机器学习模型具有创新的异常检测技术,用于预测土壤中的重金属污染
Ram Proshad1, S M Asharaful Abedin Asha2, Rong Tan3
1State Key Laboratory of Mountain Hazards and Engineering Safety, Institute of Mountain Hazards and Environment, Chinese Academy of Sciences, Chengdu 610041, Sichuan, China; University of Chinese Academy of Sciences, Beijing 100049, China.
Journal of hazardous materials
|November 20, 2024
概括
数据集的异常值显著影响机器学习 (ML) 模型的准确性,用于预测土壤中的重金属 (HM). 将ML与DBSCAN异常值检测相结合,提高了Cr,Ni,Cd和Pb的预测准确度,突出了保护的关键领域.
科学领域:
- 环境科学 环境科学
- 地质化学 地质化学
- 数据科学数据科学数据科学
背景情况:
- 机器学习 (ML) 模型对于预测土壤重金属 (HM) 污染至关重要.
- 数据集的异常值可能会损害机器学习模型的可靠性和准确性.
- 了解异常效应对于强有力的环境监测至关重要.
研究的目的:
- 评估数据异常值对ML模型性能的影响,用于预测土壤HM (Cr,Ni,Cd,Pb).
- 评估将ML与用于异常值检测和HM预测的先进统计方法相结合的有效性.
- 为了确定影响HM度和污染的空间模式的土壤因素.
主要方法:
- 应用了十个ML模型和三种异常检测方法来检测Narayanganj的土壤数据.
- 使用XGBoost与基于密度的应用程序与噪声的空间聚类 (DBSCAN) 来处理异常值.
- 使用的特征重要性,污染因子,LISA和莫兰的I用于空间分析和污染评估.
主要成果:
- 使用DBSCAN的XGBoost显著提高了Cr (11.11%),Ni (6.33%),Cd (14.47%) 和Pb (5.68%) 的R平方值.
- 土壤因素解释了HM度的显著差异:Cr (80%),Ni (72.61%),Cd (53.35%),Pb (63.47%).土壤因素解释了HM度的显著差异:Cr (80%),Ni (72.61%),Cd (53.35%),Pb (63.47%).
- LISA 和 Moran's I 显示了 Cd,Cr 和 Pb 的显著空间自相关性和聚类,污染水平相当高.
结论:
- 数据异常值明显影响了ML模型在土壤HM预测中的准确性.
- 结合ML-DBSCAN方法为环境污染物的评估提供了更高的可靠性.
- 根据空间污染模式确定了需要紧急保护干预的高风险地区.
相关概念视频
Precipitation and Co-precipitation
1.7K
Precipitation and coprecipitation methods can be used to separate a mixture of ions in a solution. In qualitative inorganic analysis, ions that form sparingly soluble precipitates with the same reagent are separated based on the differences in solubility products. For example, consider the separation of Cu(II) and Fe(II) ions by precipitation as insoluble sulfides. First, copper(II) sulfide is precipitated by the addition of acidic H2S, where the dissociation of H2S is suppressed. Adding H2S...
1.7K
Voltammetry: Stripping Methods
180
Anodic Stripping Voltammetry (ASV), Cathodic Stripping Voltammetry (CSV), and Adsorptive Stripping Voltammetry (AdSV) are electrochemical techniques used to determine trace amounts of analytes in solution. These methods involve applying a potential to an electrode and measuring the resulting current.
Anodic Stripping Voltammetry (ASV)
ASV is used to determine metals and metalloids at trace levels. It involves two steps: deposition and stripping. First, a negative potential is applied to the...
Anodic Stripping Voltammetry (ASV)
ASV is used to determine metals and metalloids at trace levels. It involves two steps: deposition and stripping. First, a negative potential is applied to the...
180


