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
南京大學吳迪、楊玉榮團隊聯合國際學者,提出了一種主動學習驅動的有效哈密頓量引數化方法,實現了從第一性原理資料到超大規模原子模擬的無縫銜接。該方法基於貝葉斯線性迴歸,在分子動力學模擬中即時預測能量、力和應力,並動態觸發第一性原理計算以最佳化引數(圖1)。研究團隊以鈣鈦礦材料(如BaTiO₃、PbTiO₃)為例,展示了該方法的突破性成果:(1) 高效引數化:僅需少量第一性原理計算,即可自動化擬合有效哈密頓量引數;(2) 高效模擬計算:模擬速度比一般機器學習力場快2~3個數量級,可模擬超千萬原子體系;(3) 精準預測相變和複雜體系:對BaTiO₃的順電-鐵電相變溫度預測精度比以往工作顯著提升,並能模擬極性拓撲結構等複雜結構。該方法不僅適用於鈣鈦礦體系,還可以推廣到一般性的材料體系中。

Figure 1 Schematic for the active-learning based effective Hamiltonian parametrization method

Fig. 2 | On-the-fly machine learning of parametrization for BaTiO3.

Fig. 3 | Dipolar mode distribution for a PbTiO3 multidomain with domain walls.
該方法為超大規模原子模擬提供了通用且高效的解決方案,為新型功能材料的研發提供了有力的工具。文章所涉及的程式已作為ALFE-H軟體面向研究人員開放使用。該文近期發表於npj Computational Materials11, 70 (2025),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。
CActive learning of effective Hamiltonian for super-large-scale atomic structures
Xingyue Ma, Hongying Chen, Ri He, Zhanbo Yu, Sergei Prokhorenko, Zheng Wen, Zhicheng Zhong, Jorge Íñiguez-González, L. Bellaiche, Di Wu & Yurong Yang
The first-principles-based effective Hamiltonian scheme provides one of the most accurate modeling techniques for large-scale structures, especially for ferroelectrics. However, the parameterization of the effective Hamiltonian is complicated and can be difficult for some complex systems such as high-entropy perovskites. Here, we propose a general form of effective Hamiltonian and develop an active machine learning approach to parameterize the effective Hamiltonian based on Bayesian linear regression. The parameterization is employed in molecular dynamics simulations with the prediction of energy, forces, stress and their uncertainties at each step, which decides whether first-principles calculations are executed to retrain the parameters. Structures of BaTiO3, PbTiO3, Pb(Zr0.75Ti0.25)O3 and (Pb,Sr)TiO3 system are taken as examples to show the accuracy of this approach, as compared with conventional parametrization method and experiments. This machine learning approach provides a universal and automatic way to compute the effective Hamiltonian parameters for any considered complex systems with super-large-scale (more than 107 atoms) atomic structures.

擴充套件閱讀
媒體轉載聯絡授權請看下方
