Thiago Silva

Dr. Thiago Silva


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2013 in Soil and Tillage Research
Verified
Journal Article
Closed access
DGDaniele Vieira Guimarães
Daniele Vieira Guimarães
MGMaria Isidória Silva Gonzaga
Maria Isidória Silva Gonzaga
TSTácio Oliveira da Silva
Tácio Oliveira da Silva
TSThiago Silva
Thiago Silva
NDNildo da Silva Dias
Nildo da Silva Dias
MMMaria Iraildes Silva Matias
Maria Iraildes Silva Matias

26 July 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
MTMarcos Tavares
Marcos Tavares
CSCarlos Augusto Alves Cardoso Silva
Carlos Augusto Alves Cardoso Silva
JRJamile Raquel Regazzo
Jamile Raquel Regazzo
ESEdson José de Souza Sardinha
Edson José de Souza Sardinha
TSThiago Silva
Thiago Silva
MBMurilo Mesquita Baesso
Murilo Mesquita Baesso
Beans are the main direct source of protein consumed by humans in the world and their productivity is directly linked to nitrogen. The short crop cycle imposes the need for fast methodologies for N quantification. In this work, we evaluated the performance of four machine learning algorithms in nitrogen estimation using NIR spectroscopy, comparing predictions between complete spectral data and only intervals obtained with the variable importance in projection (VIP). Doses of 0, 50, 100, and 150 kg ha−1 of N were applied and leaf reflectance was collected. Weka software was used to test the algorithms. The selection of the most effective spectral zones was made with the variable importance in projection (VIP). The intervals of 700–740 nm and 983–995 nm were considered the most important for the study of nitrogen. More efficient predictions were verified for RF and KNN models (R2 = 0.89, RMSE = 2.23 g kg−1; and R2 = 0.80, RMSE = 2.89 g kg−1, respectively) when only the most important spectral regions were included. The efficiency of nitrogen prediction based on NIR reflectance combined with machine learning was verified, which can serve as an important tool in precision agriculture.

18 June 2024 in Agriengineering
Verified
Journal Article
Open access
PDF file
JRJamile Raquel Regazzo
Jamile Raquel Regazzo
TSThiago Silva
Thiago Silva
MTMarcos Tavares
Marcos Tavares
ESEdson José de Souza Sardinha
Edson José de Souza Sardinha
Caroline FigueiredoCaroline Figueiredo
Caroline Figueiredo
MBMurilo Mesquita Baesso
Murilo Mesquita Baesso
Among the technological tools used in precision agriculture, the convolutional neural network (CNN) has shown promise in determining the nutritional status of plants, reducing the time required to obtain results and optimizing the variable application rates of fertilizers. Not knowing the appropriate amount of nitrogen to apply can cause environmental damage and increase production costs; thus, technological tools are required that identify the plant’s real nutritional demands, and that are subject to evaluation and improvement, considering the variability of agricultural environments. The objective of this study was to evaluate and compare the performance of two convolutional neural networks in classifying leaf nitrogen in strawberry plants by using RGB images. The experiment was carried out in randomized blocks with three treatments (T1: 50%, T2: 100%, and T3: 150% of recommended nitrogen fertilization), two plots and five replications. The leaves were collected in the phenological phase of floral induction and digitized on a flatbed scanner; this was followed by processing and analysis of the models. ResNet-50 proved to be superior compared to the personalized CNN, achieving accuracy rates of 78% and 48% and AUC of 76%, respectively, increasing classification accuracy by 38.5%. The importance of this technique in different cultures and environments is highlighted to consolidate this approach.

