Apocalypse Now? Projecting CO2 Emissions with Neural Networks

We project carbon dioxide emissions through 2100 using a reduced-form model and national-level scenarios for per capita gross domestic product from the Shared Socioeconomic Pathways (SSPs). We propose a novel neural network-based panel data model that combines country fixed effects with a long short-term memory (LSTM) recurrent neural network regression component that takes into account time implicitly by building memory and letting model predictions depend on the income path of a country. For scenarios with low socioeconomic challenges for mitigation SSP1 and SSP4, our emissions projections appear consistent with baseline projections from structural integrated assessment models (IAMs) that are meant to describe future developments in absence of new climate policies. For scenarios with medium and high socioeconomic challenges for mitigation SSP2, SSP3, and SSP5, our emissions projections appear the most consistent with mitigation projections from IAMs that target a forcing level of 6.0 W/m² by 2100.