Artificial Intelligence Models for Mango Ripeness Detection: A Systematic Literature Review

Chumioque Capuñay M.M.; Reaño Dávila B.E.; Dios Castillo C.A. · Lecture Notes in Networks and Systems (2026) · DOI: 10.1007/978-3-032-20752-4_29

Resumen

The objective of this study is to determine which artificial intelligence models are the most effective for detecting mango maturity through a systematic review of literature. A comprehensive analysis was conducted using SCOPUS and Web Of Science (WOS) databases. The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) methodology was used to ensure a rigorous and structured review process. The results indicate that Machine Learning models, particularly PLSR and SVM, are highly effective, especially when analyzing the physical and chemical characteristics of mangoes. On the other hand, Convolutional Neural Networks (CNN) excel in visual evaluations. The integration of Machine Learning and Deep Learning models, together with multi-criteria evaluation, significantly improves the accuracy of mango maturity detection, potentially transforming traditional agricultural practices. This study highlights the importance of integrating various data formats (imagery, spectral data, and numerical data), along with multiple criteria, to enhance the performance of artificial intelligence models in agricultural applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad Tecnológica del Perú