Scholarlink

<p>Purpose: Coffee farming plays an essential role in the global economy, making accurate productivity prediction methods indispensable for strategic decision-making in the sector. This study aimed to develop models for early prediction of coffee production per plant based on morphological indices.</p><p>Methods:Two models were proposed using the following attributes: plant height, canopy width, and the number of fruits on the productive internodes of plagiotropic branches. In Model 1, fruit counts were manually conducted at the 4th and 5th productive nodes of the branches, while in Model 2, the average fruit count from the 1st to the 5th productive nodes was obtained automatically through branch image analysis using Detectron2, an open-source object detection library. Both models were developed using data collected at two distinct periods before harvest—the first five months prior and the second three months prior. The research was conducted in three coffee plots in Viçosa, Minas Gerais, Brazil, where 60 plants were selected to evaluate the production prediction model. During harvest, the production of each plant was individually recorded, enabling validation of the predictions. </p><p>Results: The results revealed a strong correlation between the models and the field-observed production data, especially for the model based on data collected three months before harvest. Model 1 demonstrated a better fit (R² = 0.889; RMSE = 0.923&#xa0;L/plant; MAE = 0.635&#xa0;L/plant), while Model 2 had a lower absolute error (R² = 0.747; RMSE = 0.374&#xa0;L/plant; MAE = 0.460&#xa0;L/plant). Additionally, productivity maps were generated for each plot, showing good agreement with field-observed productivity data.</p><p>Conclusions: It was concluded that the proposed models are promising for application in coffee farming, contributing to early production prediction.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Early prediction of coffee production per plant using morphological indices

  • 期刊论文

  • 发表日期：

    2026年1月3日

查看全文
  • Gabriel Dumbá Monteiro de Castro,
  • Daniel Marçal de Queiroz,
  • Domingos Sárvio Magalhães Valente,
  • Diego Bedin Marin,
  • Ryan Moreira Borges

摘要

Purpose: Coffee farming plays an essential role in the global economy, making accurate productivity prediction methods indispensable for strategic decision-making in the sector. This study aimed to develop models for early prediction of coffee production per plant based on morphological indices.

Methods:Two models were proposed using the following attributes: plant height, canopy width, and the number of fruits on the productive internodes of plagiotropic branches. In Model 1, fruit counts were manually conducted at the 4th and 5th productive nodes of the branches, while in Model 2, the average fruit count from the 1st to the 5th productive nodes was obtained automatically through branch image analysis using Detectron2, an open-source object detection library. Both models were developed using data collected at two distinct periods before harvest—the first five months prior and the second three months prior. The research was conducted in three coffee plots in Viçosa, Minas Gerais, Brazil, where 60 plants were selected to evaluate the production prediction model. During harvest, the production of each plant was individually recorded, enabling validation of the predictions.

Results: The results revealed a strong correlation between the models and the field-observed production data, especially for the model based on data collected three months before harvest. Model 1 demonstrated a better fit (R² = 0.889; RMSE = 0.923 L/plant; MAE = 0.635 L/plant), while Model 2 had a lower absolute error (R² = 0.747; RMSE = 0.374 L/plant; MAE = 0.460 L/plant). Additionally, productivity maps were generated for each plot, showing good agreement with field-observed productivity data.

Conclusions: It was concluded that the proposed models are promising for application in coffee farming, contributing to early production prediction.