Retail Distribution using Georeferenced Systems and Genetic Algorithms for Product Delivery. Case study.

• Autores: Taquía Gutiérrez, José Antonio, García López, Yván Jesús
• Formato: artículo
• Fecha de Publicación: 2023
• Institución: Universidad de Lima
• Repositorio: ULIMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.ulima.edu.pe:20.500.12724/19527
• Enlace del recurso: https://hdl.handle.net/20.500.12724/19527; https://doi.org/10.25103/jestr.165.03
• Nivel de acceso: acceso abierto
• Materia: Genetic algorithms; Physical distribution of goods; Food; Distribución comercial; Algoritmos genéticos; Logística empresarial; Alimentos; Lima (Perú); https://purl.org/pe-repo/ocde/ford#2.02.03

This research will address air pollution, a severe problem in all world cities, because it negatively affects people's health and deteriorates the ecosystem. NO2 is a gas linked to acid rain formation and various reactions with greenhouse gases. Meteorological variables influence the behavior of tropospheric NO2 concentration. During the period of confinement due to the COVID-19 pandemic, the concentration levels of pollutants dropped abruptly, which meant relief for the ecosystem. The application of Time Series models allows us to graphically identify the concentration of contaminants in various areas and make accurate forecasts to mitigate environmental problems in the future. The research analysis shows that the SARIMA model effectively forecasts the pollutant concentration in the San Borja and San Martin de Porres districts in Lima. Error tests such as R2, MAE, MAPE, MSE, and RSME, as well as Dickey-Fuller Test, AIC, BIC, Skew, and Kurtosis, provide information on the performance of the SARIMA model and show that it is the most suitable.