The area of estimating emissions has developed quicky in the context of COVID. AI can be used to infer emissions, or even ‘potential’ emissions – for example what would have been observed, what energy use would have been… etc, in the absence of lockdown measures.

To do this, different types of activity statistics are available, such as: mobility or traffic counts, flight counts and energy network fluxes.

Importantly, these applications do not substitute to, but will feed into emissions estimates – rather than applying inverse modelling of atmospheric concentrations starting from static climatological a priori estimates, having emissions that are adjusted depending on actual temperature and other data will certainly be decisive. There could be examples about pollutants / air quality and GHG / CO2.

There has been a recent CAMS study using machine learning (gradient boosting) to study the impact of Covid on emission reductions in relation to electricity demand.

Featured Educators

• Marc Guevara
• Sara Aparicio

‍

‍