Using Machine Learning Tools to Classify Sustainability Levels in the Development of Urban Ecosystems

Abstract

Different studies have been carried out to evaluate the progress made by countries and cities towards achieving sustainability to compare its evolution. However, the micro-territorial level, which encompasses a community perspective, has not been examined through a comprehensive forecasting method of sustainability categories with machine learning tools. This study aims to establish a method to forecast the sustainability levels of an urban ecosystem through supervised modeling. To this end, it was necessary to establish a set of indicators that characterize the dimensions of sustainable development, consistent with the Sustainable Development Goals. Using the data normalization technique to process the information and combining it in different dimensions made it possible to identify the sustainability level of the urban zone for each year from 2009 to 2017. The resulting information was the basis for the supervised classification. It was found that the sustainability level in the micro-territory has been improving from a low level in 2009, which increased to a medium level in the subsequent years. Forecasts of the sustainability levels of the zone were possible by using decision trees, neural networks, and support vector machines, in which 70% of the data were used to train the machine learning tools, with the remaining 30% used for validation. According to the performance metrics, decision trees outperformed the other two tools.

Assessment of the Sustainability of Productive Systems in Nariño, Colombia

“…Although these studies were conducted using different metrics and with urban populations, the results are consistent with those recorded in this study. The metrics used for understanding sustainability on a national, regional, or local scale are important for advancing the protection of non-renewable resources in the long term [46]. The findings presented in this study will inform the development of programs and policies designed to foster community advancement and facilitate the journey toward sustainable development.…”

“…In Bogotá, for example, values of 0.55 (on a 0-1 scale) have been recorded, placing it at rank 88 out of 106 cities studied around the world [45]. Machine learning algorithms used to calculate sustainability indices in Colombian cities reveal the panorama of sustainable development [46][47][48], which will allow the government to make more informed decisions. Although these studies were conducted using different metrics and with urban populations, the results are consistent with those recorded in this study.…”

Urban community governance and machine learning: practice and prospects for intelligent decision making

“…Smart urban community governance can provide more convenient and efficient public services and improve the quality of life of community residents. At the same time, to realize sustainable development, smart urban community governance can integrate sustainable development goals into urban community management and promote the green and sustainable development of the city [9][10].…”

Formal and Informal Communication Network Patterns in Continuing Information Fulfillment Among Urban Television Reporters

“…The purpose of this study, that in order to streamline the tasks of a reporter, in meeting the information needs of urban communities, it is necessary to build a strong and sustainable network. Sustainable development requires the normalization of information, subsequently carrying out information processes and identifying the level of sustainability of urban zones annually (Isabel Molina-Gómez et al, 2020). Network and information system integration can improve sustainability and security (Ceccarini et al, 2021).…”