Aprendizaje automático para la predicción de la precipitación de lluvias en la ciudad de Iquitos

This research paper addresses the improvement of accuracy in precipitation prediction in the city of Iquitos through the use of machine learning techniques. The central problem lies in the ineffectiveness of traditional methods for capturing complex rainfall patterns in the Amazon region. The object...

Descripción completa

Detalles Bibliográficos
Autores: Alegria Rodriguez, Jhonatan Waldemar, Melgarejo Mariño, Jaime
Tipo de recurso: tesis de maestría
Fecha de publicación:2025
País:Perú
Institución:Universidad Nacional De La Amazonía Peruana
Repositorio:UNAPIquitos-Institucional
Idioma:español
OAI Identifier:oai:repositorio.unapiquitos.edu.pe:20.500.12737/11510
Acceso en línea:https://hdl.handle.net/20.500.12737/11510
Access Level:acceso abierto
Palabra clave:Aprendizaje automático
Predicción meteorológica
Algoritmos de predicción
Precipitación atmosférica
Lluvia
https://purl.org/pe-repo/ocde/ford#2.02.04
Descripción
Sumario:This research paper addresses the improvement of accuracy in precipitation prediction in the city of Iquitos through the use of machine learning techniques. The central problem lies in the ineffectiveness of traditional methods for capturing complex rainfall patterns in the Amazon region. The objectives of the study include developing a predictive model using the RandomForestClassifier algorithm, analyzing historical weather data, and evaluating the accuracy of the model by comparing it with traditional methods. The methodology used is based on the collection and analysis of data provided by SENAMHI, followed by the implementation and validation of the predictive model. The results indicate a significant improvement in the accuracy of the predictions with the proposed model, reaching an accuracy of 0. 91 and an average accuracy of 0. 862 in the cross-validation. The findings suggest that the use of machine learning can overcome the limitations of traditional methods, providing more accurate and useful predictions for resource management and planning in Iquitos.