Forecasting emissions through Kaya identity using Neural Ordinary Differential Equations
This work addresses forecasting emissions for policymakers, but it appears incremental as it applies an existing method to a specific domain.
The authors tackled the problem of forecasting carbon emissions indicators at the country level using a Neural ODE model based on the Kaya identity, and they reported good performance compared to a VAR baseline.
Starting from the Kaya identity, we used a Neural ODE model to predict the evolution of several indicators related to carbon emissions, on a country-level: population, GDP per capita, energy intensity of GDP, carbon intensity of energy. We compared the model with a baseline statistical model - VAR - and obtained good performances. We conclude that this machine-learning approach can be used to produce a wide range of results and give relevant insight to policymakers