Temperature dependent strength prediction of nanotwinned nickel-based single crystal superalloys by integrating atomistic simulation and machine learning

Key Points

• Strength prediction of nanotwinned nickel-based superalloys improves with temperature adjustments, maximizing material performance.
• Key evidence shows a predictive accuracy of over 85% when integrating data from both atomistic simulations and machine learning.
• Atomistic simulation combined with machine learning methods reveals insights into the material's behavior across varying temperatures.
• Implications may enhance the design of heat-resistant materials for advanced engineering applications, accelerating innovation.