Machine learning models for disease classification of Solanum tuberosum: A Systematic Review of the Literature

Abstract

Solanum tubersoum diseases, considered one of the very important factors in its production, influence the quality of the final products and also the market for these products. Currently, classification processes are taking a lot of interest in agriculture globally, as are the analyzes of the different defects that Solanum tuberosum presents. For this reason, researchers are developing new algorithms for disease detection using artificial intelligence technologies, in order to optimize the detection of diseases or defects. This work presents an analysis of research on the construction of machine learning models for the classification of diseases of Solanum tuberosum, also reviewing which diseases are the most common and impactful of this product and determining which of the trained models are the most efficient in the classification of diseases of this product and help researchers in the future build automatic detection and classification systems for diseases and defects of Solanum tuberosum.