Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13
This study aims to enhance the evaluation of climate-related Sustainable Development Goals (SDGs), with a focus on SDG 13 (''Climate Action''), using Artificial Neural Networks (ANNs) methods. It examines seven critical 2023 SDG Global Index indexes to model and predict environme...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Sustainable Futures |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666188825000097 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595778011398144 |
|---|---|
| author | Cosimo Magazzino Zakaria Zoundi |
| author_facet | Cosimo Magazzino Zakaria Zoundi |
| author_sort | Cosimo Magazzino |
| collection | DOAJ |
| description | This study aims to enhance the evaluation of climate-related Sustainable Development Goals (SDGs), with a focus on SDG 13 (''Climate Action''), using Artificial Neural Networks (ANNs) methods. It examines seven critical 2023 SDG Global Index indexes to model and predict environmental performance. The innovative use of ANNs allows for capturing complex and non-linear interactions among sustainability indicators, surpassing traditional linear models. A key component of the research is the application of Garson's algorithm, which identifies the relative importance of each of the seven indexes in influencing climate outcomes. The study optimizes the ANN's parameters through a grid search, ensuring robust and precise predictions. This research offers valuable insights for policymakers and researchers aiming to improve climate action strategies by providing a more nuanced understanding of the factors driving environmental performance. The findings demonstrate the potential of advanced AI techniques in refining sustainability assessments and guiding more effective environmental policies. Key policy insights drawn from the study include expanding interventions aimed at promoting more sustainable consumption and production policies, given the significant contribution of SDG 12 in driving climate goals; reviewing the methods for measuring economic growth to account for the planetary crises; and increasing the use of AI tools to guide policymaking. |
| format | Article |
| id | doaj-art-8de15b8e39a5451d923669606d64d913 |
| institution | Kabale University |
| issn | 2666-1888 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Sustainable Futures |
| spelling | doaj-art-8de15b8e39a5451d923669606d64d9132025-01-18T05:05:14ZengElsevierSustainable Futures2666-18882025-06-019100439Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13Cosimo Magazzino0Zakaria Zoundi1Department of Political Science, Roma Tre University, Rome, Italy; Economic Research Center, Western Caspian University, Baku, Azerbaijan; Corresponding author.School of International Development and Global Studies, University of Ottawa, Ottawa, CanadaThis study aims to enhance the evaluation of climate-related Sustainable Development Goals (SDGs), with a focus on SDG 13 (''Climate Action''), using Artificial Neural Networks (ANNs) methods. It examines seven critical 2023 SDG Global Index indexes to model and predict environmental performance. The innovative use of ANNs allows for capturing complex and non-linear interactions among sustainability indicators, surpassing traditional linear models. A key component of the research is the application of Garson's algorithm, which identifies the relative importance of each of the seven indexes in influencing climate outcomes. The study optimizes the ANN's parameters through a grid search, ensuring robust and precise predictions. This research offers valuable insights for policymakers and researchers aiming to improve climate action strategies by providing a more nuanced understanding of the factors driving environmental performance. The findings demonstrate the potential of advanced AI techniques in refining sustainability assessments and guiding more effective environmental policies. Key policy insights drawn from the study include expanding interventions aimed at promoting more sustainable consumption and production policies, given the significant contribution of SDG 12 in driving climate goals; reviewing the methods for measuring economic growth to account for the planetary crises; and increasing the use of AI tools to guide policymaking.http://www.sciencedirect.com/science/article/pii/S2666188825000097Environmental sustainability indicatorsSustainable development goalsClimate actionArtificial neural networks |
| spellingShingle | Cosimo Magazzino Zakaria Zoundi Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 Sustainable Futures Environmental sustainability indicators Sustainable development goals Climate action Artificial neural networks |
| title | Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 |
| title_full | Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 |
| title_fullStr | Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 |
| title_full_unstemmed | Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 |
| title_short | Enhancing climate action evaluation using artificial neural networks: An analysis of SDG 13 |
| title_sort | enhancing climate action evaluation using artificial neural networks an analysis of sdg 13 |
| topic | Environmental sustainability indicators Sustainable development goals Climate action Artificial neural networks |
| url | http://www.sciencedirect.com/science/article/pii/S2666188825000097 |
| work_keys_str_mv | AT cosimomagazzino enhancingclimateactionevaluationusingartificialneuralnetworksananalysisofsdg13 AT zakariazoundi enhancingclimateactionevaluationusingartificialneuralnetworksananalysisofsdg13 |