Optimizing Visual Estimation of Peanut Late Leaf Spot Severity with Online Training Sessions and Standard Area Diagrams

• DOI: 10.31219/osf.io/wzng4
• Publication Date: 2024-08-26T20:51:00Z
• Authors: Luis Ignacio Cazón; Juan Andrés Paredes; Noelia Rosa González; Cinthia Conforto; Lautaro Suarez; Emerson Medeiros ...
• Keywords: Training set

Quantification of plant disease severity is key for pathology research, particularly in the evaluation control measures. Visual estimation remains widely used, especially field. Training sessions and use standard area diagram sets (SADs) are known to enhance rater accuracy. We aimed quantify compare benefits these tools, either used alone or combination, when visually assessing peanut late leaf spot severity. designed validated SADs aid also evaluated training tool TraineR2, a web-based app that contains actual images with Our results show both TraineR2 significantly improved accuracy after their use. For gains overall (ρc from 0.82 0.91) precision (Pearson's r 0.73 0.88) were slightly lower compared those obtained 0.89 0.96 Pearson's 0.85 0.95). When combined, was 0.97, 0.96, values similar achieved using alone. Regarding inter-rater reliability, based on intraclass correlation coefficient (ICC), together resulted an ICC 0.95, which higher than (0.93) (0.84). study confirms utility combining improving assessments.