Potential of VIS/NIR spectroscopy to detect and predict bitter pit in ‘Golden Smoothee’ apples

Aim of study: A portable VIS/NIR spectrometer and chemometric techniques were combined to identify bitter pit (BP) in Golden apples.Area WorldwideMaterial methods: Three different classification algorithms – linear discriminant analysis (LDA), quadratic (QDA) support-vector machine (SVM) –were used two experiments. In experiment #1, measurements carried out at postharvest on apples previously classified according 3 classes (class 1: non-BP; class 2: slight symptoms; 3: severe symptoms). #2, healthy collected before harvest determinate the capacity for detecting BP prior appearance symptoms.Main results: experiement spectroscopy showed great potential pitted detection with visibly symptoms (accuracies 75–81%). The classifier LDA performed better than multivariate non-linear QDA SVM classifiers discriminating between apples. accuracy predict visible decreased 44–57%.Research highlights: identification through may be due chlorophyll degradation and/or changes intercellular water fruit tissue.