期刊
ENVIRONMENTAL SCIENCE & TECHNOLOGY
卷 54, 期 15, 页码 9454-9463出版社
AMER CHEMICAL SOC
DOI: 10.1021/acs.est.0c03617
关键词
-
资金
- National Natural Science Foundation of China [41831279, 41772265]
- Strategic Priority Research Program of the Chinese Academy of Sciences [XDA20060402]
- Shenzhen Science and Technology Innovation Commission [KQJSCX20170728163124680]
Recent advances in machine learning methods offer the opportunity to improve risk assessment and to decipher factors influencing the spatial variability of groundwater arsenic ([As](gw)). A systematic comparison reveals that boosted regression trees (BRT) and random forest (RF) outperform logistic regression. The probability of [As](gw), exceeding 5 mu g/L (approximate median value of Bangladesh [As](gw)), 10 mu g/L (WHO provisional guideline value), and 50 mu g/L (Bangladesh drinking water standard) is modeled by BRT and RF methods for Bangladesh and its four subregions demarcated by major rivers. Of the 109 geo-environmental and hydrochemical predictor variables, phosphorus and iron emerge as the most important across spatial scales, consistent with known As mobilization mechanisms. Well depth is significant only when hydrochemical parameters are not considered, consistent with prior studies. A peak of probability of [As](gw). exceedance at similar to 30 m depth is evident in the partial dependence plots (PDPs) for spatial-parameter-only models but not in the equivalent all-parameter models, suggesting that sediment depositional history explains interdependent spatial patterns of groundwater As-P-Fe in Holocene aquifers. The South region exhibits a decrease of probability of [As](gw), exceedance below 150 m depth in PDPs for spatial-parameter-only and all-parameter models, supporting that the deeper Pleistocene aquifer is a low-As water resource.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据