Sistema de predicción en la producción de arándanos

Abstract

Blueberry production in Ecuador faces significant challenges due to climate variability and the need to optimize the use of agricultural resources. This study aims to develop a prediction system for blueberry production at Ilaru, using machine learning techniques such as Support Vector Machines (SVM) and Random Forests (RF). Climate, soil, and agricultural management data were collected and analyzed to identify the most influential variables in blueberry production. The methodology included creating a dataset integrating information from various sources and training predictive models. The results obtained show a significant improvement in prediction accuracy, allowing the company to make more informed and efficient decisions regarding resource management and production planning. In conclusion, the proposed system not only increases blueberry productivity but also promotes more sustainable and responsible agricultural practices.