Proceedings

Find matching any: Reset
Rolim, G
Chaer, G.M
Freire Campos, A
Add filter to result:
Authors
Rodrigues , L
Luns, S
Rolim, G
Canata, T
Carreira, V
da Silveira, E.M
Nogueira, F.I
Camargo, S.D
Freire Campos, A
Valiati, J
Leite, E.F
Fernandes Paiva, D
Chaer, G.M
Topics
Predictive Modeling, Phenotyping, and Digital Tools for Decision Support
Decision Support Systems, Cloud Platforms, and Open Data Solutions
Type
Poster
Oral
Year
2026
Home » Authors » Results

Authors

Filter results3 paper(s) found.

1. Use of Textural and Spectral Data in Predictive Modeling of Sugarcane Yield

Sugarcane is one of the most important crops in Brazil, playing a strategic role in the production of sugar, ethanol, and bioenergy. Efficient monitoring of crop yield is essential for agricultural management and decision-making; however, conventional yield estimation methods are generally labor-intensive, destructive, and inefficient in capturing spatial variability within fields. In this context, the use of remote sensing techniques integrated with machine learning models emerges as a promising... L. Rodrigues , S. Luns, G. Rolim, T. Canata, V. Carreira

2. Mobile Edge AI for Detection of Grape Clusters and Disease Symptoms in Vineyards

Precision viticulture demands accessible technological solutions that enable rapid disease diagnosis and production monitoring directly in the field. In real-world production contexts, dependence on cloud connectivity, external servers, or specialized hardware limits the adoption of computer vision tools by small and medium-sized farmers. In this context, this work presents a solution based on artificial intelligence embedded in a mobile application for the detection of grape bunches and leaves... E.M. Da Silveira, F.I. Nogueira, S.D. Camargo, A. Freire Campos, J. Valiati, E.F. Leite

3. Transforming Agronomic Tables into Continuous Sufficiency and Fertilizer-rate Functions for Digital Recommendation Systems

Soil-test interpretation tables and fertilizer recommendation tables are widely used in agronomic practice, but they typically classify results into discrete categories (e.g., very low, low, medium, and high). While this format is suitable for manual consultation, it introduces artificial “jumps” between classes and limits automation when implementing diagnostic and recommendation rules in computerized systems. In this study, we developed a two-step methodology to convert these tables... D. Fernandes Paiva, G.M. Chaer