PAPablo de Sousa Arantes

Pablo de Sousa Arantes

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pablo de Sousa Arantes has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Physiological soybean seed quality in response to the application of plant bioregulator

    by Júlia Carvalho Costa, Adriano Teodoro Bruzi, Antonio Henrique Fonseca de Carvalho, Pablo Souza Arantes, Taine Teotonio Teixeira da Rocha, Heloísa Oliveira dos Santos

    The present study aimed to evaluate the physiological quality of freshly harvested and stored soybean seeds following the foliar application of nutrients and a plant bioregulator. Three field experiments were conducted in the municipality of Lavras, Minas Gerais, Brazil. Treatments consisted of three soybean cultivars (Desafio RR, M5917 IPRO, and 95R40 IPRO) subjected to foliar application of nine products containing nutrients and plant bioregulators at the phenological stages R1 and R2, in addition to a control treatment. After harvest, the seeds were subjected to physiological analyses, including electrical conductivity, vigor and viability by the tetrazolium test, emergence speed index, and accelerated aging, at three evaluation periods: immediately after harvest, and after three and six months of storage. Data were analyzed by analysis of variance, with effects assessed using the F-test and means compared through 95% confidence intervals. A significant effect of product application was observed for most physiological variables. However, responses varied according to cultivar, product applied, and storage period. The effects were more pronounced in vigor-related traits, particularly in freshly harvested seeds and after three months of storage. Overall, treatments did not show a consistent effect on seed storability.

  • Open Access

    Determination of full maturity in soybean using machine-learning models and UAV imagery

    by Pablo de Sousa Arantes, Adriano Teodoro Bruzi, Marcelo Junqueira Araujo Ferraz, Allyson Gabriel Santos de Paula, Jose Airton Rodrigues Nunes, Raphael Rodrigues Pereira, Júlia Silva Passos dos Santos

    This study proposes a machine-learning approach to predict soybean maturity using climatic variables and unmanned aerial vehicle (UAV) data, focusing on Brazilian high-altitude tropical conditions. The objective was to evaluate and compare different models for predicting days to full maturity, first using climatic variables exclusively and then incorporating the Green Leaf Index (GLI). Eight algorithms were initially tested, and the three best-performing models were re-evaluated with inclusion of the GLI. Model performance was assessed using R², mean absolute error (MAE), and root mean square error (RMSE). Random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNN) showed the highest accuracy, with RF outperforming the others. The inclusion of the GLI improved predictions by capturing the decline in canopy greenness. These findings demonstrate that combining machine learning, climatic data, and vegetation indices is an efficient, low-cost approach for predicting soybean maturity, supporting high-throughput phenotyping in breeding programs.

  • Open Access

    Adding climate variables to enhance understanding of grain yield full maturity traits in soybean

    by Gabriel Mendes Villela, Vitório Antônio Pereira de Souza, Pablo de Sousa Arantes, Adriano Teodoro Bruzi, Taine Teotônio Teixeira da Rocha, Gabriel de Siqueira Gesteira, Guilherme Leite Dias Vilela, Nelson Junior Dias Vilela

    This study evaluated 55 soybean cultivars over four crop seasons in Brazil to determine how key abiotic covariates influence grain yield and full maturity (FM). Comprehensive daily climatological data, including precipitation, solar radiation, relative humidity, mean, maximum, and minimum temperature, and photoperiod were incorporated into a full linear regression framework. Due to strong multicollinearity among climatic variables, elastic-net regularization was applied to select influential covariates and stabilize parameter estimates. Grain yield exhibited high sensitivity to climatic variation, retaining a larger set of predictors in the penalized model compared with FM. Minimum temperature influenced nighttime respiration and carbon balance, exerting consistent secondary effects. FM was primarily regulated by solar radiation- and photoperiod-related variables. The most limiting climatological factors for soybean yield in Brazilian environments are those associated with thermal stress, particularly minimum temperatures. These findings highlight the need for breeding programs to prioritize cultivars with enhanced tolerance to thermal stress.

  • Open Access

    Participatory and conventional plant breeding for selection of soybean cultivars for smallholder agriculture in Mozambique

    by Klinarda Bernardo Viandro, Taine Teotonio Teixeira da Rocha, Adriano Teodoro Bruzi, Stephen Kyei Boahen, Michelle da Fonseca Santos, Mateus Ribeiro Piza, Pablo de Sousa Arantes, Júlia Silva Passos dos Santos, Vitório Antônio Pereira de Souza

    The aim of this study was to select soybean cultivars adapted to Mozambican farming systems using participatory and conventional breeding and to assess the extent of agreement between these approaches. Experiments were conducted in the Zambézia and Tete provinces during the 2021/22 growing season in a randomized complete block design with 41 genotypes and three replications. In the participatory plant breeding approach, 165 farmers participated in the selection process. The top 35 cultivars for each method were identified and then compared using a coincidence index, which resulted in -29.41, confirming the divergence. The cultivar TGX 2002-3DM was ranked highest in the conventional method, whereas TGX 2014-16FM was selected by farmers. These findings indicate the need to incorporate farmers’ preferred traits in selecting varieties in the breeding process to increase the likelihood of adoption of the varieties. These results support the hypotheses proposed in this study.

  • Open Access

    Application of YOLO-based deep learning and UAV imagery in hybrid maize seed production

    by Marcelo Araújo Junqueira Ferraz, Pablo de Sousa Arantes, Adriano Teodoro Bruzi, Adão Felipe dos Santos

    In maize breeding programs, emasculation is a critical step in the production of hybrid seeds, occurring prior to anthesis. Therefore, an accurate identification of tassels is paramount for the efficient execution of detasseling. However, tassel detection poses significant challenges due to environmental variability in production fields, the spatial resolution of aerial images, lighting conditions, and the phenotypic variability of the plants. Traditional methods are also predisposed to subjectivity and detasseling errors. This study proposes a solution to these challenges by integrating a remote sensing platform, utilizing an unmanned aerial vehicle (UAV), with a deep learning (DL) algorithm to enhance the efficiency of maize tassel detection. The UAV captured the red-green-blue (RGB) images spectral region at an altitude of 20 m, and the YOLOv4 algorithm was employed to develop the tassel detection model. The image database was constructed using preprocessing strategies to augment the dataset. The detection model based on the YOLOv4 architecture demonstrated satisfactory results, with an overall accuracy of 0.89, ranging from 0.84 to 0.92, depending on the levels of detasseling errors and the morphological characteristics of maize tassels. This study underscores the applicability of YOLOv4 in detecting plants with detasseling errors in seed production fields, thereby contributing to the purity and quality of hybrid seeds.