Scholarlink

<p>Wastewater land application is widely recognized as a solution to global water scarcity. However, concerns about its environmental sustainability arise due to potential soil salinization. Three tree-based machine learning models were devised to predict soil salinity using data from previous field studies, evaluated using R<sup>2</sup> and RMSE, and interpreted using permutation importance, partial dependence plots, Shapley value plots, and Break Down plots. Data was preprocessed and split into 80% training and 20% test sets prior to being subjected to 10-fold cross-validation and hyperparameter tuning via grid search. Random forest (R<sup>2</sup> = 0.920, RMSE = 0.374 dS/m) performed better than decision tree (R<sup>2</sup> = 0.832, RMSE = 0.614 dS/m) and gradient boosting decision trees (R<sup>2</sup> = 0.918, RMSE = 0.396 dS/m) on test data. The permutation importance order was: initial soil EC &gt; initial soil pH &gt; wastewater pH &gt; total irrigation days &gt; total precipitation &gt; total irrigated wastewater amount &gt; soil depth &gt; wastewater EC. This study provides new insights into how different input features impact soil salinity and has important implications for sustainable management of wastewater land application to ensure that this solution to water scarcity is both effective and environmentally sustainable.</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

Predicting soil salinity in wastewater land application systems under field conditions with tree-based machine learning approaches

  • 期刊论文

  • 发表日期：

    2025年1月8日

查看全文
  • Runbin Duan,
  • Yao Sun,
  • Jiangqi Gao,
  • Bingzi Zhu

摘要

Wastewater land application is widely recognized as a solution to global water scarcity. However, concerns about its environmental sustainability arise due to potential soil salinization. Three tree-based machine learning models were devised to predict soil salinity using data from previous field studies, evaluated using R2 and RMSE, and interpreted using permutation importance, partial dependence plots, Shapley value plots, and Break Down plots. Data was preprocessed and split into 80% training and 20% test sets prior to being subjected to 10-fold cross-validation and hyperparameter tuning via grid search. Random forest (R2 = 0.920, RMSE = 0.374 dS/m) performed better than decision tree (R2 = 0.832, RMSE = 0.614 dS/m) and gradient boosting decision trees (R2 = 0.918, RMSE = 0.396 dS/m) on test data. The permutation importance order was: initial soil EC > initial soil pH > wastewater pH > total irrigation days > total precipitation > total irrigated wastewater amount > soil depth > wastewater EC. This study provides new insights into how different input features impact soil salinity and has important implications for sustainable management of wastewater land application to ensure that this solution to water scarcity is both effective and environmentally sustainable.