The classification of sugarcane varieties using products derived from remote sensing allows for the monitoring of plants with different profiles without necessarily having physical contact with the study objects. However, differentiating between varieties can be challenging due to the similarity of the spectral characteristics of each crop. Thus, this study aimed to classify four sugarcane varieties through deep neural networks, subsequently comparing the results with traditional machine learning techniques. In order to provide more data as input for the classification models, along with the multi-band values of the pixels and vegetation indices, other information can be obtained from the sensor bands through RGB combinations by reconciling different bands so as to yield the characteristics of crop varieties. The methodology created to discriminate sugarcane varieties consisted of a dense neural network, with the number of hidden layers determined by the greedy layer-wise method and multiples of four neurons in each layer; additionally, a 5-fold evaluation in the training data was composed of Sentinel-2 band data, vegetation indices, and RGB combinations. Comparing the results acquired from each model with the hyperparameters selected by Bayesian optimisation, except for the neural network with manually defined parameters, it was possible to observe a greater precision of 99.55% in the SVM model, followed by the neural network developed by the study, random forests, and kNN. However, the final neural network model prediction resulted in the 99.48% accuracy of a six-hidden-layers network, demonstrating the potential of using neural networks in classification. Among the characteristics that contributed the most to the classification, the chlorophyll-sensitive bands, especially B6, B7, B11, and some RGB combinations, had the most impact on the correct classification of samples by the neural network model. Thus, the regions encompassing the near-infrared and shortwave infrared regions proved to be suitable for the discrimination of sugarcane varieties.

Objetivou-se com o presente estudo avaliar o efeito residual da adição de pó de rocha basáltica associado ou não a adubação química, sobre os atributos químicos do solo e produtividade da cultura da soja. O delineamento experimental foi de blocos casualizados em esquema fatorial (5x2), testando, cinco doses de pó de rocha (0; 2,5; 5,0; 7,5 e 10,0 Mg ha-1), com ou sem adubação química de NPK na formulação 05-25-06, com quatro repetições. O experimento foi conduzido em condições de campo. Foram avaliadas as características agronômicas de altura final de plantas, altura da inserção do primeiro legume, diâmetro do coleto, peso de 1000 grãos, produtividade da soja e os atributos químicos do solo. A adubação química influenciou os teores dos nutrientes P, K e Mn no solo. Na camada de 0-10 cm houve aumento dos teores de P e K. Na camada de 10-20 cm ocasionou redução no teor de Mn. O residual da aplicação das doses de pó de basalto ocasionou a redução das concentrações foliares de P, Cu, Zn. A adubação química complementar favoreceu a redução da concentração do Mg foliar. Altura de plantas, diâmetro do coleto, peso de grãos e produtividade foram maiores nos tratamentos que receberam a adubação química. A pequena liberação dos nutrientes do pó de basalto indica que tal material não pode ser utilizado como a principal fonte de nutrientes às plantas.

Objective: This research aimed to compare two methods for determining soil organic carbon, in two soils with different textures. Method: Soil samples were collected in three locations (Dourados-MS, Chapadão do Sul-MS and Cassilândia-MS), with different textures (clayey and sandy), at a depth of 0-20 cm, to determine organic carbon . The results were subjected to statistical analysis, using the SAS version 6 software and the means were compared using the t test (p < 0.05). In the correlation study, linear regression analyzes were performed. Result and conclusion: There was variation in the soil organic carbon content (SOC) between the methods studied for both soils. Measuring soil samples by volume (spectrophotometer) modifies the results, regardless of the soil texture. There is greater variation between the data obtained in soils with a higher COS content than in soils where the COS content is lower. Furthermore, the results indicate the need for new studies in which soils from agricultural areas and under native vegetation are selected by soil classes, textures and types of land use. Research implications: Research related to comparison studies of SOC determination methods is of paramount importance, as there is a lack of information regarding the definition and recommendation of the most appropriate method. Originality/value: With this study it is possible to disseminate to the scientific community methods for determining SOC that make it possible at the same time to reduce the use of chemical reagents, without this negatively interfering with the quality of soil organic carbon determination.

A aplicação de fontes alternativas de materiais que melhoram as condições físicas, químicas, microbiológicas e mineralógicas de solos agrícolas é uma prática que vem ganhando cada vez mais importância no Brasil. Objetivou-se com o presente estudo avaliar os atributos químicos de solo e os efeitos na produção vegetal, após uso de pó de basalto associado ou não com adubação química adicional. O delineamento experimental utilizado no experimento foi o de blocos ao acaso, com distribuição em esquema fatorial (5x2), sendo cinco doses de pó de rocha (0; 2,5; 5,0; 7,5 e 10,0 Mg ha^-1), com adição ou não de adubação química (com e sem), com quatro repetições. O experimento foi realizado em condição de campo. As variáveis analisadas foram: diâmetro do coleto, altura de plantas, número de vagens por planta, produtividade e atributos químicos do solo nas camadas de 0-10 e 10-20 cm. A adubação química influenciou os teores dos nutrientes e valores de SB, CTC, V%. A adição do pó de basalto contribuiu para aumento nos teores de Fe nas duas camadas de solo avaliadas, com incremento também de Cu e redução da V% na camada de 10-20 cm. Altura de plantas e diâmetro do coleto da soja foram influenciadas pela adição do pó de rocha, com maiores valores de altura e diâmetro de coleto observados com a adição de 2,5 Mg ha^-1 de pó de basalto. A produtividade da cultura da soja foi influenciada pela adição de pó de basalto, com produtividade máxima obtida na dose de 8,3 Mg ha^-1.

Objective: This research aimed to compare two methods for determining soil organic carbon, in two soils with different textures. Method: Soil samples were collected in three locations (Dourados-MS, Chapadão do Sul-MS and Cassilândia-MS), with different textures (clayey and sandy), at a depth of 0-20 cm, to determine organic carbon . The results were subjected to statistical analysis, using the SAS version 6 software and the means were compared using the t test (p < 0.05). In the correlation study, linear regression analyzes were performed. Result and conclusion: There was variation in the soil organic carbon content (SOC) between the methods studied for both soils. Measuring soil samples by volume (spectrophotometer) modifies the results, regardless of the soil texture. There is greater variation between the data obtained in soils with a higher COS content than in soils where the COS content is lower. Furthermore, the results indicate the need for new studies in which soils from agricultural areas and under native vegetation are selected by soil classes, textures and types of land use. Research implications: Research related to comparison studies of SOC determination methods is of paramount importance, as there is a lack of information regarding the definition and recommendation of the most appropriate method. Originality/value: With this study it is possible to disseminate to the scientific community methods for determining SOC that make it possible at the same time to reduce the use of chemical reagents, without this negatively interfering with the quality of soil organic carbon determination.