Fruit growth patterns are often exploited in predictions of final fruit size and to inform planting and harvesting decisions. Ten local apricot (Prunus armeniaca) varieties with superior genotypes (two early-ripening, five mid-ripening and three late-ripening varieties) were assessed using 20 nonlinear regression models (NRMs) and a radial basis function (RBF) neural network model. Fruit diameter and weight measurements for each genotype were collected at four-day intervals from fruit set to commercial harvest. Patterns based on diameter and weights were attributed to each genotype. Among the NRM tested, only four were able to flawlessly predict apricot diameter and weight during the growing season. In addition, comparison of nonlinear regression methods with the neural network indicated than the RBF model displayed fewer prediction errors than the NRMs. The RBF model predicted fruit size with a coefficient of determination (R2 value) greater than 0.95. Therefore, predictions of growth patterns in fruit trees can be accomplished with neural network modeling.

Keywords