聚合物玻璃Transition Temperatures的机器学习模型预测的评估和改进
Assessing and Improving Machine Learning Model Predictions of Polymer Glass Transition Temperatures
摘要：
材料基因组计划的成功为材料发现的数据驱动方法带来了机会。聚合物基因组（PG）是一种基于机器学习（ML）的数据驱动信息学平台，用于聚合物性能预测，其最近的发展显着提高了聚合物设计的效率。尽管如此，“训练数据”的不断扩展对于提高ML预测的鲁棒性、通用性和准确性是必要的。为了测试PG中目前可用的预测模型的性能和可移植性（之前在450种聚合物的数据集上进行了训练），我们仔细收集了来自多个数据源的871种聚合物的额外实验玻璃化转变温度（Tg）数据。将新收集的数据集中聚合物的当前PG模型预测的Tg值直接与实验Tg进行比较，以估计当前模型的准确性。使用1321种聚合物的完整数据集，根据过去的工作建立了一个新的Tg ML模型。扩展数据集的预测RMSE与早期数据集相比，从57 K下降到27 K。为了进一步提高Tg预测模型的性能，我们正在继续积累新数据并探索新的ML方法。
英文摘要：
The success of the Materials Genome Initiative has led to opportunities for data-driven approaches for materials discovery. The recent development of Polymer Genome (PG), which is a machine learning (ML) based data-driven informatics platform for polymer property prediction, has significantly increased the efficiency of polymer design. Nevertheless, continuous expansion of the "training data" is necessary to improve the robustness, versatility and accuracy of the ML predictions. In order to test the performance and transferability of the predictive models presently available in PG (which were previously trained on a dataset of 450 polymers), we have carefully collected additional experimental glass transition temperature (Tg) data for 871 polymers from multiple data sources. The Tg values predicted by the present PG models for the polymers in the newly collected dataset were compared directly with the experimental Tg to estimate the accuracy of the present model. Using the full dataset of 1321 polymers, a new ML model for Tg was built following past work. The RMSE of prediction for the extended dataset, when compared to the earlier one, decreased to 27 K from 57 K. To further improve the performance of the Tg prediction model, we are continuing to accumulate new data and exploring new ML approaches.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
