Fernanda de Fátima da Silva Devechio

Dr. Fernanda de Fátima da Silva Devechio

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
3 November 2025 in Agriengineering
Verified
Journal Article
Open access
PDF file
GMGuilherme Augusto Martins
Guilherme Augusto Martins
MBMurilo Mesquita Baesso
Murilo Mesquita Baesso
FDFernanda de Fátima da Silva Devechio
Fernanda de Fátima da Silva Devechio
ATAdriano Rogerio Bruno Tech
Adriano Rogerio Bruno Tech
JRJamile Raquel Regazzo
Jamile Raquel Regazzo
MLMurilo De Lima Leao
Murilo De Lima Leao
Sorghum (Sorghum bicolor L.) is a resilient crop with high relevance in tropical and semi-arid regions, where nutritional deficiencies, particularly of nitrogen (N) and potassium (K), limit yield. This study evaluated the potential of RGB imagery combined with machine learning to detect N and K deficiencies in sorghum at different phenological stages. The traditional models showed significant limitations in distinguishing nutritional status, especially at the early V4 stage, where accuracies remained below 40%. At the flowering stage, their performance improved for nitrogen detection, reaching up to 58% accuracy, but remained insufficient for potassium (below 30%). In stark contrast, the CNN demonstrated substantially superior performance, effectively identifying even subtle visual symptoms. For nitrogen deficiency, the CNN achieved high accuracies of 76% at the V4 stage and 87% at flowering. While potassium classification proved more challenging overall, the CNN still outperformed traditional models, reaching 55% accuracy at flowering. These results indicate that deep learning is a powerful and viable low-cost tool for the early and accurate diagnosis of nutrient deficiencies in sorghum, overcoming the limitations of conventional machine learning approaches.

23 September 2025 in Agriengineering
Verified
Journal Article
Open access
PDF file
TSThiago Silva
Thiago Silva
FDFernanda de Fátima da Silva Devechio
Fernanda de Fátima da Silva Devechio
MTMarcos Tavares
Marcos Tavares
JRJamile Raquel Regazzo
Jamile Raquel Regazzo
ESEdson José de Souza Sardinha
Edson José de Souza Sardinha
MBMurilo Mesquita Baesso
Murilo Mesquita Baesso
Nitrogen fertilization is decisive for maize productivity, fertilizer use efficiency, and sustainability, which calls for fast and nondestructive nutritional diagnosis. This study evaluated the classification of maize plant nutritional status from red, green, and blue (RGB) leaf images using texture attributes. A greenhouse experiment was conducted under a completely randomized factorial design with four nitrogen doses, one maize hybrid Pioneer 30F35, and four replicates, at two sampling times corresponding to distinct phenological stages, totaling thirty-two experimental units. Images were processed with the gray-level cooccurrence matrix computed at three distances 1, 3, and 5 pixels and four orientations 0°, 45°, 90°, and 135°, yielding eight texture descriptors that served as inputs to five supervised classifiers: an artificial neural network, a support vector machine, k nearest neighbors, a decision tree, and Naive Bayes. The results indicated that texture descriptors discriminated nitrogen doses with good performance and moderate computational cost, and that homogeneity, dissimilarity, and contrast were the most informative attributes. The artificial neural network showed the most stable performance at both stages, followed by the support vector machine and k nearest neighbors, whereas the decision tree and Naive Bayes were less suitable. Confusion matrices and receiver operating characteristic curves indicated greater separability for omission and excess classes, with D1 standing out, and the patterns were consistent with the chemical analysis. Future work should include field validation, multiple seasons and genotypes, integration with spectral indices and multisensor data, application of model explainability techniques, and assessment of latency and scalability in operational scenarios.

6 March 2026 in Agriengineering
Verified
Journal Article
Open access
PDF file
CSCíntia Cristina Soares
Cíntia Cristina Soares
JRJamile Raquel Regazzo
Jamile Raquel Regazzo
TSThiago Silva
Thiago Silva
MTMarcos Tavares
Marcos Tavares
FDFernanda de Fátima da Silva Devechio
Fernanda de Fátima da Silva Devechio
MBMurilo Mesquita Baesso
Murilo Mesquita Baesso
The automatic detection of foliar nutritional deficiencies through computer vision represents a promising alternative within precision agriculture practices, reducing dependence on laboratory analyses and the subjectivity associated with visual inspection. This systematic review maps and compares the application of machine learning (ML) and deep learning (DL) techniques to nutritional diagnosis across different crops, highlighting methodological trends, barriers to model adoption under field conditions, and existing research gaps. Following the PRISMA guidelines (PRISMA-P and PRISMA-2020), searches were conducted in the Scopus, IEEE Xplore, and Web of Science databases, using a defined time frame and explicit inclusion and exclusion criteria, resulting in 200 articles included (2012–2026; last search on 2 February 2026). The results indicate a predominance of DL-based approaches and RGB imagery, with applications concentrated in crops such as rice and in macronutrients, mainly nitrogen (N), phosphorus (P), and potassium (K), and report a marked increase in publications from 2020 onward. Although many studies report high performance, the evidence is largely derived from controlled environments and proprietary datasets, which limit model comparability, reproducibility, and generalization to real-world scenarios. Accordingly, the main research gaps include limited validation under field conditions, identified as the primary practical barrier; the underrepresentation of micronutrients and multiple-deficiency diagnosis; and the need for lightweight architectures suitable for deployment in mobile and edge-computing applications. It is concluded that ML and DL techniques offer promising alternatives for automated nutritional diagnosis; however, advances in data standardization, open-access datasets, and validation under real field conditions are essential for consolidating these technologies in practical applications.

