| Autor: |
Huynh TM; Graduate Institute of Applied Geology, National Central University, Taoyuan 32001, Taiwan., Ni CF; Graduate Institute of Applied Geology, National Central University, Taoyuan 32001, Taiwan.; Center for Environmental Studies, National Central University, Taoyuan 32001, Taiwan., Su YS; Department of Computer Science and Engineering, National Taiwan Ocean University, Keelung 202301, Taiwan., Nguyen VC; College of Environment and Natural Resources, Can Tho University, Can Tho 94000, Vietnam., Lee IH; Graduate Institute of Applied Geology, National Central University, Taoyuan 32001, Taiwan.; Center for Environmental Studies, National Central University, Taoyuan 32001, Taiwan., Lin CP; Graduate Institute of Applied Geology, National Central University, Taoyuan 32001, Taiwan.; Center for Environmental Studies, National Central University, Taoyuan 32001, Taiwan., Nguyen HH; Graduate Institute of Applied Geology, National Central University, Taoyuan 32001, Taiwan. |
| Abstrakt: |
Monitoring ex-situ water parameters, namely heavy metals, needs time and laboratory work for water sampling and analytical processes, which can retard the response to ongoing pollution events. Previous studies have successfully applied fast modeling techniques such as artificial intelligence algorithms to predict heavy metals. However, neither low-cost feature predictability nor explainability assessments have been considered in the modeling process. This study proposes a reliable and explainable framework to find an effective model and feature set to predict heavy metals in groundwater. The integrated assessment framework has four steps: model selection uncertainty, feature selection uncertainty, predictive uncertainty, and model interpretability. The results show that Random Forest is the most suitable model, and quick-measure parameters can be used as predictors for arsenic (As), iron (Fe), and manganese (Mn). Although the model performance is auspicious, it likely produces significant uncertainties. The findings also demonstrate that arsenic is related to nutrients and spatial distribution, while Fe and Mn are affected by spatial distribution and salinity. Some limitations and suggestions are also discussed to improve the prediction accuracy and interpretability. |
