Interpretable machine learning excavates a low-alloyed magnesium alloy with strength-ductility synergy based on data augmentation and reconstruction

• This work proposed an interpretable ML method based on data augmentation and reconstruction. • The model's prediction accuracy exceeded 95 % (R 2 ) for UTS and EL. • A new as-extruded MZAX2000 alloy with a strength-ductility synergy was developed. • Heterogeneous fibrous structure acted a crucial role in enhancing the strength and ductility of low-alloyed mg alloys. The application of machine learning in alloy design is increasingly widespread, yet traditional models still face challenges when dealing with limited datasets and complex nonlinear relationships. This work proposes an interpretable machine learning method based on data augmentation and reconstruction, excavating high-performance low-alloyed…

• NN
  National Natural Science Foundation of China

  Award: 52204407
• CP
  China Postdoctoral Science Foundation

  Award: 2022M723689
• NS
  Natural Science Foundation of Jiangsu Province

  Award: BK20220595