机器学习指导使用等离子体技术进行抗生素降解
Li Xue1, Runyu Jing2, Nanya Zhong3
1College of Electronics and Information Engineering, Sichuan University, Chengdu 610064, China; School of Public Health, Southwest Medical University, Luzhou 646000, China.
Journal of hazardous materials
|September 12, 2024
概括
机器学习模型现在可以使用等离子体技术预测废水中的抗生素去除效率. 这种由XGBoost领导的方法减少了对昂贵实验的需求,并有助于设计更好的等离子处理系统.
科学领域:
- 环境科学 环境科学
- 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:
- 水中的抗生素污染对生态构成风险.
- 等离子技术为废水处理提供了一个有前途的解决方案.
- 目前的局限性包括复杂的反应堆和昂贵的效率测试.
研究的目的:
- 开发一种通用机器学习模型,用于预测等离子体废水处理中的抗生素去除效率.
- 克服复杂的实验设置和昂贵的评估的局限性.
- 确定影响血抗生素降解的关键因素.
主要方法:
- 开发和比较八个机器学习算法.
- 使用集成模型 (XGBoost) 进行预测.
- 应用多模型堆叠方法来提高准确性.
- 可解释性分析,以了解影响因素和协同效应.
主要成果:
- XGBoost模型实现了高预测准确度,Pearson相关系数为0.943.
- 多模型堆叠方法进一步提高了预测准确性.
- 影响等离子体效率的关键因素及其相互作用被定量评估.
结论:
- 机器学习为预测血系统的抗生素去除提供了一个有效的工具.
- 开发的模型可以指导设计更有效的等离子废水处理反应堆.
- 这项研究降低了实验成本,并加速了用于抗生素消毒的等离子体技术的实际应用.
更多相关视频
07:47Anti-virulent Disruption of Pathogenic Biofilms using Engineered Quorum-quenching Lactonases
Published on: January 1, 2016
11.5K
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
13.0K
相关概念视频
Antibiotic Selection
52.4K
Overview
52.4K
Bacterial Signaling
31.8K
Bacterial signaling can occur within bacteria (intracellular) or between bacteria (intercellular). At times, a group of bacteria behaves like a community. To achieve this, they engage in quorum sensing, the perception of higher cell density that causes changes in gene expression. Quorum sensing involves both extracellular and intracellular signaling. The signaling cascade starts with a molecule called an autoinducer (AI). Individual bacteria produce AIs that move out of the bacterial cell...
31.8K
Bioremediation
18.2K
Bioremediation is the use of prokaryotes, fungi, or plants to remove pollutants from the environment. This process has been used to remove harmful toxins in groundwater as a byproduct of agricultural run-off and also to clean up oil spills.
18.2K
