Net-Zero: A Comparative Study on Neural Network Design for Climate-Economic PDEs Under Uncertainty
This work addresses computational bottlenecks for policymakers in climate modeling, though it is incremental as it focuses on benchmarking existing neural network methods rather than introducing a new paradigm.
The paper tackled the computational challenges of solving high-dimensional optimal control problems in climate-economic models under uncertainty by benchmarking neural network architectures against finite-difference solutions, finding that appropriate architecture selection significantly improves solution accuracy and computational efficiency.
Climate-economic modeling under uncertainty presents significant computational challenges that may limit policymakers' ability to address climate change effectively. This paper explores neural network-based approaches for solving high-dimensional optimal control problems arising from models that incorporate ambiguity aversion in climate mitigation decisions. We develop a continuous-time endogenous-growth economic model that accounts for multiple mitigation pathways, including emission-free capital and carbon intensity reductions. Given the inherent complexity and high dimensionality of these models, traditional numerical methods become computationally intractable. We benchmark several neural network architectures against finite-difference generated solutions, evaluating their ability to capture the dynamic interactions between uncertainty, technology transitions, and optimal climate policy. Our findings demonstrate that appropriate neural architecture selection significantly impacts both solution accuracy and computational efficiency when modeling climate-economic systems under uncertainty. These methodological advances enable more sophisticated modeling of climate policy decisions, allowing for better representation of technology transitions and uncertainty-critical elements for developing effective mitigation strategies in the face of climate change.