Kim Seongmin, Noh Juhwan, Gu Geun Ho, Chen Shuan, Jung Yousung
Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST) 291, Daehak-ro, Yuseong-gu Daejeon 34141 South Korea.
School of Energy Technology, Korea Institute of Energy Technology 200 Hyuksin-ro Naju 58330 South Korea.
Chem Sci. 2023 Dec 8;15(3):1039-1045. doi: 10.1039/d3sc03538g. eCollection 2024 Jan 17.
While advances in computational techniques have accelerated virtual materials design, the actual synthesis of predicted candidate materials is still an expensive and slow process. While a few initial studies attempted to predict the synthesis routes for inorganic crystals, the existing models do not yield the priority of predictions and could produce thermodynamically unrealistic precursor chemicals. Here, we propose an element-wise graph neural network to predict inorganic synthesis recipes. The trained model outperforms the popularity-based statistical baseline model for the top- exact match accuracy test, showing the validity of our approach for inorganic solid-state synthesis. We further validate our model by the publication-year-split test, where the model trained based on the materials data until the year 2016 is shown to successfully predict synthetic precursors for the materials synthesized after 2016. The high correlation between the probability score and prediction accuracy suggests that the probability score can be interpreted as a measure of confidence levels, which can offer the priority of the predictions.
虽然计算技术的进步加速了虚拟材料设计，但预测的候选材料的实际合成仍然是一个昂贵且缓慢的过程。虽然一些初步研究试图预测无机晶体的合成路线，但现有的模型无法给出预测的优先级，并且可能产生热力学上不现实的前体化学品。在这里，我们提出了一种基于元素的图神经网络来预测无机合成方法。在顶级精确匹配准确性测试中，训练后的模型优于基于流行度的统计基线模型，证明了我们的方法对于无机固态合成的有效性。我们通过按发表年份划分的测试进一步验证了我们的模型，其中基于截至2016年的材料数据训练的模型被证明能够成功预测2016年之后合成的材料的合成前体。概率分数与预测准确性之间的高度相关性表明，概率分数可以被解释为置信水平的一种度量，它可以提供预测的优先级。
