使用简单的机器学习预测聚合物的玻璃过渡温度
Jaka Fajar Fatriansyah1,2, Baiq Diffa Pakarti Linuwih1, Yossi Andreano1
1Department of Metallurgical and Materials Engineering, Faculty of Engineering, Universitas Indonesia, Kampus UI Depok, Depok 16424, Indonesia.
Polymers
|September 14, 2024
概括
使用简化分子输入线输入系统 (SMILES) 的机器学习模型可以有效地预测聚合物玻璃过渡温度 (Tg). 采用一热编码的XGBoost模型表现出高稳定性和速度,非常适合用于聚合物属性预测.
科学领域:
- 材料科学与工程 材料科学与工程
- 计算化学计算化学
- 聚合物科学 聚合物科学
背景情况:
- 聚合物材料在各种行业中至关重要,其玻璃过渡温度 (Tg) 是操作安全的关键性质.
- 传统的Tg测量方法 (DSC,DMA) 是准确的,但往往耗时,昂贵,容易出现错误.
- 开发高效可靠的聚合物特性预测模型对于材料设计和应用至关重要.
研究的目的:
- 调查简化分子输入线输入系统 (SMILES) 作为分子描述器用于预测聚合物玻璃过渡温度 (Tg) 的有效性.
- 为了比较各种机器学习模型 (KNN,SVR,XGBoost,ANN,RNN) 使用SMILES数据预测Tg的性能.
- 评估SMILES描述符的不同数据转换方法 (一热编码和自然语言处理).
主要方法:
- 使用了五种机器学习模型:k-最近邻居 (KNN),支持向量回归 (SVR),极端梯度增强 (XGBoost),人工神经网络 (ANN) 和循环神经网络 (RNN).
- 使用One Hot Encoding (OHE) 和自然语言处理 (NLP) 技术将SMILES字符串转换为数字数据.
- 分析了SMILES描述符长度对模型性能的影响,确定了最佳输入范围 (200-200个字符).
主要成果:
- 人工神经网络 (ANN) 模型获得了0.79的最高R2,而XGBoost (XGB) 模型则表现出更高的稳定性和更快的训练时间,R2为0.774.
- 与自然语言处理 (NLP) 相比,一个热编码 (OHE) 在大多数模型中显著减少了训练时间.
- XGBoost模型在预测新聚合物数据方面表现出强度,与实际Tg值的平均偏差为9.76.
结论:
- 简化分子输入线输入系统 (SMILES) 与机器学习相结合,为预测聚合物玻璃过渡温度 (Tg) 提供了有效的替代方案.
- 使用One Hot Encoding进行SMILES转换的XGBoost模型是推用于Tg预测的,因为它具有准确性,稳定性和计算效率的平衡.
- 优化SMILES转换策略和模型参数对于提高预测可靠性和推进聚合物材料设计至关重要.
相关概念视频
01:21Polymer Classification: Crystallinity
2.8K
Unlike ionic or small covalent molecules, polymers do not form crystalline solids due to the diffusion limitations of their long-chain structures. However, polymers contain microscopic crystalline domains separated by amorphous domains.
Crystalline domains are the regions where polymer chains are aligned in an orderly manner and held together in proximity by intermolecular forces. For example, chains in the crystalline domains of polyethylene and nylon are bound together by van der Waals...
Crystalline domains are the regions where polymer chains are aligned in an orderly manner and held together in proximity by intermolecular forces. For example, chains in the crystalline domains of polyethylene and nylon are bound together by van der Waals...
2.8K
01:26Polymer Classification: Stereospecificity
2.4K
Polymerization generates chiral centers along the entire backbone of a polymer chain. Accordingly, the stereochemistry of the substituent group has a significant effect on polymer properties. Polymers formed from monosubstituted alkene monomers feature chiral carbons at every alternate position in the polymer backbone. Relative to the predominant orientation of substituents at the adjacent chiral carbons, the polymer can exist in three different configurations: isotactic, syndiotactic, and...
2.4K
01:14Polymer Classification: Architecture
2.7K
Polymers are classified as linear or branched on the basis of their chain architecture. The polymer chains in linear polymers have a long chain-like structure with minimal to no branching at all. Even if a polymer features large substituent groups on the monomer, which appear as branches to the skeleton, it is not considered a branched polymer. A branched polymer contains secondary polymer chains that arise from the main polymer chain. The branching occurs when the polymer growth shifts from...
2.7K
01:08Molecular Weight of Step-Growth Polymers
2.2K
Step growth polymerization involves bi or multifunctional monomers. Bifunctional monomers react to form linear step growth polymers, whereas multifunctional monomers react to form non-linear or branched polymers.
As the step-growth polymerization involves step-wise condensation of monomers, the molecular weight also builds up eventually. Consequently, high molecular weight polymers are obtained at the late stages of the polymerization, where 99% of monomers have been consumed.
The extent of the...
As the step-growth polymerization involves step-wise condensation of monomers, the molecular weight also builds up eventually. Consequently, high molecular weight polymers are obtained at the late stages of the polymerization, where 99% of monomers have been consumed.
The extent of the...
2.2K
01:20Types of Step-Growth Polymers: Polyesters
2.2K
The introduction of polyesters has brought major development to the textile industry. The wrinkle-free behavior of polyester blends has eliminated the need for starching and ironing clothes.
Polyesters are commonly prepared from terephthalic acid and ethylene glycol; the crude product is known as poly(ethylene terephthalate) or PET. However, polyesters are synthesized industrially by transesterification of dimethyl terephthalate with ethylene glycol at 150 °C. The two reactants and the...
Polyesters are commonly prepared from terephthalic acid and ethylene glycol; the crude product is known as poly(ethylene terephthalate) or PET. However, polyesters are synthesized industrially by transesterification of dimethyl terephthalate with ethylene glycol at 150 °C. The two reactants and the...
2.2K
01:10Polymers: Molecular Weight Distribution
3.3K
For any given polymer, the weight average molecular weight (Mw) is higher than, if not equal to, the number average molecular weight (Mn). The only situation in which the weight average molecular weight and the number average molecular weight are equal is when a polymer consists only of chains with equal molecular weight. However, this never happens in a synthetic polymer, since it is difficult to control the polymerization process up to a molecular level with accuracy to a hundred percent.
3.3K