9 January 2025 in Plants
Verified
Journal Article
Open access
ESEudocio Rafael Otavio Silva
Eudocio Rafael Otavio Silva
TSThiago Silva
Thiago Silva
MWMarcelo Chan Fu Wei
Marcelo Chan Fu Wei
RSRicardo Augusto de Souza
Ricardo Augusto de Souza
Jose MolinJose Molin
Jose Molin
Coffee yield exhibits plant-level variability; however, due to operational issues, especially in smaller operations, the scouting and management of coffee yields are often hindered. Thus, a cell-size approach at the field level is proposed as a simple and efficient solution to overcome these constraints. This study aimed to present the feasibility of a cell-size approach to characterize spatio-temporal coffee production based on soil and plant attributes and yield (biennial effects) and to assess strategies for enhanced soil fertilization recommendations and economic results. The spatio-temporal study was conducted using a database composed of yield and soil and plant attributes from four harvest seasons of coffee plantation in the southeast region of Brazil. We used small plots as cells, where soil, leaf, and yield samples were taken, and the average value of each variable was assigned to each cell. The results indicated that macro- and micronutrient contents in the soil and leaves exhibited spatio-temporal heterogeneity between cells, suggesting that customized coffee tree management practices could be employed. The cell-size sampling strategy identified regions of varying yield over time and associated them with their biennial effect, enabling the identification of profitable areas to direct resource and input management in subsequent seasons. This approach optimized the recommendation of potassium and phosphate fertilizers on farms, demonstrating that localized management is feasible even with low spatial resolution. The cell-size approach proved to be adequate on two coffee farms and can be applied in scenarios with limited resources for high-density sampling, especially for small- and medium-sized farms.

1 March 2017 in Revista Caatinga
Verified
Journal Article
Open access
PDF file
JMJuliana Augusta Moura
Juliana Augusta Moura
MGMaria Isidória Silva Gonzaga
Maria Isidória Silva Gonzaga
TSThiago Silva
Thiago Silva
DGDanielle Vieira Guimaraes
Danielle Vieira Guimaraes
ISIsaac Leal DE Santana
Isaac Leal DE Santana
The use of organic residues and compost is a common practice to improve soil quality and content of organic matter. In this study, the labile and stable fractions of soil organic matter were evaluated after application of layers of fresh (non-composted) or composted organic residues in a 6-year-old citrus orchard. The experiment was set up as a randomized block design, with 6 treatments: control without NPK, control with NPK, non-composted organic residue (NCOR, with and without NPK), and composted organic residue (humus, with and without NPK), with three replicates. The treatments were applied under the plant canopy. Soil samples were collected from the 0-0.05, 0.05-0.10, and 0.10-0.15 m layers. There were increases of 10.3, 22.4, 16.3, and 37.1 % in the organic carbon contents of the surface soil for the treatments using NCOR without NPK, NCOR with NPK, humus with NPK, and humus without NPK, respectively. The organic carbon contents of the labile fraction varied from 1.0 to 12.8 g kg-1, representing between 8 and 62 % of the total carbon. The carbon concentrations in the stable fraction varied from 3.1 to 9.7 g kg-1, representing between 38 and 92 % of the total carbon, and this was the dominant fraction for most of the treatments.

7 July 2017 in Interfaces Científicas - Saúde e Ambiente
Verified
Journal Article
Closed access
PDF file
CSCamila Pinheiro Costa Silva
Camila Pinheiro Costa Silva
LOLarissa Santos Oliveira
Larissa Santos Oliveira
TSThiago Silva
Thiago Silva
JFJosé Augusto Andrade Filho
José Augusto Andrade Filho
IRIgor Adriano de Oliveira Reis
Igor Adriano de Oliveira Reis
A água de coco é uma bebida popularmente consumida na sua forma in natura em diversas regiões do Brasil. Quando envasada insere-se na linha dos produtos de conveniência, apresentando praticidade no manuseio e estocagem. A sua extração acontece de forma artesanal ou mecânica, sendo preocupantes as condições higiênico-sanitárias nas quais são produzidos. Considerando o aumento do consumo deste alimento e os aspectos citados acima, o presente estudo teve como objetivo avaliar a qualidade microbiológica de águas de coco comercializadas no município de Aracaju, Sergipe. Os parâmetros microbiológicos contidos na resolução RDC nº 12 de 2 de janeiro de 2001 (ANVISA) e, além destes, o número de coliformes totais foram determinados em 10 amostras de água de coco, adquiridas em distintos estabelecimentos comerciais. Verificou-se que 62,5% das amostras de água de coco extraídas e envasadas artesanalmente apresentaram coliformes acima do limite legal. Nas amostras em embalagens cartonadas não se detectou coliformes. Salmonella spp. foi detectada em apenas uma amostra. Conclui-se que a água de coco em embalagens tetra park apresentava melhor qualidade microbiológica e a extraída e envasada artesanalmente apresentava a maior contaminação, sugerindo falha na aplicação de boas práticas para o envasamento e comercialização da água de coco.