Non-destructive estimation of the leaf weight and leaf area in cacao (Theobroma cacao L.)

Regression models to predict leaf area and leaf weight in cacao (Theobrama cacao L.) were fitted using leaves from cultivated plants under nursery conditions and from plants of commercial plantations, both located in the Amazon Investigations Center CIMAZ at Macagual, Caquetá, Colombia. A total of 2895 leaves were collected in such a way to cover a wide range of leaf sizes. Width, length, weight, and leaf area were measured for each leaf. The total number of leaves was randomly divided into training and validation sets. The training set was used for model fitting and selection, the other for measuring model prediction ability. Leaf area and leaf weight were modeled using different linear regression models based on length and width of leaf. Polynomial regressions involving both length and width of leaves provided very good models to estimate the expected area (R2 = 0.98) and weight (R2 = 0.91) of leaves.