论文标题
人工智能供电材料搜索引擎
Artificial Intelligence Powered Material Search Engine
论文作者
论文摘要
由于最近在人工智能（AI）方面取得了突破，因此已经成为了材料科学中许多数据驱动的应用程序。随着材料数据的数量，例如X射线衍射，各种光谱和显微镜数据的增长，AI在材料工程中的使用变得越来越可行。在这项工作中，我们报告了一种使用X射线衍射中原子间空间（D值）的物质搜索引擎来提供物质信息。我们已经研究了使用X射线衍射数据预测前瞻性材料的各种技术。我们使用了随机的森林，天真的贝叶斯（高斯）和神经网络算法来实现这一目标。这些算法的平均精度分别为88.50 \％，100.0 \％和88.89 \％。最后，我们将所有这些技术结合在一起，使预测更通用。该合奏方法的精度率为〜100 \％。此外，我们正在设计基于图形神经网络（GNN）的体系结构，以提高解释性和准确性。因此，我们希望解决基于传统词典和基于元数据的材料搜索引擎的计算和时间复杂性，并提供更通用的预测。
Many data-driven applications in material science have been made possible because of recent breakthroughs in artificial intelligence(AI). The use of AI in material engineering is becoming more viable as the number of material data such as X-Ray diffraction, various spectroscopy, and microscope data grows. In this work, we have reported a material search engine that uses the interatomic space (d value) from X-ray diffraction to provide material information. We have investigated various techniques for predicting prospective material using X-ray diffraction data. We used the Random Forest, Naive Bayes (Gaussian), and Neural Network algorithms to achieve this. These algorithms have an average accuracy of 88.50\%, 100.0\%, and 88.89\%, respectively. Finally, we combined all these techniques into an ensemble approach to make the prediction more generic. This ensemble method has a ~100\% accuracy rate. Furthermore, we are designing a graph neural network (GNN)-based architecture to improve interpretability and accuracy. Thus, we want to solve the computational and time complexity of traditional dictionary-based and metadata-based material search engines and to provide a more generic prediction.
