ABSTRACT Image analysis combined with machine learning models can be an excellent tool for classification of fava (Phaseolus lunatus L.) genotypes and is a low-cost system. Fava is grown by family farmers, mainly, in the Northeast and South regions of Brazil, presenting economic and social importance. Evaluations to gather information on qualitative and quantitative characters of seeds enable the description and distinction of genotypes, allowing the evaluation of variability of plant species, which is essential in breeding programs. The use of image analysis is a fast and economic tool for obtaining large quantity of information. Machine learning techniques have been developed and implemented in the agricultural sector due to technological advances and increasing use of artificial intelligence, which enables the automatization of several processes. In this context, the objective of this work was to evaluate different machine learning models to classify fava genotypes, using data obtained through image analysis. Images of fava seeds were captured using a table scanner (HP Scanjet 2004), set to true color mode, arranged upside down inside of an aluminum box fully closed during the capture of the images for an adequate illumination and prevention of environmental noises. The K-Nearest Neighbor, Naive Bayes, Linear Discriminant Analysis, Support Vector Machine, Gradient Boosting, Bootstrap Aggregating, Classification and Regression Trees, Random Forest, and C50 models were used for the study. Linear Discriminant Analysis was the model that presented the highest efficiency for classifying the genotypes, with an accuracy of 90%.

ABSTRACT - Lima bean (Phaseolus lunatus L.) develops at an optimal temperature in the range of 20-30°C, temperatures above 30-35°C compromise the photosynthetic efficiency of the crop. Considering the importance of lima bean cultivation, the objective of this study was to carry out a morphoagronomic and phenological characterization of 46 lima bean accessions tolerant to high temperatures from the core collection of lima bean at the Universidade Federal do Piauí. The experiment was conducted from February to July 2021 in a completely randomized block design with four replications, where the plot consisted of a pot with two plants. Genotype characterization was performed based on 20 morphoagronomic and phenological descriptors of lima bean. Based on Pearson's correlation, the number of emitted and aborted flowers had a greater genetic correlation with the total number of seeds and pods produced. Pod length and width were positively correlated with seed thickness, length, and width. Five groups were formed based on UPGMA grouping. It was observed that the UFPI-922 and UFPI-945 accessions had a higher performance under high-temperature conditions in relation to the number of flowers and pods emitted, as well as lower values for the number of aborted pods. The accessions UFPI-1037, UFPI-876, UFPI-1036, UFPI-1028, UFPI-1052, UFPI-1064, UFPI-1038, and UFPI-1062 are promising for precocity, productivity, emission of flowers and pods formed, and can be used in breeding programs.

ABSTRACT The characterization of genetic divergence in common bean cultivars for various traits related to plant architecture and grain yield is unprecedented. This study proposes to determine whether common bean cultivars of different grain types differ for 12 traits of plant architecture and grain yield; examine the correlations between these traits; analyze the genetic divergence of these cultivars; and select superior cultivars for these traits. A total of 22 common bean cultivars with the grains types most produced in Brazil were evaluated in two growing seasons. Plant architecture was analyzed based on 12 traits, and grain yield was determined at maturity. Significant genotype and genotype × environment interaction effects were obtained, indicating the existence of genetic variability for all evaluated traits. Several plant architecture traits were correlated, but none was highly correlated with grain yield. Firstand second-internode lengths are more important in differentiating common bean cultivars. Principal component and Tocher’s analyses resulted in the formation of four and seven groups of cultivars, respectively. Both methods are efficient in analyzing genetic divergence; however, Tocher's method is more informative. Cultivars BRS Campeiro, SCS 205 - Riqueza, BRS Esteio, IAC Imperador and Guapo Brilhante have a high grain yield potential, but only BRS Campeiro, BRS Esteio and Guapo Brilhante have upright plant architecture.

