超声波预测微污染物降解运动常数,使用机器学习
Shiyu Sun1, Yangmin Ren1, Yongyue Zhou1
1School of Civil, Environmental, and Architectural Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.
Chemosphere
|June 26, 2024
概括
一个XGBoost模型准确地预测了微污染物的超声波降解动力常数. 通过SHAP分析进行优化,显示高R2 (0.99) 和低SMAPE (2.06%),其中功率密度和频率是关键因素.
科学领域:
- 环境化学环境化学
- 化学工程是化学工程的重要组成部分.
- 数据科学数据科学数据科学
背景情况:
- 使用超声波降解微污染物对于水净化至关重要.
- 预测运动常数对于优化超声波降解过程至关重要.
- 现有的模型可能在预测这些常数时缺乏准确性或效率.
研究的目的:
- 开发和验证基于XGBoost的超声波降解动力常量预测模型.
- 使用SHAP分析识别影响预测准确性的关键操作参数.
- 评估数据库大小对微量污染物降解模型性能的影响.
主要方法:
- 使用XGBoost回归模型来预测运动常数.
- 沙普利添加式解释 (SHAP) 用于分析参数的重要性.
- 使用R2和SMAPE指标评估模型性能,并优化数据库大小.
主要成果:
- 优化的XGBoost模型实现了高预测准确性 (R2 = 0.99,SMAPE = 2.06%).
- 电源密度和频率被确定为影响预测的最重要的参数.
- 一个缩小的数据库 (60个数据点) 为大多数测试的污染物提供了准确的预测,证明了效率.
结论:
- XGBoost 模型提供了一种强大而准确的方法来预测超声波降解动力学.
- 参数优化和数据库大小缩小可提高模型效率,而不会损害准确度.
- 这种方法有助于更好地设计和控制超声波处理系统,以消除微污染物.
更多相关视频
05:46Identification of Pharmaceuticals in The Aquatic Environment Using HPLC-ESI-Q-TOF-MS and Elimination of Erythromycin Through Photo-Induced Degradation
Published on: August 1, 2018
13.1K
06:51Microparticle Manipulation by Standing Surface Acoustic Waves with Dual-frequency Excitations
Published on: August 21, 2018
7.0K
相关概念视频
Mechanistic Models: Compartment Models in Individual and Population Analysis
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least squares (OLS)...
Microbial Bioremediation of Pesticides
Pesticides often feature structurally complex chemical architectures, incorporating halogen groups and multiple aromatic rings. These characteristics confer high chemical stability, rendering many pesticides resistant to natural degradation processes. This resistance poses significant environmental concerns, as persistent pesticide residues can accumulate in ecosystems and affect non-target organisms.Despite the inherent stability of many pesticides, certain microorganisms possess the metabolic...
Microbial Corrosion
Microbiologically Influenced Corrosion (MIC) is a significant form of material degradation caused by the metabolic activities of microorganisms. This phenomenon poses substantial challenges across various industries, including oil and gas, maritime, and water treatment sectors.MIC occurs when microorganisms, such as bacteria, archaea, and fungi, colonize metal surfaces, forming biofilms that alter the local electrochemical environment. These biofilms can lead to the production of corrosive...
