Explore the vast range of titles available.

Optical sensors combined with machine learning algorithms have led to significant advances in seed science. These advances have facilitated the development of robust approaches, providing decision-making support in the seed industry related to the marketing of seed lots. In this study, a novel approach for seed quality classification is presented. We developed classifier models using Fourier transform near-infrared (FT-NIR) spectroscopy and X-ray imaging techniques to predict seed germination and vigor. A forage grass (Urochloa brizantha) was used as a model species. FT-NIR spectroscopy data and radiographic images were obtained from individual seeds, and the models were created based on the following algorithms: linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), random forest (RF), naive Bayes (NB), and support vector machine with radial basis (SVM-r) kernel. In the germination prediction, the models individually reached an accuracy of 82% using FT-NIR data, and 90% using X-ray data. For seed vigor, the models achieved 61% and 68% accuracy using FT-NIR and X-ray data, respectively. Combining the FT-NIR and X-ray data, the performance of the classification model reached an accuracy of 85% to predict germination, and 62% for seed vigor. Overall, the models developed using both NIR spectra and X-ray imaging data in machine learning algorithms are efficient in quickly, non-destructively, and accurately identifying the capacity of seed to germinate. The use of X-ray data and the LDA algorithm showed great potential to be used as a viable alternative to assist in the quality classification of U. brizantha seeds.

Creation, adjustments and adoption of tests and tools that help in the prediction of seed storability have been highly demanded. Therefore, this work aimed to analyze the efficiency of different artificial aging times in predicting the performance of soybean seeds after storage, using the GGE biplot method. Seeds of six genotypes were subjected to storage, under refrigerated and non-refrigerated conditions, and artificial aging, being artificially aged for periods of 0, 48, 96 and 144 hours. Seeds freshly harvested and after natural and artificial aging were subjected to germination and vigor tests. The experiments were analyzed separately, using means test, regression analysis and model identity test, and together, using the GGE biplot method. Artificial aging at a temperature of 41 °C for 96 hours has the potential to be used to predict the performance of soybean seeds after eight months of storage. The GGE biplot is a method that can be used as a tool to analyze the relationships between aging environments and visualize the ranking of genotypes regarding the performance of seeds subjected to natural and artificial aging. Resumo: Tem sido altamente requerida a elaboração, ajustes e adoção de testes e ferramentas que auxiliem na predição da armazenabilidade de sementes. Diante disso, este trabalho teve por objetivo analisar a eficiência de diferentes tempos de envelhecimento artificial na predição do desempenho das sementes de soja após o armazenamento, utilizando-se o método GGE biplot. Sementes de seis genótipos foram submetidas ao armazenamento, sob condição refrigerada e não refrigerada, e envelhecimento artificial, sendo envelhecidas artificialmente pelos períodos de 0, 48, 96 e 144 horas. As sementes recém-colhidas e após o envelhecimento natural e artificial foram submetidas a testes de germinação e vigor. Os experimentos foram analisados separadamente, por meio de teste de médias, análise de regressão e teste de identidade de modelos, e em conjunto, utilizando-se o método GGE biplot. O envelhecimento artificial, à temperatura de 41 °C por 96 horas apresenta potencial para ser utilizado na predição do desempenho de sementes de soja após oito meses de armazenamento. O GGE biplot é um método que pode ser utilizado como ferramenta para analisar as relações entre os ambientes de envelhecimento e visualizar o ranqueamento dos genótipos quanto ao desempenho das sementes submetidas ao envelhecimento natural e artificial.

Weathering deterioration affects seed quality, especially in areas with excessive rainfall. This study aimed to evaluate the oxidative stress, physiological quality, and protein metabolism of seeds of different soybean cultivars under weathering deterioration at the pre-harvest phase. Six soybean cultivars (BMX Apolo, DM 6563, NS 5959, NA 5909, BMX Potência, and TMG 1175) were subjected to simulated rainfall at the R8 stage. Each level was divided into two applications at 72-h intervals: 60 mm (30 + 30), 120 mm (60 + 60), and 180 mm (90 + 90). Then, the seeds were harvested and evaluated for physiological potential, antioxidative enzymes, hydrogen peroxide, malondialdehyde, proteins, and protease activity. The simulated rainfall allowed the variation in seed moisture, promoting a significant reduction in germination and seed vigor, especially at 120 and 180 mm levels. There were also reductions in antioxidative enzyme activity with weathering deterioration (mainly for catalase, ascorbate peroxidase, and peroxidase), accumulation of hydrogen peroxide and malondialdehyde, and reductions in protein content and protease activity. The proposed rainfall system is efficient in inducing weathering deterioration during the pre-harvest phase and its deleterious effects. Weathering deterioration in soybean seeds in the pre-harvest stage is directly influenced by genotype.

