Global, high-resolution mapping of tropospheric ozone – explainable machine learning and impact of uncertainties

• Published in: Geoscientific Model Development Vol. 15; no. 11; pp. 4331 - 4354
• Main Authors: Betancourt, Clara, Stomberg, Timo T, Edrich, Ann-Kathrin, Patnala, Ankit, Schultz, Martin G, Roscher, Ribana, Kowalski, Julia, Stadtler, Scarlet
• Format: Journal Article
• Language: English
• Published: Katlenburg-Lindau Copernicus GmbH 03.06.2022; Copernicus Publications
• Subjects: Air pollution; Air quality; Algorithms; Altitude; Benchmarks; Datasets; Distribution; Emission measurements; Emissions; Geospatial data; Greenhouse effect; Greenhouse gases; High resolution; Learning algorithms; Machine learning; Mapping; Methods; Modelling; Neural networks; Outdoor air quality; Ozone; Ozone concentration; Ozone measurements; Photochemistry; Proxies; Radiation; Resolution; Spatial data; Spatial distribution; Statistics; Troposphere; Tropospheric ozone; Uncertainty; Vegetation; Workflow
• ISSN: 1991-9603; 1991-959X; 1991-962X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-15-4331-2022

Tropospheric ozone is a toxic greenhouse gas with a highly variable spatial distribution which is challenging to map on a global scale. Here, we present a data-driven ozone-mapping workflow generating a transparent and reliable product. We map the global distribution of tropospheric ozone from sparse, irregularly placed measurement stations to a high-resolution regular grid using machine learning methods. The produced map contains the average tropospheric ozone concentration of the years 2010-2014 with a resolution of 0.1.sup." x 0.1.sup." . The machine learning model is trained on AQ-Bench ("air quality benchmark dataset"), a pre-compiled benchmark dataset consisting of multi-year ground-based ozone measurements combined with an abundance of high-resolution geospatial data.