Scholarlink

<p>Selenium (Se) is a vital nutrient for human health and closely associated with various bodily functions. Human intake of Se is often increased through the diet, and the Se level in crops is not solely dictated by soil Se levels. For example, it also depends on the interactions between plants and soil elements. This study explored the factors influencing the Se bioaccumulation coefficient in lilies in karst areas, based on 1:50,000 land-quality geochemical survey data. Utilizing a random forest, two indicators (Se and nitrogen) were selected from 49 soil indicators to predict the Se content in lilies, thereby providing a more flexible and scientific approach to planning Se-rich agricultural products. The results show that the random forest model predicts Se content in lilies more accurately and precisely than traditional multiple linear regression. These findings provide theoretical support for the rational layout of Se-rich agricultural production areas and promotes the high-quality, sustainable development of regional specialty agriculture.</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

Exploring influential indicators for cultivating selenium-rich lily using a random forest model

  • 期刊论文

  • 发表日期：

    2025年9月16日

查看全文
  • Hao Gong,
  • Liangliang Dai,
  • Jie Luo,
  • Qiaohui Zhu

摘要

Selenium (Se) is a vital nutrient for human health and closely associated with various bodily functions. Human intake of Se is often increased through the diet, and the Se level in crops is not solely dictated by soil Se levels. For example, it also depends on the interactions between plants and soil elements. This study explored the factors influencing the Se bioaccumulation coefficient in lilies in karst areas, based on 1:50,000 land-quality geochemical survey data. Utilizing a random forest, two indicators (Se and nitrogen) were selected from 49 soil indicators to predict the Se content in lilies, thereby providing a more flexible and scientific approach to planning Se-rich agricultural products. The results show that the random forest model predicts Se content in lilies more accurately and precisely than traditional multiple linear regression. These findings provide theoretical support for the rational layout of Se-rich agricultural production areas and promotes the high-quality, sustainable development of regional specialty agriculture.