Centre de documentation
scientifique

Identification of urban sectors prone to solid waste accumulation: A machine learning approach based on social indicators / Luis Izquierdo-Horna in Computers, Environment and Urban Systems, vol 96 (September 2022)  

Public [article]  inComputers, Environment and Urban Systems > vol 96 (September 2022) . - n° 101834 Titre : Identification of urban sectors prone to solid waste accumulation: A machine learning approach based on social indicators Type de document : Article/Communication Auteurs : Luis Izquierdo-Horna, Auteur ; Miker Damazo, Auteur ; Deyvis Yanayaco, Auteur Année de publication : 2022 Article en page(s) : n° 101834 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] apprentissage automatique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] déchet [Termes IGN] densité de population [Termes IGN] données socio-économiques [Termes IGN] Pérou [Termes IGN] régression logistique [Termes IGN] zone urbaine Résumé : (auteur) In the last decades, the accumulation of municipal solid waste in urban areas has become a latent concern in our society due to its implications for the exposed population and the possible health and environmental issues it may cause. In this sense, this research study contributes to the timely identification of these sectors according to the anthropogenic characteristics of their residents as dictated by 10 social indicators (i.e., age, education, income, among others) sorted into three assessment categories (sociodemographic, sociocultural, and socioeconomic). Then, the data collected was processed and analyzed using two machine learning algorithms (random forest (RF) and logistic regression (LR)). The primary information that fed the machine learning model was collected through field visits and local/national reports. For this research, the Puente Piedra and Chaclacayo districts, both located in the province of Lima, Peru, were selected as case studies. Results suggest that the most relevant social indicators that help identifying these sectors are monthly income, consumption patterns, age, and household population density. The experiments showed that the RF algorithm has the best performance, since it efficiently identified 63% of the possible solid waste accumulation zones. In addition, both models were capable of determining different classes (AUC – RF = 0.65, AUC – LR = 0.71). Finally, the proposed approach is applicable and reproducible in different sectors of the national Peruvian territory. Numéro de notice : A2022-512 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1016/j.compenvurbsys.2022.101834 Date de publication en ligne : 10/06/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2022.101834 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101052 [article]