Sustainable development goals: classifying European countries through self-organizing maps Cristina Davino University of Naples Federico II, Italy Nicola D'Alesio University of Campania Luigi Vanvitelli, Italy This is a section of ASA 2022 Data-Driven Decision Making(DOI: 10.36253/979-12-215-0106-3) by Enrico di Bella, Luigi Fabbris, Corrado Lagazio Firenze University Press Firenze 2023 https://doi.org/10.36253/979-12-215-0106-3.17

Available for academic research purposes

Open Access

Copyright Author(s)

Content licence CC BY 4.0

Metadata licence CC0 1.0

This is original content, published for academic research purposes

 Digital edition XML powered by Booksflow

Environmental sustainability is one of the main goals of all countries in the world. Sustainable Development Goals (SDGs) have been proposed by the United Nations in 2015. The purpose of this paper is to explore if and how European countries achievethe goals of environmental sustainability (tracked by the SDGs number 13, 14, and 15). In particular, SDG 13 refers to climate change and its impacts; SDG 14 refers to the conservation of water and marine resources while the last one; SDG 15 deals with the preservation of forests. The reference methodology of the paper are the Self-Organizing Maps proposed by Kohonen in 1982 as an unsupervised clustering method in the framework of artificial neural networks. The proposed analysis considers the 23 indicators related to the three SDGs of environmental sustainability and aims to explore and identify groups of countries with similar characteristics through a dimensionality reduction. Such clusters will be visually represented in a two-dimensional map. The proposed analysis considers the most recent data for all the above SDGs, which is 2018, with the aim of classifying the countries in terms of environmental sustainability and highlighting possible implications for policymakers. An analysis of the network accuracy is shown, using appropriate indicators. These results allow us to see which countries have achieved these goals and how they have deviated from them.

 Environmental Sustainability Artificial Neural Networks Self-Organizing Maps Sustainable Development Goals

It is available online at https://doi.org/10.36253/979-12-215-0106-3.17

References European Commission (2020). Sustainable development in the European Union — Overview of progress towards the SDGs in an EU context — 2020 edition. G.H. Brundtland et al. (World Commission on Environment and Development, 1987) in Our Common Future, Oxford University Press, Oxford. Goodland, R., (1995). The concept of environmental sustainability. Annual review of ecology and systematics, 26(1), pp. 1-24. Hák, T., Janoušková, S., Moldan, B. (2016). Sustainable Development Goals: A need for relevant indicators. Ecological indicators, 60, pp. 565-573. Hueting, R., Reijnders, L. (1998) Sustainability is an objective concept. Ecological economics, 27 (2), pp. 139-148. Husson, F., Josse, J., Le, S., Mazet, J., & Husson, M. F. (2016). Package ‘factominer’. An R package, 96, 698. Jenkins, I., Schröder, R. (2013). Sustainability in Tourism A Multidisciplinary Approach, Springer Science & Business Media, 1. Boelaert J., Ollion, E., Sodoge, J. (2021). aweSOM: Interactive Self-Organizing Maps. R package version 1.2. https://CRAN.R-project.org/package=aweSOM Kassambara, A., Mundt, F. (2017). Package ‘factoextra’. Extract and visualize the results of multivariate data analyses, 76(2). Kohonen, T. (1982a). Clustering, Taxonomy, and Topological Maps of Patterns in Sixth International Conference on Pattern Recognition, Munich, Germany, Oct. 19-22, pp. 114-128. Kohonen, T. (1982b). Self-organized formation of topologically correct feature maps. Biol. Cybern. 43, pp. 59–69. Kohonen, T. (1990). The self-organizing map. Proceedings of the IEEE, 78(9), pp. 1464-1480. Matsushita, H., Nishio, Y. (2010). Batch-Learning Self-Organizing Map with Weighted Connections avoiding false-neighbor effects in The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1-6.