ABSTRACT The objective of this work was to evaluate the effect of soil application of different boron (B) rates to the soil, with and without application of zinc (Zn), on growth, production components, and grain yield of maize crops grown in a Lithic Quartzipsamment with low B and Zn contents. A randomized block experimental design was used, in a 6×2 factorial arrangement corresponding to six B rates (0, 1, 2, 3, 4, and 5 kg ha-1), with and without application of Zn (2.0 kg ha-1), applied to the soil at sowing, with four replications. Growth variables (stem diameter and plant height), and chlorophyll SPAD index were evaluated at the R1 phenological stage. Maize ear length, one-thousand grain weight, and grain yield, and the B maximum efficiency rate were evaluated at the R6 phenological stage. Application of B and Zn to the soil increases maize grain yield in soils with sandy clay loam texture and low B and Zn contents; the plant absorption and metabolism indicated synergism between these elements when using soil applications of 1.0 kg ha-1 of B combined with 2.0 kg ha-1 of Zn to the planting furrows. The rates with maximum technical efficiency for grain yield were 3.29 and 4.31 kg of B ha-1 in treatments without and with application of Zn, respectively.

ABSTRACT Plant parasitic nematodes cause severe agricultural damage in Northeast Brazil. Additionally, soil salinization, especially in the semiarid region of the Northeast, is another factor that limits crop yield. The study evaluated the motility of Meloidogyne enterolobii and Pratylenchus coffeae, and the vertical migration of P. coffeae under saline conditions. Motility was assessed by submitting juveniles of the second stage of M. enterolobii and juveniles and adults of P. coffeae to saline solutions of NaCl, CaCl2, and MgCl2 at concentrations of 0.00, 0.25, 0.50, 0.75, and 1.00 M, and in a mixed solution (combination of the three salts in a 7:2:1 ratio) at 2, 4, 6, and 8 days of exposure. The migration of P. coffeae was studied in segmented columns of 10 cm in length and 4.40 cm in internal diameter, filled with saline soil (mixture of NaCl, CaCl2, and MgCl2) and non-saline, whose evaluations were carried out at 2, 4, and 6 days after soil infestation. The motility and number of active juveniles of both nematodes reduced with increasing saline concentration. From 0.50 M, M. enterolobii activity was not observed in any of the exposure periods to NaCl and CaCl2. The increase in the concentrations of NaCl, CaCl2, and MgCl2 exponentially reduced the number of active P. coffeae, decreasing its activity from 0.75 M. The vertical migration of P. coffeae in the soil was negatively affected by salinity, presenting a more uniform distribution in the non-saline soil.

ABSTRACT Aroeira-do-sertão is a Brazilian native species that has been widely explored. Thus, the population of this species has been reduced and techniques for its preservation are essential, such as the conservation of seeds in liquid nitrogen (LN). The objective of this work was to evaluate different cryoprotectant solutions for cryopreservation of aroeira-do-sertão seeds in LN (-196 °C). The treatments used were: control (7.5±1.5 °C); LN without cryoprotectant; sucrose 0.4 mol L-1; sucrose 0.8 mol L-1; glycerol 1 mol L-1; glycerol 2 mol L-1; PVS1 (plant vitrification solution); PVS2; PVS2 + 1% phloroglucinol; and PVS3. The seeds remained frozen for 120 days. The seeds were evaluated for germination and water content before cryopreservation. Several germination parameters were evaluated on the seventh day and plant growth variables were evaluated after 150 days. The seeds presented 9.2% water content and 74% germination before cryopreservation. The germination in the control treatment was 55%, whereas it varied from 61% to 69% under cryopreservation, denoting the positive effect of cryopreservation, even without cryoprotectants (69%). The seeds presented a triphasic water absorption model; the LN accelerated the germination, which started within 56 hours, whereas the germination in the control treatment started after 66 hours. The plant parts presented satisfactory development after 150 days, as shown by the Dickson quality index. The use of cryoprotectants did not affect seed germination and initial growth of seedlings. Aroeira-do-sertão seeds with 9.2% water content can be cryopreserved in LN without cryoprotectants.

