DSpace Coleção:https://repositorio.ufms.br/handle/123456789/30612026-04-07T20:10:37Z2026-04-07T20:10:37ZRelação entre Dados Hiperespectrais e a Composição de Aminoácidos em Genótipos de Sojahttps://repositorio.ufms.br/handle/123456789/141192025-12-11T12:17:56Z2025-01-01T00:00:00ZTítulo: Relação entre Dados Hiperespectrais e a Composição de Aminoácidos em Genótipos de Soja
Abstract: The spectral reflectance of plants can be readily correlated with physiological and biochemical
parameters. Thus, relating spectral data to amino acid (AA) content in different genetic
materials provides an innovative and efficient approach to understanding and managing genetic
diversity. The objective of this work was: (I) to separate genetic materials according to amino
acid content and spectral reflectance and (II) to establish a relationship between amino acids
and spectral bands calculated from hyperspectral data. In the 2023/2024 growing season, 32
soybean genotypes were used in randomized blocks with four replications. Spectral analysis
was performed 60 days after emergence (DAE). The samples were taken to the laboratory where
reflectance was measured using a spectroradiometer, which has the capacity to measure the
spectrum in the range of 350 to 2500 nm. The wavelengths were grouped into averages of
representative intervals, organized into 28 bands. Initially, the genotypes were subjected to
cluster analysis using the k-means algorithm. In the present study, the k value that best
discriminated the groups according to the characteristics was set at 4. A correlation was
performed to ascertain the relationship between the variables within each group. The averages
of the results were grouped using the Scott-Knott test. Soybean leaf reflectance was efficient in
separating soybean genotypes according to leaf amino acid content. The spectral bands show
relationships with amino acids. Bands B21 to B28 show the strongest positive correlations with
glutamic acid, arginine, cystine, isoleucine, leucine, methionine, proline, threonine, and valine.
Bands B12 to B17 are positively correlated with glutamic acid, histidine, methionine, proline,
and threonine. Bands B23 and B26 show positive correlations with arginine, cystine, proline,
tyrosine, and valine. Vitamins B12 to B17 are positively correlated with glutamic acid,
histidine, methionine, proline, and threonine. Vitamins B23 and B26 show positive correlations
with arginine, cystine, proline, tyrosine, and valine. Negatively correlated: Vitamins B2 to B10
are correlated with aspartic acid, alanine, arginine, methionine, proline, serine, tyrosine, and
valine; Vitamins B15 to B18 are correlated with aspartic acid, alanine, cystine, methionine,
proline, and serine; and Vitamin B27 is correlated with glycine, histidine, lysine, methionine, proline, tyrosine, and valine.
KEYWORDS: Remote sensing. High-precision phenotyping. Protein.
Tipo: Dissertação2025-01-01T00:00:00ZAplicação de espectroscopia VNIR – SWIR e aprendizado de máquinas para predição da qualidade de grãos de arroz em unidades armazenadoras e indústrias beneficiadorashttps://repositorio.ufms.br/handle/123456789/141172025-12-11T11:46:01Z2025-01-01T00:00:00ZTítulo: Aplicação de espectroscopia VNIR – SWIR e aprendizado de máquinas para predição da qualidade de grãos de arroz em unidades armazenadoras e indústrias beneficiadoras
Abstract: Rice (Oryza sativa L.) is an essential food in the global diet, and its physicochemical quality is a determining factor in the production chain. The objective of this study is to evaluate the predictive and characterization capacity of the physicochemical quality of different rice types using hyperspectral sensors and machine learning algorithms. Samples of White, Black, Red, and Parboiled rice were analyzed through hyperspectral spectroscopy (350–2500 nm) and subjected to Linear Regression; traditional models such as Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB); and deep learning models, including Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Spectral and physicochemical data were explored using multivariate analysis techniques (PCA) and cross- validation with the following metrics: Correlation Coefficient (r); Coefficient of Determination (r²); Mean Absolute Error (MAE); and Root Mean Square Error (RMSE). The results indicated that the SVM, RF, and GB models showed superior performance, with r and r² ranging from
0.95 to 1.0 and MAE and RMSE below 0.2, while deep learning models showed lower performance, especially with datasets of moderate size. Black rice stood out for its high levels of protein (~9), lipids (~2), and ash (~1.45); parboiled rice showed a higher fiber content (~2.8), while white rice was characterized by its starch content (~73). Hyperspectral spectroscopy proved to be effective in differentiating rice types, allowing the selection of relevant bands for optimized sensor development. It is concluded that the use of non-destructive technologies integrated with machine learning is promising for quality control in the rice industry, providing speed, accuracy, and sustainability in the post-harvest process.
