Net-Zero: A Comparative Study on Neural Network Design for Climate-Economic PDEs Under Uncertainty

2025/05/19 by Carlos Rodriguez-Pardo, Louis Daumas, Rodriguez-Pardo, Carlos +5 · 1 voice
Computer Science · Economics, Econometrics and Finance · Mathematics · #68T07 (Primary) 35Q91 #91B76 (Secondary) #Analysis of PDEs (math.AP) #Artificial Intelligence (cs.AI) #Capital Investment and Risk Analysis #Climate Change Policy and Economics #FOS: Computer and information sciences #FOS: Mathematics #I.2.1 #I.5.1 #J.4 #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Performance (cs.PF) #Sustainable Finance and Green Bonds #cs.AI #cs.LG #cs.NE #cs.PF #math.AP

paper · pdf · doi:10.48550/arxiv.2505.13264

openalex publication_date 2025/05/19 · arxiv published 2025/05/19 · arxiv updated 2025/05/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• A Deep Learning Analysis of Climate Change, Innovation, and Uncertainty
• Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next
• Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next
• Choose a Transformer: Fourier or Galerkin
• Fourier Neural Operator for Parametric Partial Differential Equations
• Implicit Neural Representations with Periodic Activation Functions
• Extensions of the Deep Galerkin Method
• Quantifying the Carbon Emissions of Machine Learning
• Attention Is All You Need
• Deep Residual Learning for Image Recognition
• Highway Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Long Short-Term Memory

Discussions

• 📯 arxiv.org/abs/2505.13264 [bsky, 3 points, 0 comments]

Related

• A Deep Learning Analysis of Climate Change, Innovation, and Uncertainty
• Solving stochastic climate-economy models: A deep least-squares Monte Carlo approach
• Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling
• The Importance of Architecture Choice in Deep Learning for Climate Applications
• PCE-PINNs: Physics-Informed Neural Networks for Uncertainty Propagation in Ocean Modeling