Modeling national decarbonization capabilities using Kohonen maps

• Autor(a) principal: Zhytkevych, O.
• Data de Publicação: 2022
• Outros Autores: Brochado, A.
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/28849
• topic: Carbon dioxide (CO2); Emission target; Decarbonization; Clustering; Self-organizingmap; Neural network

This study sought to develop a method to cluster countries based on their decarbonization capabilities and to determine how these nations’ reduction of carbon dioxide (CO2) emissions has evolved over time. CO2 emissions clusters were identified using 11 indicators that measure both direct and indirect CO2 emissions, differentiating countries by their economic and population growth, energy consumption, and CO2 emission level. The panel data included 39 countries over the 10-year period of 2012–2021. The clustering was based on such type of neural networks as Kohonen self-organizing maps. This type of model facilitated grouping countries by similar decarbonization capabilities and economic development. The findings reveal that Norway and Sweden are the leaders in creating climate-resilient economies among the 39 countries analyzed. The analysis carried out can help other countries establish benchmarks for improving their own internal decarbonization activities based on leader nations’ strategies and borrowing their best practices for more efficient results. This study thus contributes to the literature regarding decarbonization activities by offering a multi-country dynamic clustering method using Kohonen maps.