We have developed a machine learned interatomic potential for the prototypical austenitic steel ${\mathrm{Fe}}_7{\mathrm{Cr}}_2\mathrm{Ni}$, using the Gaussian approximation potential (GAP) framework. This GAP can model the alloy's properties with close to density functional theory (DFT) accuracy, while at the same time allowing us to access larger length and time scales than expensive first-principles methods. We also extended the GAP input descriptors to approximate the effects of collinear spins (spin GAP), and demonstrate how this extended model successfully predicts structural distortions due to antiferromagnetic and paramagnetic spin states. We demonstrate the application of the spin GAP model for bulk properties and vacancies and validate against DFT. These results are a step towards modeling the atomistic origins of ageing in austenitic steels with higher accuracy.

中文翻译：

---

共线自旋机学习 Fe7Cr2N 合金的原子间势

我们为原型奥氏体钢开发了一种机器学习的原子间势${铁}_7{铬}_2你$，使用高斯近似势（GAP）框架。该 GAP 可以以接近密度泛函理论 (DFT) 的精度对合金的特性进行建模，同时允许我们获得比昂贵的第一原理方法更大的长度和时间尺度。我们还扩展了 GAP 输入描述符以近似共线自旋（自旋 GAP）的影响，并演示了该扩展模型如何成功预测由于反铁磁和顺磁自旋状态而导致的结构扭曲。我们演示了自旋 GAP 模型在块体属性和空位方面的应用，并针对 DFT 进行了验证。这些结果是朝着以更高的精度模拟奥氏体钢时效原子起源的方向迈出的一步。