소재 AI 공유함
Menu
← AI in materials

Materials AI · written by AI

Predicting Vacancy Formation Energy in Ni-based Superalloys with Machine Learning

AI editorPublished 2026.09.15

A study published in npj Computational Materials combined density functional theory calculations with machine learning to predict the vacancy formation energy of Ni-based superalloys. It reported that Cr, Nb, Ta, Al, and Ti substitution broadened the energy distribution and increased the standard deviation by up to 0.15 eV. [1]

1/ AI 활용 방법: 머신러닝
2/ 적용 과제: DFT 계산과 결합한 Ni 기반 초내열합금의 vacancy formation energy 예측
3/ 보고된 결과: Cr, Nb, Ta, Al, Ti 치환이 vacancy formation energy 분포를 넓히고 표준편차를 최대 0.15 eV까지 증가시킴
4/ This study used DFT calculations together with machine learning to predict vacancy formation energy in Ni-based superalloys.
5/ The researchers investigated how compositional substitution affects the distribution of vacancy formation energy and reported that Cr, Nb, Ta, Al, and Ti substitution broadens the distribution and increases the standard deviation by up to 0.15 eV.
6/ From a materials research perspective, this result shows how strongly compositional changes can alter the dispersion of defect energies in alloy design.
7/ Such an approach can be a useful reference for rapidly comparing high-temperature stability or diffusion-related behavior.
8/ However, a summary at the article level does not reveal the input features, model form, training data range, or extrapolation capability.
9/ Therefore, it is not possible to expect the same accuracy immediately in other alloy systems. [1]

How to apply this

Use DFT results and compositional descriptors to build a regression model that predicts vacancy formation energy in alloys.

  1. Compute vacancy formation energy by DFT for representative compositions and build a consistent reference dataset.
  2. Organize compositional, elemental statistical, and structural information as input features.
  3. Train a machine learning regression model and check for overfitting with cross-validation.
  4. Test on compositions excluded from training and compare the error and rank agreement with DFT.
Data needed
A dataset is needed that includes the structures of multiple alloy compositions, DFT vacancy formation energy for each composition, and feature quantities such as composition or elemental statistics.
Checking the result
Test the model on compositions not used in training, check MAE or RMSE, and compare whether the predicted values reproduce the DFT trend and defect sensitivity.
What can go wrong
If the training compositions are narrow, the model may extrapolate to new alloy compositions and produce plausible but incorrect values.

이 가이드는 원문의 방법을 바탕으로 AI가 제안한 적용 방향입니다. 원문에 적힌 내용이 아니며 같은 결과가 재현된다는 보장도 아닙니다.

Related concepts and practice

이 이슈를 읽는 데 필요한 개념입니다. 용어마다 Colab에서 바로 돌려볼 수 있는 실습 노트북이 있습니다.

Sources

  1. Prediction of vacancy formation energies in Ni-based superalloys by density functional theory calculations and machine learning | npj Computational Materials

웹 자료를 바탕으로 AI가 자동 요약한 글입니다. 연구의 세부 조건과 결과는 연결된 원문을 확인해주세요.