Near-infrared (NIR) spectroscopy is a promising tool for optimizing seed analyses quickly and assertively. The aim of this study was to investigate the viability of NIR in association with chemometric methods in classification of soybean seed lots regarding their physiological potential. We evaluated 372 soybean seed lots for vigor and obtained NIR spectra from seed samples. The original spectra were pre-processed by the following methods: Standard Normal Variate (SNV), SNV + 1st and 2nd derivatives, Gap-segment derivative, and Savitzky-Golay for the first- and second-degree derivatives, as well as combinations of the methods. The lots were divided into Class I (≥ 85% germination after accelerated aging) and Class II (< 85% germination after accelerated aging); and the pre-processed spectra were used to build classification models through the following methods: K-nearest neighbors (KNN), Partial Least Squares - Discriminant Analysis (PLS-DA), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM). The PLS-DA model showed greater classification accuracy and kappa, followed by SVM. The lowest accuracy values were obtained for the NB and RF models. The regions between the wavelengths 1,000-1,200 nm and 2,200-2,500 nm were the most important for distinguishing the quality levels of soybean seeds. RESUMO: A espectroscopia no infravermelho próximo (NIR) consiste em uma ferramenta promissora para otimização das análises de sementes de forma rápida e assertiva. Este trabalho teve como objetivo investigar a viabilidade do NIR, associado a métodos quimiométricos, para classificar lotes de sementes de soja quanto ao potencial fisiológico. Foram utilizados 372 lotes de sementes de soja avaliados quanto ao vigor e obtidos espectros NIR das amostras de sementes. Os espectros originais foram submetidos aos métodos de pré-processamento Standard Normal Variate (SNV), SNV + 1ª e 2ª derivadas; Gap-segment derivative; e Savitzky-Golay, pelas derivadas de primeiro e segundo grau, e a combinação entre os métodos. Os lotes foram divididos em Classe I (≥ 85% de germinação após envelhecimento acelerado), Classe II (< 85% de germinação após envelhecimento acelerado) e os espectros pré-processados foram utilizados para a construção de modelos de classificação por meio dos métodos K-nearest neighbors (KNN), Partial Least Squares - Discriminant Analysis (PLS-DA), Naive Bayes (NB), Random Forest (RF) e Support Vector Machine (SVM). O modelo de classificação PLS-DA apresentou maior acurácia e kappa, seguido pelo SVM. Os menores valores de acurácia foram obtidos para os modelos NB e RF. As regiões entre os comprimentos de ondas 1.000-1.200 nm e 2.200-2.500 nm foram as mais importantes para distinguir os níveis de qualidade das sementes de soja.

Cedrela fissilis Vell., commonly known as cedro-rosa, is a tree species native to Brazil, with ecological and economic relevance, that exhibits seed heteromorphism associated with seed coat color. In this study, the classification of light- and dark-colored seeds using near-infrared (NIR) spectroscopy and its relationship with physiological quality was evaluated. NIR spectra were obtained, reserve compounds were quantified, and germination and vigor tests were conducted. The NIR spectra, collected from individual seeds, were preprocessed and used to develop classification models based on the Partial Least Squares - Discriminant Analysis (PLS-DA) method. The physiological and biochemical composition data were analyzed using Student’s t-test. Dark seeds showed higher thousand-seed weight, total protein content, as well as greater germination and vigor. Light seeds exhibited higher levels of reducing sugars, suggesting a lower degree of maturity or the onset of deterioration. NIR spectroscopy demonstrated high accuracy in distinguishing between light and dark seeds, especially in the spectral band near 1938 nm, whose relevance may be mainly associated with variations in total protein content. Seed coat color proved to be a reliable indicator of the physiological quality of C. fissilis seeds. RESUMO: Cedrela fissilis Vell., conhecida como cedro-rosa, é uma espécie arbórea nativa do Brasil, de relevância ecológica e econômica, que apresenta heteromorfismo de sementes associado à cor do tegumento. Neste estudo, uma classificação de sementes claras e escuras por meio da espectroscopia no infravermelho próximo (NIR) e sua relação com a qualidade fisiológica foi avaliada. Foram obtidos espectros NIR, quantificados os compostos de reserva e realizados testes de germinação e vigor. Os espectros NIR, obtidos de sementes individuais, foram pré-processados e utilizados para modelagem com base no método da Análise Discriminante por Mínimos Quadrados Parciais (PLS-DA). Os dados de qualidade fisiológica e composição bioquímica foram analisados pelo teste t de Student. Sementes escuras apresentaram maior peso de mil sementes, teor de proteína total, além de maior potencial de germinação e vigor. Sementes claras apresentaram conteúdo mais elevado de açúcares redutores, sugerindo menor grau de maturidade ou início de deterioração. A espectroscopia NIR mostrou alta precisão na distinção entre sementes claras e escuras, especialmente na região espectral próxima de 1938 nm, cuja relevância pode estar associada às variações no teor de proteína total. A coloração demonstrou ser um bom indicativo da qualidade fisiológica em sementes de C. fissilis.

