The Spatiotemporal Prediction Model of Urban Carbon Emissions Based on Graph Neural Networks

Global warming is becoming increasingly serious because of excessive carbon dioxide emissions, which have caused damage to ecosystems, biodiversity, and human economic activities, prompting countries to pay attention to carbon emissions (CE) control. Accurate prediction of CE is crucial for energy conservation and emission reduction, as it can inform the formulation of effective environmental policies. However, the existing methods are mostly based on measurement data or post-assessment calculation of power flow results, which cannot accurately give the power CE factors of different load nodes in the future, and it is difficult to guide low-carbon regulation on the user side. In view of this, this article proposes a spatiotemporal prediction model of urban CE based on a graph neural network.