Figure 1 - uploaded by Bruno Portela Brasileiro
Content may be subject to copyright.
Histograms with continuous data distribution and the respective classification (good, fair and poor) of each plant for the traits stalk number (SN), stalk diameter (SD) and stalk height (SH).
Source publication
The objective of this study was to evaluate Artificial Neural Networks (ANN) applied in an selection process within sugarcane
families. The best ANN model produced no mistake, but was able to classify all genotypes correctly, i.e., the network made the same
selective choice as the breeder during the simulation individual best linear unbiased predic...
Contexts in source publication
Context 1
... inferior results of model 2 by both logistic regression and ANN may be related to the difficulty in classifying the yield components (Figure 1). ...
Context 2
... very low or very high plants were classified correctly, as also observed for stalk diameter (SD), where only plants with a very large or small diameter were classified appropriately. For SD and SH the difficulty was in defining the category fair, since plants that should receive this rating were misclassified as good or poor (Figure 1). ...
Similar publications
Sugarcane (Saccharum spp.) brown rust (caused by Puccinia melanocephala Syd. & P. Syd.) was first reported in the United States in 1978 and is still one of the great challenges for sugarcane production. A better understanding of sugarcane genotypic variation in response to brown rust will help optimize breeding and selection strategies for disease...
In the aim of improving selection technique in Egyptian sugarcane breeding program under different selection intensities, ninety sugarcane clones that were selected from 10 bi-parental crosses and three selfing populations at seedling stage and check cultivar (GT54-9) were evaluated for yield and quality traits and genetic parameters were measured...
Citations
... In evaluating different artificial neural network configurations, the results showed that the neural network model was superior to linear models for predicting genetic values and had a high generalization performance in validation experiments [97]. The effectiveness of ANN in selection procedures was assessed with data from sugarcane families [98]. The best ANN model tested in this study was proven to be accurate and able to classify all genotypes correctly with no mistakes, thus replicating the selective choice made by the breeder during the simulation of the individual best linear unbiased predictor (BLUP). ...
... genetic values and had a high generalization performance in validation experiments [97]. The effectiveness of ANN in selection procedures was assessed with data from sugarcane families [98]. The best ANN model tested in this study was proven to be accurate and able to classify all genotypes correctly with no mistakes, thus replicating the selective choice made by the breeder during the simulation of the individual best linear unbiased predictor (BLUP). ...
... The best ANN model tested in this study was proven to be accurate and able to classify all genotypes correctly with no mistakes, thus replicating the selective choice made by the breeder during the simulation of the individual best linear unbiased predictor (BLUP). This highlights the ANN's capability to successfully learn from training and validation inputs and outputs [98]. The successful use of ANN for evaluating genetic diversity in plants was assessed by Sant'Anna et al. [99], comparing ANN's accuracy with traditional methods. ...
In the face of a growing global population, plant breeding is being used as a sustainable tool for increasing food security. A wide range of high-throughput omics technologies have been developed and used in plant breeding to accelerate crop improvement and develop new varieties with higher yield performance and greater resilience to climate changes, pests, and diseases. With the use of these new advanced technologies, large amounts of data have been generated on the genetic architecture of plants, which can be exploited for manipulating the key characteristics of plants that are important for crop improvement. Therefore, plant breeders have relied on high-performance computing, bioinformatics tools, and artificial intelligence (AI), such as machine-learning (ML) methods, to efficiently analyze this vast amount of complex data. The use of bigdata coupled with ML in plant breeding has the potential to revolutionize the field and increase food security. In this review, some of the challenges of this method along with some of the opportunities it can create will be discussed. In particular, we provide information about the basis of bigdata, AI, ML, and their related subgroups. In addition, the bases and functions of some learning algorithms that are commonly used in plant breeding, three common data integration strategies for the better integration of different breeding datasets using appropriate learning algorithms, and future prospects for the application of novel algorithms in plant breeding will be discussed. The use of ML algorithms in plant breeding will equip breeders with efficient and effective tools to accelerate the development of new plant varieties and improve the efficiency of the breeding process, which are important for tackling some of the challenges facing agriculture in the era of climate change.
... When working with families with high genotypic, it is possible to maximize the probability of identifying superior genotypes . For this reason, some sugarcane breeding programs have initially undertaken the selection of families and, subsequently, the selection of individuals within families (Brasileiro et al., 2015;Mbuma et al., 2020;Oliveira et al., 2016;Zeni-Neto et al., 2013). ...