The use of multispectral images has great potential to assess seed quality and represents a significant technological advance in the search for fast and non-destructive analysis techniques. However, the devices currently available are expensive. Thus, this study aimed to propose a low-cost method for acquisition and processing of multispectral images of soybean seeds and to evaluate their potential for rapid determination of seed physiological potential. The study was conducted in three steps: implementation of the multispectral image acquisition system, development of an algorithm for automatic image processing, and evaluation of the relationship between the data obtained through image analysis and the results of standard tests used to evaluate seed physiological potential. A total of 43 variables were assessed, eight related to seed physiological potential (germination and vigor) and 35 obtained from the analysis of the multispectral images. Of the variables obtained from multispectral images, 21 were related to pixel values in the images in the different bands evaluated (green, red, and infrared) and 14 associated with seed morphometric characteristics. The proposed system is efficient in obtaining multispectral images and the algorithm developed was efficient to extract morphometric characteristics and pixel information from the images. The parameters obtained from the NIR spectrum region showed a good relationship with the physiological potential of soybean seeds.

Physalis ixocarpa is a Solanaceae species commonly consumed in Mexico and holds significant market value in horticulture in Brazil. Although seeds are the primary means of propagation for this species, there are few studies on seed quality assessment. The objectives of this research were: (i) to investigate the potential of X-ray imaging as a method for evaluating the morphological characteristics of P. ixocarpa seeds and as a complementary approach to verifying the quality of seed lots processed by a gravity table; and (ii) to correlate the data obtained from radiographic images with the physiological potential of the seeds. Seeds from two accessions were separated using a gravity table, generating seed lots of high, intermediate-high, intermediate-low, and low density. X-ray images of the seeds were acquired, and information on tissue filling and density was correlated with physiological performance. Seeds from the high-density discharge had intact and denser tissues, as well as higher primary root protrusion speed and germination rates. Seeds from the low-density lots exhibited embryo malformations and a lower proportion of reserve tissue, resulting in reduced germination percentages and a higher occurrence of abnormal seedlings. Through radiographic image analysis, it was possible to classify P. ixocarpa seeds based on their morphological characteristics and establish correlations with their physiological potential. RESUMO: O tomatilho (Physalis ixocarpa Brot. Ex Hornem) é uma solanácea comum na alimentação dos mexicanos e de alto valor de mercado para a olericultura no Brasil. Embora as sementes sejam a principal forma de propagação da espécie, há poucos estudos sobre a avaliação da sua qualidade. Os objetivos da pesquisa foram: (i) investigar o potencial da técnica de raios X para a avaliação de características morfológicas de sementes de P. Ixocarpa e como método complementar para a verificação da qualidade dos lotes beneficiados pela mesa densimétrica; (ii) correlacionar os dados obtidos por meio das imagens radiográficas com o potencial fisiológico das sementes. Sementes de dois acessos foram separadas em mesa densimétrica originando lotes de alta, intermediária alta, intermediária baixa e baixa densidade. Foram adquiridas imagens de raios X das sementes e informações de preenchimento e densidade dos tecidos foram correlacionados com o desempenho fisiológico. Sementes provenientes da descarga de alta densidade tiveram tecidos íntegros e mais densos, além de maior velocidade de protrusão da raiz priméria e germinação. Sementes dos lotes de baixa densidade apresentaram malformações no embrião e menor proporção de tecido de reserva, o que resultou em baixo percentual de germinação e plântulas com anormalidades. Por meio da análise das imagens radiográficas, foi possível classificar as sementes de P. ixocarpa quanto as características morfológicas e correlacioná-las com o potencial fisiológico.

