Decision Trees as a Tool to Select Sugarcane Families

Abstract

New strategies are required in the sugarcane selection process to optimize the genetic gains in breeding programs. Conventional selection strategies have the disadvantage of requiring the weighing of all the plants in a plot or a sample of stalks and the counting of the number of stalks in all the experimental plots, which cannot always be performed because more than 200,000 genotypes routinely comprise the first test phase (T1) of most sugarcane breeding programs. One way to circumvent this problem is to use decision trees to rank the yield components (the stalk height, the stalk diameter and the number of stalks) and to subsequently use this categorization to select the best families for a specific trait. The objective of this study was to evaluate the categorization of yield components using the classification and regression tree (CART) algorithm as a family selection strategy by comparing the performance of CART with those of conventional methods that require the weighing of stalks, such as the best linear unbiased prediction (BLUP) with sequential (BLUPS) or individual simulated (BLUPIS) procedures. Data from five experiments performed in May 2007 in a randomized block design were analyzed. Each experiment consisted of five blocks, 22 families and two controls (commercial varieties). CART effectively defined the classes of the yield components and selected the best families with an accuracy of 74% compared to BLUPS and BLUPIS. Families with at least 11 stalks per linear meter of furrow resulted in productivities that were above the average productivity of the commercial varieties used in this study and are, therefore, recommended for selection.

Morphological growth performance and genetic parameters on Korean pine in Northeastern China

“…Average values on performance of trees from different families or clones are most important for selection, primarily to minimize the environmental effects arising from individual trees when estimating genotype performance value for a given morphological traits and to establish straight order of genotypes based on their ranks (Mckeand et al 2006;Peternelli et al 2018). In this study, 11 growth traits (7 related to stem and 4 to crown) were investigated on 28 full-sib families.…”

Can statistical learning models make early selection among sugarcane families easier and still efficient?

“…Lately, for the same datasets, Peternelli, Moreira, Nascimento, and Cruz (2017) demonstrate that the statistical learning techniques artificial neural network (ANN) is superior to linear discriminant analysis (LDA) for the same purpose of selecting among families. However, it must be pointed out that other learning techniques can be used for classification, as found in the literature (Grinberg et al., 2016; Heslot, Yang, Sorrells, & Jannink, 2012; Ogutu, Piepho, & Schulz‐Streeck, 2011; Peternelli, Bernardes, Brasileiro, Barbosa, & Silva, 2018), and some of them might improve even more the selection efficiency.…”