Scholarlink

<p>Groundwater δ<sup>18</sup>O interpretation in arid regions is challenging due to complex recharge, salinization, and limited datasets. We applied ensemble machine learning, Random Forest, Lasso, and Gradient Boosting, to predict δ<sup>18</sup>O using hydrochemical and spatial variables in the mid-Nile Valley. Under random splitting, RFR performed best (R<sup>2</sup> = 0.83), followed by Lasso (0.81) and GBR (0.80). Longitude, chloride, potassium, and magnesium emerged as the main predictors, consistent with hydrochemical evidence. But performance dropped under spatial cross-validation, a more realistic test: RFR R<sup>2</sup> = 0.50, Lasso = 0.45, GBR = 0.41. So, part of the predictive skill comes from spatial structure, not transferable relationships. A sensitivity test without longitude showed that hydrochemical variables alone explain about 40% of the δ<sup>18</sup>O variance (R<sup>2</sup> = 0.405). Within the data-rich range (-3‰ to -1‰, <i>n</i> = 54), the model achieved a mean absolute residual of 0.70‰ and a 95% prediction interval of ± 2.26‰. Outside this range, for Eocene end-members (<i>n</i> = 7) and Quaternary enriched samples (<i>n</i> ≈ 6), uncertainty increased substantially. Machine learning is useful for isotope prediction in data-scarce regions, but results must be interpreted with caution. Spatial effects matter. The model is best suited for site-specific analysis within its reliable range. Future work should focus on collecting more end-member samples to bridge the isotopic gap.</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

Ensemble machine learning method for δ18O prediction in groundwater

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月21日

查看全文
  • Faten. A. Mohamed,
  • Mostafa Sadek,
  • Nema Mohamed Kandil

摘要

Groundwater δ18O interpretation in arid regions is challenging due to complex recharge, salinization, and limited datasets. We applied ensemble machine learning, Random Forest, Lasso, and Gradient Boosting, to predict δ18O using hydrochemical and spatial variables in the mid-Nile Valley. Under random splitting, RFR performed best (R2 = 0.83), followed by Lasso (0.81) and GBR (0.80). Longitude, chloride, potassium, and magnesium emerged as the main predictors, consistent with hydrochemical evidence. But performance dropped under spatial cross-validation, a more realistic test: RFR R2 = 0.50, Lasso = 0.45, GBR = 0.41. So, part of the predictive skill comes from spatial structure, not transferable relationships. A sensitivity test without longitude showed that hydrochemical variables alone explain about 40% of the δ18O variance (R2 = 0.405). Within the data-rich range (-3‰ to -1‰, n = 54), the model achieved a mean absolute residual of 0.70‰ and a 95% prediction interval of ± 2.26‰. Outside this range, for Eocene end-members (n = 7) and Quaternary enriched samples (n ≈ 6), uncertainty increased substantially. Machine learning is useful for isotope prediction in data-scarce regions, but results must be interpreted with caution. Spatial effects matter. The model is best suited for site-specific analysis within its reliable range. Future work should focus on collecting more end-member samples to bridge the isotopic gap.