Fe-based metallic glasses (MGs) have shown great commercial values due to their excellent soft magnetic properties. Magnetism prediction with consideration of glass forming ability (GFA) is of great significance for developing novel functional Fe-based MGs. However, theories or models established based on condensed matter physics exhibit limited accuracy and some exceptions. In this work, based on 618 Fe-based MGs samples collected from published works, machine learning (ML) models were well trained to predict saturated magnetization (B_s) of Fe-based MGs. GFA was treated as a feature using the experimental data of the supercooled liquid region (ΔT_x). Three ML algorithms, namely eXtreme gradient boosting (XGBoost), artificial neural networks (ANN) and random forest (RF), were studied. Through feature selection and hyperparameter tuning, XGBoost showed the best predictive performance on the randomly split test dataset with determination coefficient (R²) of 0.942, mean absolute percent error (MAPE) of 5.563%, and root mean squared error (RMSE) of 0.078 T. A variety of feature importance rankings derived by XGBoost models showed that ΔT_x played an important role in the predictive performance of the models. This work showed the proposed ML method can simultaneously aggregate GFA and other features in thermodynamics, kinetics and structures to predict the magnetic properties of Fe-based MGs with excellent accuracy.

铁基金属玻璃（MG）由于其优异的软磁性能而显示出巨大的商业价值。考虑玻璃形成能力（GFA）的磁性预测对于开发新型功能性铁基镁具有重要意义。然而，基于凝聚态物理建立的理论或模型表现出有限的准确性和一些例外。在这项工作的基础上，从618发表的作品收集铁基的MG样，机器学习（ML）模型，训练有素的预测饱和磁化强度（乙_小号）铁基的MG的。使用过冷液体区域的实验数据 (Δ T _x）。研究了三种 ML 算法，即极限梯度提升 (XGBoost)、人工神经网络 (ANN) 和随机森林 (RF)。通过特征选择和超参数调整，XGBoost 在随机拆分的测试数据集上表现出最佳预测性能，决定系数 (R ² ) 为 0.942，平均绝对百分比误差 (MAPE) 为 5.563%，均方根误差 (RMSE) 为 0.078 T. XGBoost 模型得出的各种特征重要性排名表明，Δ T _x在模型的预测性能中发挥了重要作用。这项工作表明，所提出的 ML 方法可以同时聚合 GFA 和热力学、动力学和结构方面的其他特征，从而以优异的精度预测 Fe 基 MG 的磁性能。