Machine Learning's contribution to mango cultivation and production (#862)

Authors

Capuñay-Uceda, Oscar Efraín

Villegas-Cubas, Juan Elías

Otake, Luis

Abstract

This research explores and evaluates the application of Machine Learning techniques in the field of agriculture, with a particular focus on mango cultivation and production. The research addresses traditional challenges in the identification, classification, and detection of diseases in mango crops, areas where manual assessments have proven to be error-prone and subjective. The paper highlights how advanced techniques, such as convolutional neural networks and transfer learning, have significantly improved accuracy and efficiency in these critical processes, overcoming the limitations of traditional methods. Several methodologies are presented, ranging from automatic fruit identification using computer vision to non-destructive fruit quality assessment using colour and X-ray images. The results show that the implementation of these technologies has led to an improvement in quality standards and product competitiveness in global markets, consolidating ML as an indispensable tool for the sustainable development of mango cultivation. In conclusion, the study underlines the need to integrate advanced technologies in agriculture to improve both efficiency and quality of mangoes, suggesting that these innovations are key to address contemporary challenges in agricultural production.