The simplified system (SS) is a new method of selecting families in the first experimentation phase used in some sugarcane (Saccharum officinarum L.) breeding programs in Brazil. In the SS, clones are obtained from families whose genotypes are not individualized in the field. Such selected clones are used to compose the cloned family trial. In the conventional method (CM) of breeding, each genotype is individualized to form part of the family evaluation experiment. This work aimed to compare and verify if the SS provides genetic information at least similar to the CM. Two experiments were conducted, one for the CM and the other for the SS. Sixty full‐sib families were evaluated in each experiment. The characteristics evaluated were average stalk height, average stalk diameter, the content of total soluble solids (BRIX), the number of stalks per meter, average stalk mass, tonnes of stalks per hectare, and tonnes of BRIX per hectare. The mixed model methodology was used to estimate the genetic parameters and predict the families' genotypic values. Both methods enabled high precision in the evaluation of families and similar average genetic gains (10.1% for CM and 9.6% for SS). The SS makes it possible to select families with high genotypic value, high accuracy, and genetic gains comparable to the CM. Therefore, although the SS presents similar results as the CM, its simplicity and ease of being installed in the field in a smaller experimental area make it a promising methodology for selecting cloned families in a sugarcane breeding program.
... The efficiency of the use of neural networks in breeding programs has been presented in several studies, such as the selection of more productive genotypes of sugarcane (Saccharum spp.) [19] and the evaluation of genetic divergence (Vitis vinifera L.) [20], papaya (Carica papaya L.) [1] and guava (Psidium guajava L.) [9]. ...
The objective of this study was to study the genetic divergence between genotypes of kale, to propose a methodology for the use of neural networks of the SOM type and to test its efficiency through Anderson's discriminant analysis. We evaluated 33 families of half-siblings of kale and three commercial cultivars. The design was a randomized block with four replications with six plants per plot. A total of 14 plant-level quantitative traits were evaluated. Genetic values were predicted at family level via REML / BLUP. For the study of divergence, neural networks of the SOM type (Self-organizing Map) were adopted. We evaluated different network architectures, whose consistencies of the clusters were identified by the Anderson discriminant analysis and by the number of empty clusters. After selecting the best network configuration, a dissimilarity matrix was obtained, from which a dendrogram was constructed using the UPGMA method. The best network architecture was formed with five rows and one column, totaling five neurons and consequently five clusters. The greatest dissimilarity was established between clusters I and V. The crossing between the genotypes of cluster I and those belonging to clusters III and V are the most recommended, since they aim to recombine families with characteristics of interest to the improvement and high dissimilarity. Anderson's discriminant analysis showed that the genotype classification was 100% correct, indicating the efficiency of the methodology used.
... The artificial neural networks (ANN) is a successful tool to describe, substantiate, and elucidate high-complexity issues in the field of modeling Azevedo et al., 2015;Brasileiro et al., 2015;Soares et al., 2015;Aquino et al., 2016aAquino et al., , 2016bAzevedo et al., 2017). Thus, the use of ANN in agronomic modeling for the cactus pear crop can be efficient for predicting yield. ...
... Moreover, according to Aquino et al. (2016a), the ANN consider numerous explanatory variables concomitantly in the model that does not always present good results by other statistical models, such as multiple linear regression. Several researchers also confirmed the efficiency of artificial intelligence found in this study (Azevedo et al., 2015;Brasileiro et al., 2015;Soares et al., 2015;Aquino et al., 2016aAquino et al., , 2016b. Table 1. ...
Estimating cactus pear yield is important for the planning of small and medium rural producers, especially in environments with adverse climatic conditions, such as the Brazilian semi-arid region. The objective of this study was to evaluate the potential of artificial neural networks (ANN) for predicting yield of ‘Gigante’ cactus pear, and determine the most important morphological characters for this prediction. The experiment was conducted in the Instituto Federal Baiano, Guanambi campus, Bahia, Brazil, in 2009 to 2011. The area used is located at 14° 13’ 30” S and 42° 46’ 53” W, and its altitude is 525 m. Six vegetative agronomic characters were evaluated in 500 plants in the third production cycle. The data were subjected to ANN analysis using the R software. Ten network architectures were trained 100 times to select the one with the lowest mean square error for the validation data. The networks with five neurons in the middle layer presented the best results. Neural networks with coefficient of determination (R2) of 0.87 were adjusted for sample validation, assuring the generalization potential of the model. The morphological characters with the highest relative contribution to yield estimate were total cladode area, plant height, cladode thickness and cladode length, but all characters were important for predicting the cactus pear yield. Therefore, predicting the production of cactus pear with high precision using ANN and morphological characters is possible.
... A novel method that is being exploited for different purposes in plant breeding programs, although marginally, is the use of artificial neural networks (Zhou et al. 2011, Barbosa et al. 2011, Barroso et al. 2013, Brasileiro et al. 2015, Sant'Anna et al. 2015. This approach is based on principles of statistical learning and artificial intelligence. ...
