从各种精油来源提取超临界CO2的可解释产量预测,使用优化机器学习和PCA-based描述器
Mohamed Kouider Amar1, Mohamed Hentabli1,2,3, Nabil Touzout4
1Laboratory of Biomaterials and Transfer Phenomena, Theoretical and Computational Chemistry in Process Engineering Team, Faculty of Technology, University Yahia Fares of Medea, 26000 Medea, Algeria.
Journal of chemical information and modeling
|December 15, 2025
概括
机器学习模型通过将过程参数与分子数据集成,准确地预测超临界CO2提取中的精油产量. 这种方法提高了跨多种植物物种的预测准确性,并优化了提取效率.
科学领域:
- 化学工程是化学工程的重要组成部分.
- 计算化学的计算化学
- 植物生物化学 植物生物化学
背景情况:
- 在超临界CO2 (SC-CO2) 提取过程中预测精油产量是具有挑战性的,因为植物组成和工艺条件的变化.
- 传统模型通常由于对原料行为均的假设而失败,从而限制了它们在不同植物物种中的使用.
研究的目的:
- 开发先进的机器学习模型,用于预测SC-CO2提取中的精油产量.
- 将提取参数与从主要成分分析 (PCA) 获得的分子描述符集成.
- 为了提高在各种植物物种的产量预测的准确性和通用性.
主要方法:
- 编制了一个数据集,包含了42个植物物种的1313个实验记录.
- 训练有素的光GBM (LGBMR),HistGradientBoosting (HGBR) 和额外树木 (ETR) 算法.
- 使用四个元启发算法优化模型,并使用夏普利添加式扩展 (SHAP) 进行特征重要性分析.
主要成果:
- 所有模型都实现了高预测性能 (R2 > 0.97).
- 通过遗传算法 (ETR-3PCs-GA) 优化的额外树回归器 (ETR) 模型显示了最高的性能 (R2 = 0.9808).
- 在HistGradientBoosting Regressor (HGBR) 模型 (HGBR-2PCs-GA) 中,它在预测动态提取配置文件方面表现出色 (RMSE = 0.408).
- SHAP分析确定压力和PCA坐标是关键特征,表明工艺参数和分子组成的联合影响.
结论:
- 将分子级信息与工艺数据集成,为SC-CO2提取提供了可转移和可解释的模型.
- 整个分子形状,而不仅仅是主要化合物,协同影响精油产量.
- 开发的模型成功地将种类间的产量预测概括起来,并证实已知的过程趋势.
更多相关视频
相关概念视频
Extraction: Advanced Methods
1.0K
Metal ions can be separated from one another by complexation with organic ligands–the chelating agent– to form uncharged chelates. Here, the chelating agent must contain hydrophobic groups and behave as a weak acid, losing a proton to bind with the metal. Since most organic ligands used in this process are insoluble or undergo oxidation in the aqueous phase, the chelating agent is initially added to the organic phase and extracted into the aqueous phase. The metal-ligand complex is...
1.0K
Supercritical Fluid Chromatography
825
Supercritical fluid chromatography (SFC) provides a beneficial substitute for gas chromatography (GC) and liquid chromatography (LC) for certain samples because it merges the top attributes of both techniques. SFC allows the separation and analysis of compounds that GC or LC does not easily manage. These compounds are traditionally nonvolatile or thermally unstable, making GC unsuitable and lacking functional groups required for HPLC analysis.
SFC utilizes a supercritical fluid mobile phase,...
SFC utilizes a supercritical fluid mobile phase,...
825
Predicting Reaction Outcomes
9.9K
Kinetics describes the rate and path by which a reaction occurs. In contrast, thermodynamics deals with state functions and describes the properties, behavior, and components of a system. It is not concerned with the path taken by the process and cannot address the rate at which a reaction occurs. Although it does provide information about what can happen during a reaction process, it does not describe the detailed steps of what appears on an atomic or a molecular level. On the other hand,...
9.9K
Extraction: Partition and Distribution Coefficients
4.5K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
4.5K


