Tang et al. (2026): Unequal economic impacts of climate change via idealized carbon dioxide removal: insights from deep learning
Bin Tang, Jianan Wei, Yimin Liu, Bian He, Wen Bao, Yi Yang, Wenguan Wang, Wenting Hu and Anmin Duan, IN: The Innovation, https://doi.org/10.1016/j.xinn.2026.101505
Rapidly reducing carbon dioxide (CO₂) levels is essential to meeting the Paris Agreement’s temperature targets.1,2 Previous assessments of CO₂ removal (CDR) have primarily focused on the hysteresis and invertibility of climate change itself,3–7 overlooking quantitative analysis of potential economic impacts of climate change via CDR. In this study, the authors first develop a powerful neural network model, EconClimNet, trained on decades of economic data from 1,554 sub-national regions worldwide and 111 climate indices derived from the fifth-generation ECMWF atmospheric reanalysis (ERA5). Compared to popular machine learning algorithms used in the Earth Science community, EconClimNet achieves superior performance in capturing the intricate relationship between climate indices and economic outcomes. On this basis, they apply EconClimNet to the outputs from idealized CO₂ ramp up and ramp down experiments from phase 6 of the Coupled Model Intercomparison Project (CMIP6).