One of the major challenges in sugarcane breeding programs is an efficient selection of genotypes in the initial phase. The purpose of this study was to compare modelling by artificial neural networks (ANN) and linear discriminant analysis (LDA) as alternatives for the selection of promising sugarcane families based on the indirect traits number of sugarcane stalks (NS), stalk diameter (SD) and stalk height (SH). The analysis focused on two models, a full one with all predictors, and a reduced one, from which the variable SH was excluded. To compare and assess the applied methods, the apparent error rate (AER) and true positive rate (TPR) were used, derived from the confusion matrix. Modeling with ANN and LDA can be used successfully for selection among sugarcane families. The reduced model may be preferable, for having a low AER, high TPR and being easier to obtain in operational terms. © 2017, Brazilian Society of Plant Breeding. All rights reserved.
... After hybridization with parents to obtain cane energy, families must be evaluated to then select individual plants within the best families, because selection in families with high genotypic values increases the probability of finding superior clones among the progenies (Barbosa et al. 2005). Based on this premise, family selection has been routinely applied prior to clone development in several breeding sugarcane programs (Stringer et al. 2011, Barbosa et al. 2012, Brasileiro et al. 2015. ...
... With the exploitation of the best families, possibly a higher number of high-yielding clones can be included in the subsequent steps of a sugarcane breeding programs (Barbosa et al. 2005, Brasileiro et al. 2015. Therefore, the identification of promising parents for crosses is essential to accelerate genetic gains and increase the likelihood of identification and selection of transgressive genotypes. ...
The objective of this study was to identify superior parents for crosses and the best families to breed new clones of energy cane. The best-performing parents were RB867515, RB93509, KRAKATAU, IM76-228, IM76-229, and US85-1008. The heritability (0.59 – 0.85)and accuracy values (0.76 – 0.92) for the traits tons of cane per hectare, fiber, and sucrose content indicate high correlation between the predicted genotypic means and observed values, enabling efficient selection of the best cane energy families. The extensive genetic variation detected and the presence of promising seedlings in the selected segregating population indicate the possibility of using new crosses in some clones and even in future commercial plantings. It was possible to identify the best parents involved in the evaluated crosses, and to select, in the best families, seedlings with a high fiber and good sucrose content, seedlings with high fiber and low sugar content, as well as seedlings with the same fiber and sucrose contents as the current cultivars.
... Because artificial neural networks (ANNs) are efficient to model complex problems (Barbosa et al. 2011;Nascimento et al. 2013;Azevedo et al. 2015;Brasileiro et al. 2015), they may also be effective in the indirect phenotyping of vitamin A content by using colorimetric data. The ANNs are computational models of the human brain that can recognize patterns and regularities of the data, becoming an alternative as universal approximator of complex functions (Gianola et al. 2011). ...
ABSTRACT Banana is one of the most consumed fruits in Brazil and an important source of minerals, vitamins and carbohydrates for human diet. The characterization of banana superior genotypes allows identifying those with nutritional quality for cultivation and to integrate genetic improvement programs. However, identification and quantification of the provitamin carotenoids are hampered by the instruments and reagents cost for chemical analyzes, and it may become unworkable if the number of samples to be analyzed is high. Thus, the objective was to verify the potential of indirect phenotyping of the vitamin A content in banana through artificial neural networks (ANNs) using colorimetric data. Fifteen banana cultivars with four replications were evaluated, totaling 60 samples. For each sample, colorimetric data were obtained and the vitamin A content was estimated in the ripe banana pulp. For the prediction of the vitamin A content by colorimetric data, multilayer perceptron ANNs were used. Ten network architectures were tested with a single hidden layer. The network selected by the best fit (least mean square error) had four neurons in the hidden layer, enabling high efficiency in prediction of vitamin A (r2 = 0.98). The colorimetric parameters a* and Hue angle were the most important in this study. High-scale indirect phenotyping of vitamin A by ANNs on banana pulp is possible and feasible.
... Zhou et al. (2014) demonstrated the potential for using a logistic regression model as a statistical decision support tool for selection among individual seedlings based only on production components during the initial phases of genetic breeding programs for sugarcane. Brasileiro et al. (2015) also noted the potential for logistic regression during seedling selection and the importance of qualitative traits in breeder decision-making. ...
... As noted by Brasileiro et al. (2015), the use of categorical data for yield components (SD, SH and NS) did not affect the quality of the logistic model. Therefore, due to the ease of classification by the breeder of the perceived stem diameter and plant height, the genotypes were classified as good diameter (SD = 1) and poor diameter (SD = 0), as well as tall plant (SH = 1) and short plant (SH = 0); the breeders had 25 years of work experience in clonal selection. ...
