The efficiency of artificial neural networks (ANN) to model complex problems may enable the prediction of characteristics that are hard to measure, providing better results than the traditional indirect selection. Thus, this study aimed to investigate the potential of using artificial neural networks (ANN) for indirect selection against early flowering in lettuce, identify the influence of genotype by environment interaction in this strategy and compare your results with the traditional indirect selection. The number of days to anthesis were used as the desired output and the information of six characteristics (fresh weight of shoots, mass of marketable fresh matter of shoots, commercial dry matter of shoots, average diameter of the head, head circumference and leaf number) as input file for the training of the ANN-MLP (Perceptron Multi-Layer). The use of ANN has great potential adjustment for indirect selection for genetic improvement of lettuce against early flowering. The selection based on the predicted values by network provided estimates of gain selection largest that traditional indirect selection. The ANN trained with data from an experiment have low power extrapolation to another experiment, due to effect of interaction genotype by environment. The ANNs trained simultaneously with data from different experiments presented greater predictive power and extrapolation.

O objetivo deste trabalho foi avaliar os parâmetros genéticos das características agronômicas e de tolerância ao florescimento precoce de onze cultivares de alface, bem como verificar a existência de associação entre as características. O experimento foi realizado em ambiente protegido, em delineamento de blocos ao acaso, com quatro repetições e doze plantas por parcela. Quarenta e cinco dias após o transplantio das mudas, foram mensuradas as seguintes características: massa de matéria fresca total e "comercial" da parte aérea, massa de matéria seca "comercial" da parte aérea, massa de matéria fresca e seca da raiz, diâmetro e circunferência da cabeça, altura de planta, número de folhas por planta e número de dias até a antese. Há variabilidade genética entre as cultivares, em todas as variáveis, exceto quanto à circunferência de planta e matéria fresca da raiz. As cultivares Regina 500, Lívia e Atração foram superiores quanto ao número de dias para o florescimento e também para as demais características avaliadas. A seleção contra o florescimento precoce ocasionou ganho em todas as características; porém, não interferiu na matéria seca da raiz. A matéria fresca da parte aérea e o diâmetro de cabeça são indicadas para a seleção indireta contra o florescimento precoce.

The objective of this study was to evaluate the genetic parameters of agronomic traits and of tolerance to early flowering of eleven cultivars of lettuce, as well as to verify the existence of an association between the characteristics. The experiment was carried out in a protected environment, in a randomized complete block design, with four replicates, and twelve plants per plot. Forty-five days after seedling transplanting, the following traits were measured: total shoot fresh mass, marketable shoot fresh mass, marketable dry shoot weight, fresh and dry weight of roots, diameter and circumference of head, plant height, number of leaves per plant, and number of days until anthesis. There was genetic variability between cultivars for all variables, except for circumference of plant and fresh weight of root. The cultivars Regina 500, Lívia and Atração were superior for number of days to flowering and also for the other characteristics. The selection against early flowering caused gain of all the characteristics, but did not affect root dry matter. Fresh matter of shoots and head diameter are indicated for indirect selection against early flowering.