Title: EU's green taxonomy analysis incorporated with energy-mix by machine learning for climate mitigations

Authors: Sewon Lee; Changho Han; Chang Hyun Baek; Tae Ho Woo

Addresses: School of Mechanical Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, South Korea ' School of Mechanical Engineering, Korea University, Anam-dong, Seongbuk-gu, Seoul 02841, South Korea ' Division of Mechanical and Control Engineering, The Cyber University of Korea, 106 Bukchon-ro, Jongno-gu, Seoul 03051, South Korea ' Division of Mechanical and Control Engineering, The Cyber University of Korea, 106 Bukchon-ro, Jongno-gu, Seoul 03051, South Korea

Abstract: This paper analyses the European Union (EU) 's green taxonomy incorporated with energy-mix by nonlinear algorithms where the uncertainties of the energy-mix are described by the artificial intelligence (AI). There are simulations of dynamical configuration of the EU's taxonomy incorporated with the energy-mix. The trends of precision, recall, specificity, and accuracy are converged after the 30th year. The comparisons are done using a new factor of energy-mix consideration. The figure shows the comparison with and without energy-mix. The differences between two values are bigger around the 20th and 30th years and it is not much near the 50th year. This analysis of the EU's green taxonomy could provide solutions for optimising the environment and energy production.

Keywords: climate; taxonomy; energy-mix; artificial intelligence; AI; machine learning; ML.

DOI: 10.1504/IJGW.2023.131406

International Journal of Global Warming, 2023 Vol.30 No.3, pp.296 - 308

Received: 16 Oct 2022
Received in revised form: 11 Dec 2022
Accepted: 11 Dec 2022
Published online: 09 Jun 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article