Predicción de consumo del servicio de agua potable basado en métodos de Machine Learning en la ciudad de Iquitos

• Autores: Vasquez Coquinche, Jason Robie Jhunior, Pinedo Flores, Harold
• Formato: tesis de grado
• Fecha de Publicación: 2023
• Institución: Universidad Nacional De La Amazonía Peruana
• Repositorio: UNAPIquitos-Institucional
• Lenguaje: español
• OAI Identifier: oai:repositorio.unapiquitos.edu.pe:20.500.12737/9935
• Enlace del recurso: https://hdl.handle.net/20.500.12737/9935
• Nivel de acceso: acceso abierto
• Materia: Redes neuronales (Informática); Aprendizaje automático; Modelos de simulación; Predicción; Consumo de agua; Agua potable; https://purl.org/pe-repo/ocde/ford#2.02.04

The study developed and evaluated a prediction model for drinking water consumption in the city of Iquitos, using a sample of size 288 obtained from historical data from SENAMHI, INEI, and SEDALORETO. A quantitative, applied, and non-experimental correlational approach was used to build and test an Artificial Neural Network (ANN) model, comparing model results with historical consumption data. The accuracy of the model was evaluated using algorithms and statistical models in MATLAB, using indicators such as Mean Squared Error (MSE), Correlation Coefficient (R), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2). The results showed that the RNA model presented a high performance in terms of precision in the training, validation and test set, with MSEs of 99736607.27x10-8, 283364279.46x10-8 and 373108841.22x10-8, and correlation coefficients (R) of 0.996463, 0.986462 and 0.984320, respectively. The prediction model for drinking water consumption in the city of Iquitos showed a MAPE of 1.72%, a correlation of 0.909 and a coefficient of determination (r2) of 0.826, which suggests a strong positive relationship between the variables and a capacity acceptable value of the model to accurately predict drinking water consumption. In conclusion, the Machine Learning model used proved to be effective in predicting drinking water consumption in the city of Iquitos, which can improve efficiency in resource management and guarantee an adequate supply of drinking water to the population.