Verified
Journal Article
Open access
PDF file
SPSamira Polezi
Samira Polezi
GMGabriel Sgarbiero Montanha
Gabriel Sgarbiero Montanha
FDFernanda de Fátima da Silva Devechio
Fernanda de Fátima da Silva Devechio
JMJoão Paulo Rodrigues Marques
João Paulo Rodrigues Marques
Elephant grass (Pennisetum purpureum) exhibits high biomass production, is readily accepted by animals, and demonstrates good adaptation to the various soil types. Consequently, the utilization of P. purpureum shows promise in amending surface and subsurface soil acidity, thereby contributing to increased crop yield while enhancing water and nutrient utilization efficiency. In this study, the effects of corrective processes involving limestone and plastering on the root anatomy of P. purpureum were investigated. Roots subjected to different treatments were fixed, dehydrated, and embedded in historesin. Subsequently, samples were sectioned in a microtome, stained with toluidine blue for the conventional analysis, or submitted to the histochemical test. The qualitative and quantitative anatomical analyses were conducted to evaluate the impact of liming and plastering on the root structure of P. purpureum. The results showed that liming led to an increase in both the number and diameter of vessel elements, while plastering reduced these parameters compared to the acidic soils. Additionally, liming induced the formation of suberized endodermal cell walls. These findings highlight the significance of effective soil management to obtain P. purpureum plants with a well-developed vascular system, thereby promoting optimal plant performance in agricultural crops.

5 October 2026 in Journal of Education, Science and Health
Verified
Journal Article
Open access
PDF file
JBJoão Paulo Bernardi
João Paulo Bernardi
LBLucas Barbosa
Lucas Barbosa
LBLuiz Guilherme Pessoa Lourenço Bomfiglio
Luiz Guilherme Pessoa Lourenço Bomfiglio
Ronilson Martins SilvaRonilson Martins Silva
Ronilson Martins Silva
FDFernanda de Fátima da Silva Devechio
Fernanda de Fátima da Silva Devechio
PMPatricia Andrea Monquero
Patricia Andrea Monquero
As forragens representam o método mais econômico para fornecer alimento ao rebanho bovino brasileiro (Araújo et al., 2020), mas os produtores enfrentam desafios constantes com espécies invasoras que prejudicam a produtividade. As plantas daninhas Sporobolus indicus (capim-mourão) e Paspalum virgatum (capim-navalha) são particularmente relevantes, pois podem reduzir o rendimento das pastagens em até 80% e 50%, respectivamente (Barbosa et al., 2018; Blanco, 2012). Embora os herbicidas sejam frequentemente utilizados, seu excesso pode causar a contaminação do solo e do lençol freático (Brasil, 2020). Consequentemente, a pesquisa em alelopatia como uma ferramenta de manejo sustentável tem aumentado (Brasil, 2009; CEPEA/USP, 2023). Este estudo avaliou o potencial de extratos aquosos das forrageiras Andropogon gayanus, Urochloa brizantha cv. Marandu e Panicum maximum cv. Massai na supressão dessas plantas daninhas. Utilizando uma metodologia de extração adaptada de Barbosa et al. (Conte, 2018), as sementes foram tratadas com extratos nas concentrações de 0%, 5%, 10% e 20% e colocadas em uma câmara BOD sob condições controladas (Ferreira; Aquila, 2000; Hierro; Callaway, 2021). O percentual de germinação (%G) e o Índice de Velocidade de Germinação (IVG) foram determinados de acordo com Maguire (Ferreira; Aquila, 2000). Os resultados indicaram que o extrato de A. gayanus possuiu um efeito inibitório superior, particularmente contra S. indicus, onde a %G caiu de 20% para 6% e o IVG de 4,23 para 1,27. Em contraste, os capins Marandu e Massai não mostraram inibição química significativa, com o Massai confirmando o baixo potencial alelopático tipicamente associado ao gênero Panicum (Maguire, 1962). Esses achados sugerem que o A. gayanus pode ser utilizado estrategicamente em sistemas de manejo integrado para suprimir a infestação de plantas daninhas e promover a produção sustentável de pastagens tropicais (Ferreira; Aquila, 2000; Pires; Oliveira, 2011).

2 April 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Ronilson Martins SilvaRonilson Martins Silva
Ronilson Martins Silva
ISIara Maciel da Silva
Iara Maciel da Silva
RPRaimundo Vagner de Lima Pantoja
Raimundo Vagner de Lima Pantoja
ACAnderson Carvalho Corrêa
Anderson Carvalho Corrêa
RKRubens Muller Kautzmann
Rubens Muller Kautzmann
LFLetícia De Abreu Faria
Letícia De Abreu Faria
This study evaluated the effect of byproduct from mining process of granite rock doses in cultures of high demand in soil fertility with annual and perennial cycles, such as soybean and Tamani perennial grass, for two years in the municipality of Paragominas-PA. Experimental design was in randomized blocks comprising five treatments and five replications. Treatments comprised doses of byproduct from granite rock of 1000, 2000, 4000 and 6000 kg ha-1 and a control treatment (without application) applied in soybean and Tamani perennial grass. Soil parameters and crops productivity were evaluated for two years. The higher doses showed positive effects on soil fertility parameters, including potassium increases. Crops productivity had low responses to application or residual effects of the byproduct from granite rock mining process from Tracuateua-PA. The byproduct from mining process of granite rock has low influence in soil fertility and yield of soybean and Tamani perennial grass.