溶相NAPL的时空演变被综合的地下水质量和机器学习模型揭示出来
Fei Qiao1, Jinguo Wang1, Jian Song1
1School of Earth Sciences and Engineering, Hohai University, Nanjing 210098 China.
Water research
|March 27, 2025
概括
这项研究引入了一种机器学习框架,用于使用in-situ传感器预测地下水中的溶相污染羽毛. 长短期记忆 (LSTM) 模型准确地预测了分布,有助于快速做出地下水整治决策.
科学领域:
- 环境科学 环境科学
- 水文地质学 水文地质学
- 数据科学数据科学数据科学
背景情况:
- 预测水层中的溶相污染羽流分布对于有效地修复非水相液体 (NAPLs) 至关重要.
- 传统方法面临的挑战是采样成本,不频繁的分析,含水层异质性和复杂的生物地化学反应.
- 现有的数值模型经常在实时预测准确性和适应性方面扎.
研究的目的:
- 开发一种新的机器学习 (ML) 框架,用于预测溶相NAPL羽毛的时空分布.
- 用低成本的现场地下水质量参数 (iWQP) 作为预测指标.
- 加强在受污染地区地下水整治的快速决策.
主要方法:
- 开发了一个机器学习框架,结合了滑窗时间序列预测和一般回归.
- 一个随机森林 (RF) 模型使用历史数据预测了未来的iWQP.
- 四个ML模型 (RF,XGBoost,MLP,LSTM) 使用预测的iWQP和历史羽毛数据预测了NAPL羽毛分布.
主要成果:
- 长短期记忆 (LSTM) 模型在预测NAPL羽毛分布方面表现出卓越的性能 (R2>0.92).
- 在最长的时间内,LSTM模型保持了预测准确性.
- 变特征的重要性确定了pH值为羽毛预测中最关键的iWQP.
结论:
- 开发的ML框架允许使用易于获得的iWQP数据准确预测溶相NAPL羽毛.
- 这些发现支持开发数据驱动模型,用于实时地表水监测和预估.
- 这种方法可以显著帮助快速和知情地做出关于地下水整治的决策.
相关概念视频
01:19Quality of Water
715
In concrete preparation, the quality of water is paramount as it affects the strength and durability of the concrete. Potable water is usually preferred; however, it must not have excessive sodium or potassium to prevent compromising the concrete's integrity. Water quality is typically evaluated based on impurities such as dissolved solids, chlorides, and sulfates, and its pH value is ideally between 6 and 8. Even slightly acidic natural water may be acceptable unless it contains harmful...
715
01:24Freshwater Microbial Ecology
44
Freshwater systems such as streams, rivers, and lakes exhibit distinct physical and biological characteristics that influence their microbial communities. These environments are broadly categorized into lotic systems—those with flowing waters like streams and most rivers—and lentic systems, which include still or slow-moving waters such as lakes, ponds, and marshes.In lentic systems, phytoplankton drive primary production, generating autochthonous organic carbon. In contrast, lotic...
44