ABSTRACT Forage cactus (Opuntia ficus-indica Mill) is an important forage resource in the Northeast region of Brazil due to its adaptation to the edaphoclimatic conditions of the region, mainly to the drought periods. The objective of this work was to assess the effects of diets with forage cactus combined with different sources of fibers on dry matter and water intakes, digestibility, microbial protein production, balance of nitrogen compounds, and performance of Red Sindhi cows in the Semiarid region of Brazil. The silages used were prepared from plants of Atriplex nummularia Lindi., Sorghum bicolor (L.) Moench, Gliricidia sepium (Jacq.) Walp., and Manihot pseudoglaziovii Pax & K. Hoffm. They were included in forage cactus-based diets at a roughage to concentrate ratio of 58:42. The cows were distributed in a 4×4 double Latin square design with 12 days for each period. Water intake presented differences (p<0.05) when using the diet with A. nummularia silage (19.42 L d-1). The diet with S. bicolor silage resulted in lower (p<0.05) coefficient of digestibility of dry matter (48.71%) than the diet with A. nummularia silage (68.46%). The diet with A. nummularia silage resulted in higher (p<0.05) microbial synthesis than that with G. sepium silage, 115.01 and 80.07 g CPmic kg-1 TDN, respectively. The silages evaluated, combined with forage cactus, can be used as diets for lactating Red Sindhi cows without affecting the daily dry matter intake, milk production, fat content, microbial protein synthesis, and balance of nitrogen compounds.

ABSTRACT Quantifying soil gas emissions is costly, since it requires specific methodologies and equipment. The objective of this study was to evaluate modeling by nonlinear regression and artificial neural networks (ANN) to estimate CO2 emissions caused by soil managements. CO2 emissions were evaluated in two different soil management systems: no-tillage and minimum tillage. Readings of CO2 flow were carried out by an automated closed system chamber; soil temperature, water content, density, and total organic carbon were also determined. The regression model and the ANN models were adjusted based on the correlation of the variables measured in the areas where the soil was managed with no-tillage and minimum tillage with data of CO2 emission. Artificial neural networks are more accurate to determine correlations between CO2 emissions and soil temperature, water content, density, and organic carbon content than linear regression.

ABSTRACT The objective of this work was to compare three methods of estimating the optimal plot size to evaluate the fresh matter in black oat (Avena strigosa Schreb), common vetch (Vicia sativa L.) and forage turnip (Raphanus sativus L.) intercropping. Six uniformity trials with black oat, common vetch and forage turnip intercropping were carried out. Three trials were evaluated at 84 days after sowing and the other three trials at 119 days after sowing. The fresh matter was evaluated in 216 basic experimental units (36 per trial) of 1 m × 1 m. The optimal plot size was determined using the methods of modified maximum curvature, linear response and plateau model and quadratic response and plateau model. The optimal plot size differs between the methods and decreases in the following order: quadratic response and plateau model (15.13 m2), linear response and plateau model (8.24 m2) and modified maximum curvature (5.62 m2). The optimal plot size for assessing the fresh matter of black oat, common vetch and forage turnip, grown in intercropping, is 15.13 m2. This size can be used as a reference for future experiments.

ABSTRACT The biological control, thinking about the integrated management, has been inserted with other management techniques to disease control, such as soybean anthracnose. The aims of this work were to verify the action of Trichoderma and Bacillus isolates in the induction of soybean resistance mechanisms to anthracnose as a function of seed treatment. The statistical design was entirely randomised, in a 5 x 2 (agent species x sampling times) factorial scheme with five replicates. Soybean seeds were treated with Bacillus amyloliquefaciens BV03, B. subtilis BV02, Trichoderma asperellum BV10, Carbendazim + Thiram and distilled water (control). Seven days after seedling emergence, 2 μL of 1 x 10−4 Colletotrichum truncatum spores were inoculated on the cotyledons. Catalase (CAT), peroxidase (POX), phenylalanine ammonia lyase (PAL) and glyceollin (GLY) activities before and after pathogen inoculation, as well as the diameter of the anthracnose lesion on the cotyledons, were evaluated. Data were submitted to analysis of variance and, when significant, the mean values were compared by Fisher’s test (p < 0.05). The treatments did not influence the first sampling time before inoculation. Trichoderma asperellum BV10 increased POX and PAL activities up to 173%, while B. amyloliquefaciens BV03 increased POX activity. Glyceollin was not influenced by the treatments. The T. asperellum BV10 reduces the diameter of the anthracnose lesion by up to 61%. Thus, T. asperellum BV10 has the potential to control soybean anthracnose, improved the response defense against C. truncatum, when performed on seed treatment.