Scholarlink

<p>Iron (Fe) deficiency significantly affects the quality of peaches in temperate zones. Conventional iron assessment methods, such as laboratory analysis, are time- and resource- consuming. This study presents an image-based diagnostic tool for rapid estimation of the iron status in peach (<i>Prunus persica</i> (L.) Batsch) orchards. Therefore, a dataset of 1000 peach leaves from 200 trees across 65 orchards was collected and photographed. The leaves were then labeled based on the active iron (Fe<sup>2+</sup>) concentration, as determined by the orthophenanthroline extraction and atomic absorption spectrometry in the laboratory. Thirty-six different features were extracted from the images and analyzed using linear regression and neural network models. Subsequently, the most relevant features were identified by stepwise linear regression and sensitivity analysis to refine the models. The optimal linear model, incorporating blue difference chroma (Cb), lightness (L), green-minus-red (GMR), and normalized red index (NRI), achieved an <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(R^2=0.80\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(RMSE=1.08\)</EquationSource> </InlineEquation>, and <InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(MAE=0.80\)</EquationSource> </InlineEquation>. The neural network model, with selected features showed slightly better accuracy (<InlineEquation ID="IEq4"> <EquationSource Format="TEX">\(R^2 = 0.83\)</EquationSource> </InlineEquation>, <InlineEquation ID="IEq5"> <EquationSource Format="TEX">\(RMSE = 1.05\)</EquationSource> </InlineEquation>, and <InlineEquation ID="IEq6"> <EquationSource Format="TEX">\(MAE = 0.77\)</EquationSource> </InlineEquation>) compared to the linear model. The results indicate the potential of this method as an in-situ alternative to laboratory analysis for estimating active iron in peach leaves.</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

A cost-effective image-based machine learning framework for automating active iron estimation in Peach (Prunus persica (L.) Batsch) Leaves

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月9日

查看全文
  • Aydin Imani,
  • Ebrahim Sepehr,
  • Zed Rengel,
  • Nasim Hajizade

摘要

Iron (Fe) deficiency significantly affects the quality of peaches in temperate zones. Conventional iron assessment methods, such as laboratory analysis, are time- and resource- consuming. This study presents an image-based diagnostic tool for rapid estimation of the iron status in peach (Prunus persica (L.) Batsch) orchards. Therefore, a dataset of 1000 peach leaves from 200 trees across 65 orchards was collected and photographed. The leaves were then labeled based on the active iron (Fe2+) concentration, as determined by the orthophenanthroline extraction and atomic absorption spectrometry in the laboratory. Thirty-six different features were extracted from the images and analyzed using linear regression and neural network models. Subsequently, the most relevant features were identified by stepwise linear regression and sensitivity analysis to refine the models. The optimal linear model, incorporating blue difference chroma (Cb), lightness (L), green-minus-red (GMR), and normalized red index (NRI), achieved an \(R^2=0.80\) , \(RMSE=1.08\) , and \(MAE=0.80\) . The neural network model, with selected features showed slightly better accuracy ( \(R^2 = 0.83\) , \(RMSE = 1.05\) , and \(MAE = 0.77\) ) compared to the linear model. The results indicate the potential of this method as an in-situ alternative to laboratory analysis for estimating active iron in peach leaves.