A breeder can select a visually appealing phenotype, whether for ornamentation or landscaping. However, the organic vision is not accurate and objective, making it challenging to bring a reliable phenotyping intervention into implementation. Therefore, the objective of this study was to develop an innovative solution to predict the intensity of the flower’s color upon the external shape of the crop. We merged the single linear iterative clustering (SLIC) algorithm and box-counting method (BCM) into a framework to extract useful imagery data for biophysical modeling. Then, we validated our approach by fitting Gompertz function to data on intensity of flower’s color and fractal dimension (S^D) of the architecture of white-flower, yellow-flower, and red-flower varieties of Portulaca umbraticola. The SLIC algorithm segmented the images into uniform superpixels, enabling the BCM to precisely capture the S^D of the architecture. The S^D ranged from 1.938315 to 1.941630, which corresponded to pixel-wise intensities of 220.85 and 47.15. Thus, the more compact the architecture the more intensive the color of the flower. The sigmoid Gompertz function predicted such a relationship at r_adj² > 0.80. This study can provide further knowledge to progress the field’s prominence in developing breakthrough strategies toward improving the control of visual quality and breeding of ornamentals.

Purslanes are frequently used in Brazil as potted plants and for landscaping because of their beautiful colored flowers. Despite their commercial importance, the genetic diversity within ornamental purslane remains largely unknown. Thus, a complete characterization of ornamental purslane resources is essential for its utilization since genetic variability is indispensable for the efficient development of new cultivars. This study aimed to evaluate genetic variability and recommend accessions to start a genetic breeding program for purslane (Portulaca umbraticola). Twenty purslane accessions were collected in public places in Areia City and Santa Rita City, Paraiba State, Brazil. The experiment was conducted in a greenhouse. An entirely randomized experimental design with 20 accessions and 5 replicates was utilized. Plants were evaluated for quantitative and qualitative traits. Data were submitted to analysis of variance and grouped by Scott–Knott’s criteria (p ≤ 0.05). The accessions were grouped using Tocher’s method based on the generalized Mahalanobis distance. Principal component analysis was also used to analyze the genetic divergence. There were significant differences (p ≤ 0.05) for all evaluated traits except for internode distance, plant height, and leaf length. The Scott–Knott criteria clustered the accessions into two groups for all traits except days to flowering (five groups). Tocher’s grouping based on Mahalanobis distance allowed the accessions to be separated into eight clusters. The genetic diversity observed in this study was supported by the consonance between the Tocher cluster method and the PC analyses. The traits that most contributed to genetic divergence among accessions were days to flowering (70.37%), flower length (6.10%), leaf width (3.89%), branch number (3.57%), and stem length (3.36%). Considering the criteria for use in outdoor spaces, wider plants with several large colored flowers, thicker stems, greener leaves, and earliness were interesting. Accessions 5, 7, 13, 14, 16, 18, and 20 should be selected as parents for further breeding programs. However, if the objective is to produce potted plants, dwarf plants with bigger leaves are desired, and accession 1 should be selected. This will create greater variability in segregating populations, which will increase the overall quality of ornamental use of this species. For those accessions with no reproductive verticils but with other excellent attributes, for example, high chlorophyll content breeding strategies, such as induced mutations or protoplast fusion, can be used.

The primary objective of soybean-breeding programs is to develop cultivars that offer both high grain yield and a maturity cycle tailored to the specific soil and climatic conditions of their cultivation. Therefore, predicting the genetic value is essential for selecting and advancing promising genotypes. Among the various analytical approaches available, deep machine learning emerges as a promising choice due to its capability to predict the genetic component of phenotypes assessed under field conditions, thereby enhancing the precision of breeding decisions. This study aimed to determine the efficiency of artificial neural networks (ANNs) in predicting the genetic values of soybean genotypes belonging to populations derived from crosses between parents of different relative maturity groups (RMGs). We characterized populations with broad and restricted genetic bases for RMG traits. Data from three soybean populations, evaluated over three different agricultural years, were used. Genetic values were predicted using the multilayer perceptron (MLP) artificial neural network and compared to those obtained using the best unbiased linear prediction from variance components using restricted maximum likelihood (RR-BLUP). The MLP neural network efficiently predicted genetic values for the relative maturity group trait for genotypes belonging to populations of broad and restricted crosses, with an R² of 0.999 and root-mean-square error (RMSE) of 0.241, and for grain yield, there was an R² of 0.999 and an RMSE of 0.076. While the percentage of coincident superior genotypes remained relatively consistent, a significant difference was observed in their ranking order. The genetic gain with selection estimated using MLP was higher by 30–110% compared to RR-BLUP for the relative maturity group trait and 90–500% for grain yield. Artificial neural networks (ANNs) showed higher efficiency than RR-BLUP in predicting the genetic values of the soybean population. Local selection at intermediate latitudes is conducive to developing lines adaptable for regions at higher and lower latitudes.

