Future Co‐Occurrences of Hot Days and Ozone‐Polluted Days Over China Under Scenarios of Shared Socioeconomic Pathways Predicted Through a Machine‐Learning Approach. Issue 6 (2nd June 2022)

• Record Type: Journal Article
• Authors: Gong, Cheng; Wang, Ye; Liao, Hong; Wang, Pinya; Jin, Jianbing; Han, Zhiwei
• Is Part Of: Earth's future. Volume 10:Issue 6(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-02
• Subjects: ozone polluted days -- hot days -- random forest algorithm; Environmental sciences -- Periodicals; Environmental sciences; Periodicals; 550
• DOI: 10.1029/2022EF002671
• Languages: English
• ISSNs: 2328-4277

Abstract

Abstract: The warming climate increases the probability of hot days, which leads to a penalty effect of increasing ozone (O3 )‐polluted days in polluted regions. Here, we established a random forest algorithm to predict future probabilities of O3 exceedance ( P ) during hot days and further examined the future co‐occurrences of O3 ‐polluted days and hot days under two different scenarios of Shared Socioeconomic Pathways (SSPs) 1‐2.6 and 5‐8.5 for 2030–2050s. Ground‐level observations, simulated O3 ‐temperature sensitivities in the GEOS‐Chem model, multimodel seasonal‐mean O3 concentrations and daily maximum temperature from the sixth Coupled Model Intercomparison Project (CMIP6), leaf area index from reanalyzed data, and local geographical information were comprehensively utilized. Evaluations showed that the algorithm captured the spatial patterns of present‐day P values well with a correlation coefficient of 0.92 over China. Results showed that the strong reductions in anthropogenic emissions under SSP 1‐2.6 significantly reduced the risks of O3 exceedance during hot days nationwide from 3.7 days in the 2030s to 3.0 days in the 2050s. However, the SSP 5‐8.5 scenario witnessed more frequent co‐occurrences of O3 ‐polluted days and hot days over the 2030–2050s with nationally averaged values from 4.5 to 6.4 days. Our results highlight the co‐benefits of reducing anthropogenic emissions to alleviate the composite risks of extreme weather events and air‐polluted days in the future. Plain Language Summary: Temperature is generally considered as the most important meteorological factor that influences ground‐level ozone (O3 ) concentrations. A warmer climate is highly likely to lead to frequent occurrence of hot days, which could further increase ozone‐polluted days in regions with high anthropogenic emissions. The co‐occurrences of O3 ‐polluted days and hot days lead to composite risks to human health, but how such co‐occurrences will change in the future is rarely examined. Here, we established a novel machine‐learning approach by using a random forest algorithm to quantify the probability of O3 exceedance ( P ) during hot days and then predicted the future co‐occurrence of O3 ‐polluted days and hot days under two different future emission scenarios (Shared Socioeconomic Pathways [SSP]1‐2.6 and SSP5‐8.5). Multisource data, including ground‐level observations, reanalyzed data, GEOS‐Chem simulations, and multimodel outputs from Coupled Model Intercomparison Project, were comprehensively utilized. We found that the random forest algorithm was capable to derive a reasonable pattern of P values over China. Composite risks of O3 exceedance during hot days are projected to be reduced significantly in the future under the SSP 1‐2.6 scenario, whereas to keep increasing until the 2050s under the SSP 5‐8.5 scenario. Key Points: A machine‐learning approach was developed to quantify the climatological risk level of ozone (O3 ) pollution during hot days over China Co‐occurrence of O3 ‐polluted days and hot days reduced from 3.7 days in 2030s to 3.0 days in 2050s over China under the Shared Socioeconomic Pathway (SSP) 1‐2.6 scenario The SSP 5‐8.5 scenario led to higher co‐occurrences of O3 ‐polluted days and hot days in 2050s, especially in North China and northwest China