The aim of this study was to evaluate the importance of agronomic traits during the selection of sugarcane (Saccharum spp.), as well as to evaluate the potential for using logistic regression and decision trees to identify the best genotypes. A total of 7,719 seedlings of 128 half-sib families were evaluated during the first test phase (T1), and 659 clones were selected for the second (T2). Logistic regression was applied to both populations. The number of stalks, bud prominence and length of the internode were the most important selection traits in the T1 population. The plant vigor, stalk diameter and stalk height were the most important selection traits in the T2 population. There were 174 individuals selected when using the mass selection method in T1 and 113 individuals in T2, whereas a logistic regression selected 153 individuals in T1 and 79 in T2. The apparent error rates of the logistic models fitted to the selections in T1 and T2 were 0.8 and 5.10%, respectively. By using a decision tree, 67 clones were selected among the most productive ones in phase T2. Therefore, the formulation of decision trees is highly applicable to identifying potential clones during the initial phases of breeding programs.
... As RNAs são modelos que emulam uma rede de neurônios biológicos, capazes de processar rapidamente uma grande quantidade de dados e de reconhecer padrões com base em sua autoaprendizagem (Haykin, 2009). Por causa dessas características, essas redes têm sido empregadas para selecionar indivíduos dentro de famílias de cana-de-açúcar (Saccharum spp.) (Brasileiro et al., 2015); predizer o volume de eucalipto (Eucalyptus spp.) (Bhering et al., 2015); e quantificar a divergência genética de acessos de mamão (Carica papaya L.) (Barbosa et al., 2011). Contudo, sua aplicação para a seleção de genótipos em presença de interação genótipos x ambientes significativa ainda se restringe ao trabalho de Nascimento et al. (2013); portanto, são necessárias mais pesquisas que comprovem a eficácia desse método. ...
Resumo: O objetivo deste trabalho foi verificar a concordância entre as redes neurais artificiais (RNAs) e o método de Eberhart & Russel na identificação de genótipos de feijão-caupi (Vigna unguiculata) com alta adaptabilidade e estabilidade fenotípicas. Utilizou-se o delineamento experimental de blocos ao acaso com quatro repetições. Os tratamentos consistiram de 18 linhagens experimentais e duas cultivares de feijão-caupi. Foram conduzidos quatro ensaios de valor de cultivo e uso nos municípios de Aquidauana, Chapadão do Sul e Dourados, no estado do Mato Grosso do Sul. Os dados de produtividade de grãos foram submetidos às análises de variância individual e conjunta. Em seguida, os dados foram submetidos às análises de adaptabilidade e estabilidade por meio dos métodos de Eberhart & Russell e de RNAs. Houve elevada concordância entre os métodos avaliados quanto à discriminação da adaptabilidade fenotípica dos genótipos de feijão-caupi semiprostrado, o que indica que as RNAs podem ser utilizadas em programas de melhoramento genético. Em ambos os métodos avaliados, os genótipos BRS Xiquexique, TE97-304G-12 e MNC99-542F-5 são recomendados para ambientes desfavoráveis, gerais e favoráveis, respectivamente, por apresentarem produtividade de grãos acima da média geral dos ambientes e alta estabilidade fenotípica.
... It has the objective of obtaining RB (Republic of Brazil) cultivars with high sugar yield, a characteristic which depends on the mass of stalks per unit area, and sucrose content of stalks. In the development of RB cultivars (Germplasm Bank of Serra do Ouro Flowering and Crossing Station) (Santos et al. 2014, Silva et al. 2015, around 300 thousand seedlings per year are planted in eight distinct environments of Alagoas, followed by stages of phenotypic selection, experimentation, maturation curve, disease assessment and multiplication of clones in production areas (Barbosa et al. 2002, Brasileiro et al. 2015. In clones selection processes, drought tolerance and non-flowering characteristics are also considered. ...
RB99395 cultivar was developed by the Sugarcane Breeding Program at the Federal University of Alagoas, which is part
of RIDESA. In 1999, seeds were obtained from crosses between RB867515 cultivar and pollen from an unknown genotype in “Serra
do Ouro” Crossing Station. The process of selection and experimentation was carried out in three Research Stations of Alagoas.
RB99395 cultivar was released in Alagoas in May 2010, and has a high content of sucrose throughout the harvest period. Planting is
recommended in fertile soils and in environments with no water deficiency, a condition which results in high agricultural yields. It is
tolerant most diseases that occur in Northeast, Brazil.