Tipo: Dissertação2025-01-01T00:00:00ZVariação populacional de soja em função de zonas de manejo de menor fertilidade potencialhttps://repositorio.ufms.br/handle/123456789/135722025-12-02T13:47:23Z2025-01-01T00:00:00ZTítulo: Variação populacional de soja em função de zonas de manejo de menor fertilidade potencial
Abstract: Soybean (Glycine max) is a legume of extreme importance to the Brazilian economy,
seeking to increase productivity to meet global demands. The objective of this study is to
define a methodology for sowing using VRT (Variable Rate Technology) based on the
law of the minimum and to correlate the synergy between spatial variation in soil
attributes and the productivity of different areas of soybean plants. The experiment was
conducted at the Chapadão do Sul, Mato Grosso do Sul, campus. Treatments consisted of
sowing rates varying by 20% more, 20% less, and not recommended by the genetic
material manufacturers, i.e., sown using VRT. The area was sown in zones according to
the identification of the most limiting element, potassium (K), along with the CTC. The
management zones contained greater variations of 20% more seeds. The results were
analyzed using multivariate statistics. The spatial variability of K, which was defined as
limiting, influenced the spatial variability of grain yield by 4,907.84 kg ha-1. However,
the increase in the plant population in the zone with the greatest limitations compromised
grain yield as a consequence of intraspecific competition, in addition to increasing
production costs due to increased seed consumption.
Palavras-chave: Technology, variable rate, precision agriculture, spatial variability,
geostatistics.
Tipo: Dissertação2025-01-01T00:00:00ZATRIBUTOS FÍSICOS DO SOLO NA CULTURA DE SORGO CONSORCIADO SOB SISTEMA DE PLANTIO DIRETOhttps://repositorio.ufms.br/handle/123456789/132852025-11-26T13:52:44Z2025-01-01T00:00:00ZTítulo: ATRIBUTOS FÍSICOS DO SOLO NA CULTURA DE SORGO CONSORCIADO SOB SISTEMA DE PLANTIO DIRETO
Abstract: A favorable physical environment in the soil is essential and of
fundamental importance for the root growth and development of sorghum, in order to maximize crop productivity. In this study, we evaluated the physical aspects of the soil under a no-tillage system in a grain sorghum area intercropped with Urochloa ruziziensis and Crotalaria spectabilis during the second season, based on a long-term field experiment. The experimental design was a randomized block, with four cropping systems (sorghum; sorghum + Urochloa ruziziensis; sorghum + Crotalaria spectabilis; sorghum + Urochloa ruziziensis + Crotalaria spectabilis) and two crop years (2023 and 2024), with crop year considered as a random effect, totaling 16 experimental units and 4 replications. The soil physical attributes analyzed included soil bulk density (BD), gravimetric moisture (GM), total porosity (TP), microporosity (MIC), macroporosity (MAC), and root penetration resistance (PR), as well as CO2 flux and soil temperature. The cropping systems influenced the physical and biological attributes of the soil, with the sorghum + Crotalaria intercrop standing out for improving soil quality and conservation, highlighting the potential of crop integration as a sustainable management practice.
Tipo: Dissertação2025-01-01T00:00:00Z