New computer vision solutions combined with artificial intelligence algorithms can help recognize patterns in biological images, reducing subjectivity and optimizing the analysis process. The aim of this study was to propose an approach based on interactive and traditional machine learning methods to classify soybean seeds and seedlings according to their appearance and physiological potential. In addition, we correlated the appearance of seeds to their physiological performance. Images of soybean seeds and seedlings were used to develop models using low-cost approaches and free-access software. The models developed showed high performance, with overall accuracy reaching 0.94 for seeds and seedling classification. The high precision of the models that were developed based on interactive and traditional machine learning demonstrated that the method can easily be used to classify soybean seeds according to their appearance, as well as to classify soybean seedling vigor quickly and non-subjectively. The appearance of soybean seeds is strongly correlated with their physiological performance.

Chickpea (Cicer arietinum L.) cultivation in Brazil has expanded as a winter or second-crop option, increasing demand for superior quality seeds. This study evaluated physiological performance, biochemical parameters and storability of BRS Aleppo seeds harvested at different maturation stages. Field production was performed at DAA/UFV from April to September 2020. Harvests were carried out at stages R11, R11.5, R12 and R12+7 (with 50%, 75% and 90% of pods with golden-yellow color and seven days after R12, respectively). The seeds were sealed in paper bags and stored at 23 °C ± 1.8 and 66% RH. At 0, 3, 6 and 9 months, samples were evaluated for seed moisture content, germination, accelerated aging, seedling emergence, tetrazolium test, activity of antioxidant enzymes (CAT and APX) and protein content. Chickpea seeds with higher physiological quality and storage potential were obtained when harvesting was carried out at the R11.5 and R12 stages, equivalent to 75% and 90% of the pods with golden-yellow color, respectively. Harvest delay (R12+7) reduced seed germination, vigor and storage potential, also reducing protein content and activity of APX and CAT enzymes. Storage under laboratory environment conditions for nine months reduces physiological quality of seeds, regardless of the harvest time.

Cultivation of chickpea has been expanding in Brazil, and defining appropriate strategies for its preservation is essential. The aim of this study was to evaluate the biochemical and physiological changes in chickpea seeds stored in different packaging materials and environmental conditions. Seeds of the BRS Aleppo cultivar were placed in impermeable (plastic) and permeable (paper) packaging and then stored under the following conditions: cold and dry storage - CS (8 ± 1.0 °C and 35 ± 1.3% RH), cooled room - CR (18 ± 1.3 °C and 62 ± 4.0% RH), and ambient conditions without climate control - AMB (24 ± 1.8 °C and 68 ± 6.7% RH). At the beginning of storage and at 3, 6, 9, and 12 months, the seeds were evaluated regarding moisture content, germination, first germination count, seedling length, accelerated aging, electrical conductivity, malondialdehyde content, and superoxide dismutase and catalase enzyme activity. Storage under CR conditions, regardless of the packaging, and under AMB conditions in impermeable packaging (plastic) maintained seed germination for up to twelve months, although vigor decreased after nine months. The physiological quality of the seeds stored under AMB conditions in porous packaging (paper) declined from six months on, showing that this condition is unsuitable for storage for 12 months. Under this condition, biochemical changes harmful to seed quality occurred, such as lipid peroxidation and reduction in SOD and CAT enzyme activity. RESUMO: O cultivo do grão-de-bico vem se expandindo no Brasil e definir estratégias adequadas para a sua conservação é fundamental. Objetivou-se avaliar as alterações bioquímicas e fisiológicas em sementes de grão-de-bico armazenadas em diferentes embalagens e condições de ambiente. Sementes da cultivar BRS Aleppo foram acondicionadas em embalagem impermeável (plástico) e permeável (papel) e armazenadas em: câmara fria e seca - CF (8 °C ± 1,0 e 35% UR ± 1,3); sala refrigerada - REF (18 °C ± 1,3 e 62% UR ± 4,0) e ambiente não controlado - AMB (24 °C ± 1,8 e 68% UR ± 6,7). Inicialmente e aos 3, 6, 9 e 12 meses de armazenamento as sementes foram avaliadas quanto ao teor de água, germinação, primeira contagem de germinação, comprimento de plântula, envelhecimento acelerado, condutividade elétrica, conteúdo de malonaldeído e atividade das enzimas superóxido dismutase e catalase. O armazenamento em REF, independente da embalagem, e em AMB na embalagem impermeável (plástico) permitiu manter a germinação por até doze meses, com redução do vigor após nove meses. Houve redução da qualidade fisiológica das sementes armazenadas em AMB em embalagem porosa (papel) a partir de seis meses, sendo essa condição inadequada para o armazenamento por 12 meses, ocorrendo alterações bioquímicas prejudiciais à qualidade das sementes como peroxidação lipídica e redução da atividade das enzimas SOD e CAT.