Lima bean cultivation has not received proper national and regional attention by research agencies, impairing the knowledge of the agronomic characteristics and its potential, information that is essential for the selection and launching of superior genotypes. The objective of this work was to characterize the seeds of 17 lima bean genotypes produced by family farmers in Paraíba State. The characterization was based on the descriptors for Phaseolus lunatus. A completely randomized design was used with 15 replicates. Data were submitted to analysis of variance with a subsequent grouping of means by the Scott-Knott test at 1% of probability. For analysis of the genetic diversity, the Tocher method was used based on the generalized Mahalanobis distance. There is variability among the genotypes. According to the means test, genotype 10 has a higher seed length, width, and weight. Considering the diversity among the groups and aiming to select light-colored and higher means of the evaluated traits, the selection of genotypes 8, 13, 4, and 10 is recommended to establish a breeding program that satisfies both the consumer and the producer. Lima bean cultivation has not received proper national and regional attention by research agencies, impairing the knowledge of the agronomic characteristics and its potential, information that is essential for the selection and launching of superior genotypes. The objective of this work was to characterize the seeds of 17 lima bean genotypes produced by family farmers in Paraíba State. The characterization was based on the descriptors for Phaseolus lunatus. A completely randomized design was used with 15 replicates. Data were submitted to analysis of variance with a subsequent grouping of means by the Scott-Knott test at 1% of probability. For analysis of the genetic diversity, the Tocher method was used based on the generalized Mahalanobis distance. There is variability among the genotypes. According to the means test, genotype 10 has a higher seed length, width, and weight. Considering the diversity among the groups and aiming to select light-colored and higher means of the evaluated traits, the selection of genotypes 8, 13, 4, and 10 is recommended to establish a breeding program that satisfies both the consumer and the producer.

Breeding wheat for production in the Brazilian Cerrado region should aim at developing productive genotypes adapted to heat and drought conditions; therefore, this study evaluated the tolerance of wheat cultivars to heat/thermal and drought stress. To meet this objective, 30 wheat cultivars were cultivated in 3 greenhouse environments, namely control, drought, and heat, applying stress from the booting stage to the end of anthesis. The following parameters were evaluated: cycle, plant height, spike number per plant, spike length, spike weight, spikelet number per spike, percentage of fertile spikelets, number of grains per spike, and grain weight per spike. Principal component analysis and cluster analysis were performed by the Ward and “K-means” methods. Principal component analysis showed that the correlations between the productivity traits and the principal components were more affected by drought than by the control and heat environments. The cluster analyses formed five clusters for the control and heat environments and seven clusters for the drought environment. Grain productivity was highlighted in the heat environment for ‘BRS 210’, ‘BR18 Terena’, ‘IPR Catuara TM’, ‘CD 154’, ‘BR 220’, ‘MGS Aliança’, ‘IAC 350’, ‘IAC Tucunaré’, ‘BR 24’, ‘IAC 5 Maringá’, ‘UFVT1 Pioneiro’, and ‘CD 151 4’ with a positive relationship in principal component analysis. Considering spikelet number per spike in the drought environment, cultivars ‘BRS 208’, ‘IAC 350’, ‘Supera’, ‘BRS 210’, ‘IPR 85’, ‘IPR Catuara TM’, ‘Anahuac 73’, ‘BR 24’, ‘IAC 5 Maringá’, and ‘UFVT1 Pioneiro’ were highlighted. In the drought environment, most of the productivity-related traits exhibited components with negative relationships among cultivars and the evaluated traits, confirming their response to the induced stress.