Exploring the potential of machine learning for simulations of urban ozone variability

Machine learning (ML) has emerged as a powerful technique in the Earth system science, nevertheless, its potential to model complex atmospheric chemistry remains largely unexplored. Here, we applied ML to simulate the variability in urban ozone (O₃) over Doon valley of the Himalaya. The ML model, trained with past variations in O₃ and meteorological conditions, successfully reproduced the independent O₃ data (r² ~ 0.7). Model performance is found to be similar when the variation in major precursors (CO and NO_x) were included in the model, instead of the meteorology. Further the inclusion of both precursors and meteorology improved the performance significantly (r² = 0.86) and the model could also capture the outliers, which are crucial for air quality assessments. We suggest that in absence of high-resolution measurements, ML modeling has profound implications for unraveling the feedback between pollution and meteorology in the fragile Himalayan ecosystem.

Ozone chemistry and dynamics at a tropical coastal site impacted by the COVID-19 lockdown

The nationwide lockdown in India to curb the spread of Coronavirus disease 2019 (COVID-19) led to colossal reduction in anthropogenic emissions. Here, we investigated the impact of lockdown on surface ozone (O₃) and nitrogen dioxide (NO₂) over a tropical coastal station – Thumba, Thiruvananthapuram (8.5°N, 76.9°E). Daytime as well as night-time NO₂ showed reduction by 0.8 (40%) and 2.3 (35%) ppbv, respectively during the lockdown period of 25–30 March 2020 as compared with the same period of previous 3 years. Unlike many urban locations, daytime surface O₃ is found to be dramatically reduced by 15 ppbv (36%) with O₃ production rate being lower by a factor of 3 during the lockdown. Interestingly, a feature of O₃-hump during the onset of land breeze typically observed during 1997–1998 has reappeared with magnitude of 5–10 ppbv. A photochemical box model, capturing this feature, revealed that significant O₃ sustained till onset of land breeze over the land due to weaker titration with NO_x during lockdown. It is suggested that the transport of this O₃ rich air with onset of land breeze led to the observed hump. Our measurements unravel a remarkable impact of the COVID-19 lockdown on the chemistry and dynamics of O₃ over this tropical coastal environment.