Comparison of the machine learning and aquacrop models for quinoa crops

• Autores: Chumbe Llimpe, Rossy Jackeline, Silva Paucar, Stefany Dennis
• Formato: tesis de grado
• Fecha de Publicación: 2024
• Institución: Universidad de Lima
• Repositorio: ULIMA-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.ulima.edu.pe:20.500.12724/22481
• Enlace del recurso: https://hdl.handle.net/20.500.12724/22481
• Nivel de acceso: acceso abierto
• Materia: Quinua; Riego; Agua; Aprendizaje automático; https://purl.org/pe-repo/ocde/ford#2.11.04

One of the main causes of low crop efficiency in Peru is poor management of water resources; that is why the main objective of this article is to estimate the amount of irrigation water required in quinoa crops through a comparison between the machine learning and Aquacrop models. For the development of this study, meteorological data from the province of Jauja and descriptive data of quinoa crops were processed and a simulation period was established from June to December. From the simulation carried out, it was determined that the best model to predict the required irrigation water is the Ada Boost model in which it was observed that the mean and standard deviation of the Ada Boost models (Mean = 19.681 and Std. Dev. = 4.665) behave similarly to AquaCrop (Mean = 19.838 and Std. Dev. = 5.04). In addition, the result of the analysis of variance (ANOVA) was that the AdaBoost model has the best p-value indicator with a value of 0.962 and a smaller margin of error in relation to the MAE indicator with a value of 0.629. Likewise, it was identified that for the simulation period of 190 days, 472.35mm of water was required to carry out the irrigation process in red quinoa crops.