Forecasting emissions through Kaya identity using Neural Ordinary Differential Equations

TL;DR

This paper introduces a Neural ODE-based model to forecast carbon emissions using Kaya identity indicators, demonstrating its effectiveness over traditional methods and its potential to inform policy decisions.

Contribution

The paper presents a novel Neural ODE approach for modeling emissions based on Kaya identity variables, outperforming baseline statistical models like VAR.

Findings

Neural ODE model achieved better predictive performance than VAR.

The approach provides insights useful for policymakers.

Model accurately predicts country-level emission indicators.

Abstract

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