environment, Imperial College London, London SW7 2AZ, UKDepartment of Physics, Imperial College London, London SW7 2AZ, UKData Science Institute, Imperial College London, London SW7 2AZ, UK<p>Surface ozone concentrations increased in many regions of China from 2015 to 2019. While the central role of meteorology in modulating ozone pollution is widely acknowledged, its quantitative contribution remains highly uncertain. Here, we use a data-driven machine learning approach to assess the impacts of meteorology on surface ozone variations in China for the period 2015–2019, considering the months of highest ozone pollution from April to October. To quantify the importance of various meteorological driver variables, we apply nonlinear random forest regression (RFR) and linear ridge regression (RR) to learn about the relationship between meteorological variability and surface ozone in China, and contrast the results to those obtained with the widely used multiple linear regression (MLR) and stepwise MLR. We show that RFR outperforms the three linear methods when predicting ozone using local meteorological predictor variables, as evident from its higher coefficients of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) with observations (0.5–0.6 across China) when compared to the linear methods (typically <span class="inline-formula"><i>R</i><sup>2</sup></span> <span class="inline-formula">=</span> 0.4–0.5). This refers to the importance of nonlinear relationships between local meteorological factors and ozone, which are not captured by linear regression algorithms. In addition, we find that including nonlocal meteorological predictors can further improve the modelling skill of RR, particularly for southern China where the averaged <span class="inline-formula"><i>R</i><sup>2</sup></span> increases from 0.47 to 0.6. Moreover, this improved RR shows a higher averaged meteorological contribution to the increased trend of ozone pollution in that region, pointing towards an elevated importance of large-scale meteorological phenomena for ozone pollution in southern China. Overall, RFR and RR are in close agreement concerning the leading meteorological drivers behind regional ozone pollution. In line with expectations, our analysis underlines that hot and dry weather conditions with high sunlight intensity are strongly related to high ozone pollution across China, thus further validating our novel approach. In contrast to previous studies, we also highlight surface solar radiation as a key meteorological variable to be considered in future analyses. By comparing our meteorology based predictions with observed ozone values between 2015 and 2019, we estimate that almost half of the 2015–2019 ozone trends across China might have been caused by meteorological variability. These insights are of particular importance given possible increases in the frequency and intensity of weather extremes such as heatwaves under climate change.</p>https://acp.copernicus.org/articles/22/8385/2022/acp-22-8385-2022.pdf |
| spellingShingle | X. Weng G. L. Forster G. L. Forster P. Nowack P. Nowack P. Nowack P. Nowack A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 Atmospheric Chemistry and Physics |
| title | A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 |
| title_full | A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 |
| title_fullStr | A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 |
| title_full_unstemmed | A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 |
| title_short | A machine learning approach to quantify meteorological drivers of ozone pollution in China from 2015 to 2019 |
| title_sort | machine learning approach to quantify meteorological drivers of ozone pollution in china from 2015 to 2019 |
| url | https://acp.copernicus.org/articles/22/8385/2022/acp-22-8385-2022.pdf |
| work_keys_str_mv | AT xweng amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT glforster amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT glforster amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack amachinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT xweng machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT glforster machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT glforster machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 AT pnowack machinelearningapproachtoquantifymeteorologicaldriversofozonepollutioninchinafrom2015to2019 |