NpjComput.Mater.：預測三元碳化物晶體結構：基於資料庫訓練的機器學習原子間勢

海歸學者發起的公益學術平臺

分享資訊，整合資源

交流學術，偶爾風月

三元碳化物材料因其在極端條件下具備優異的機械和熱效能，在航空航天、高溫環境等應用中具有廣泛的潛力。針對三元碳化物的晶體結構預測，傳統的密度泛函理論（DFT）計算在預測其熱力學穩定性方面成本過高，難以在多組分體系中大規模應用。近年來，隨時機器學習的發展，基於機器學習的原子間勢（ML-IAPs）在晶體結構預測領域中變得越來越重要。同時，隨著材料系統中不同元素組合複雜度增加，如三元或四元系統，開發可用於晶體結構預測的原子間勢變得越來越重要。

Fig. 1 | Workflow in the Plan for
Robust and Accurate Potentials (PRAPs) package.

來自美國紐約州立大學水牛城分校化學系的Eva
Zurek教授團隊，開發了穩健和精確原子間勢工具（PRAPs），並透過機器學習生成三元碳化物的原子間勢，從而加速材料的結構預測。PRAPs流程以AFLOW資料庫中的DFT資料為基礎，採用矩張量勢模型來訓練機器學習勢，並透過主動學習進一步最佳化訓練集。穩健勢和精確勢的結合使PRAPs能夠快速篩選和最佳化低能量候選結構，構建材料的凸包圖，以預測其熱力學穩定性。在對CMoW、CHfTa等碳化物體系的應用中，所生成的準確勢成功預測了幾個熱力學上穩定的新結構，其中一些結構在AFLOW資料庫中尚未記錄。

Fig. 5 | A sample of convex hull
diagrams produced by PRAPs for CHfTa.

這一方法為多組分材料的晶體結構預測提供了高效的計算工具，有助於加速材料設計和開發。該文近期發表於npj Computational Materials10: 142 (2024)，英文標題與摘要如下，點選左下角“閱讀原文”可以自由獲取論文PDF。

Machine learned interatomic potentials for ternary carbides trained on the AFLOW database

Josiah Roberts, Biswas Rijal, Simon Divilov, Jon-Paul Maria, William G. Fahrenholtz, Douglas E. Wolfe, Donald W. Brenner, Stefano Curtarolo & Eva Zurek

Large-density functional theory (DFT) databases are a treasure trove of energies, forces, and stresses that can be used to train machine-learned interatomic potentials for atomistic modeling. Herein, we employ structural relaxations from the AFLOW database to train moment tensor potentials (MTPs) for four carbide systems: CHfTa, CHfZr, CMoW, and CTaTi. The resulting MTPs are used to relax ~6300 random symmetric structures, and are subsequently improved via active learning to generate robust potentials (RP) that can relax a wide variety of structures, and accurate potentials (AP) designed for the relaxation of low-energy systems. This protocol is shown to yield convex hulls that are indistinguishable from those predicted by AFLOW for the CHfTa, CHfZr, and CTaTi systems, and in the case of the CMoW system to predict thermodynamically stable structures that are not found within AFLOW, highlighting the potential of the employed protocol within crystal structure prediction. Relaxation of over three hundred (Mo1−xWx)C stoichiometry crystals first with the RP then with the AP yields formation enthalpies that are in excellent agreement with those obtained via DFT.