Ultralow compressible materials, which have high bulk modulus (K), are invaluable in extreme conditions due to their ability to undergo significant compression without structural failure. As large number of borides can be found with high K, this study develop a computational framework to scan the vast chemical space to identify the ultralow compressible borides. Transformer-based networks are helpful to generate new chemical compositions due to their self-attention mechanism, scalability, and ability to capture long-range dependencies. First, we developed a transformer-based network to generate new binary and ternary boride compositions based on the known boride compositions. Next, we trained a hybrid model based on AdaBoost and Gradient Boosting algorithms with mean absolute error (MAE) of 14.1 GPa to scan the high K borides. The CALYPSO code was used to find the possible structures for those materials. After predicting K for broad chemical domain, we found that Re-B and W-B systems are promising ultralow compressible materials. We then performed density functional theory (DFT) calculations to investigate the stability of high K materials. Our computations suggest that Re3B2, Re2B3, W5VB4, and Re5CrB4 materials exhibit K > 300 GPa with negative formation energy and energy-above-hull less than 40 meV. Those materials are mechanically and dynamically stable based on the elastic constant calculations and the phonon dispersion.

中文翻译：

---

利用基于 Transformer 的网络和升压算法进行超低可压缩硼化物设计


超低可压缩材料具有高体积模量 （K），由于能够承受显著压缩而不会发生结构故障，因此在极端条件下非常宝贵。由于可以发现大量具有高 K 的硼化物，本研究开发了一个计算框架来扫描广阔的化学空间以识别超低可压缩硼化物。基于 Transformer 的网络有助于生成新的化学成分，因为它们具有自注意力机制、可扩展性和捕获长距离依赖关系的能力。首先，我们开发了一个基于 transformer 的网络，以基于已知的硼化物成分生成新的二元和三元硼化物成分。接下来，我们训练了一个基于 AdaBoost 和 Gradient Boosting 算法的混合模型，平均绝对误差 （MAE） 为 14.1 GPa，以扫描高 K 硼化物。CALYPSO 代码用于查找这些材料的可能结构。在预测了广化学域的 K 之后，我们发现 Re-B 和 W-B 系统是很有前途的超低可压缩材料。然后，我们进行了密度泛函理论 （DFT） 计算，以研究高 K 材料的稳定性。我们的计算表明，Re3B2、Re2B3、W5VB4 和 Re5CrB4 材料表现出 K > 300 GPa，具有负形成能和小于 40 meV 的船体以上能量。这些材料基于弹性常数计算和声子色散在机械和动态上是稳定的。