A DFT-Tuned MACE Potential Reproduces the Oxidation-Dependent Tensile Behavior of Graphene Oxide More Accurately

AI editorPublished 2026.11.02Posted 2026.11.03 06:00 KST

The accepted paper in APS Physical Review Materials systematically calculated the tensile behavior of graphene oxide as a function of oxidation degree and OH/O ratio using a MACE-based machine-learning interatomic potential fine-tuned with DFT data. It reduced the overestimation seen in ReaxFF and reproduced the decreasing trends in Young’s modulus and ultimate tensile strength more accurately, while showing that dehydration is important to fracture behavior under highly oxidized and hydrophilic conditions. [1][2]

1/ AI 활용 방법: A MACE-based machine-learning interatomic potential fine-tuned with DFT data
2/ 적용 과제: Calculating the tensile behavior of graphene oxide according to oxidation degree and OH/O ratio
3/ 보고된 결과: It reduced the overestimation of ReaxFF and more accurately reproduced the decreasing trends in Young’s modulus and ultimate tensile strength
4/ This paper investigated the oxidation-dependent mechanical response of graphene oxide by creating a machine-learning interatomic potential that fine-tuned the MACE foundation model with DFT data.
5/ It calculated tensile behavior while varying oxidation degree from 10–40% and changes in the OH/O ratio, and reported that it reduced the overestimation seen in existing ReaxFF while more accurately reproducing the decreasing trends in Young’s modulus and ultimate tensile strength.
6/ From a materials research perspective, the significance is that it provides an MLIP case that enables rapid atomic-level exploration of how oxidation degree and surface chemistry affect ductility loss and fracture modes.
7/ In particular, it shows that dehydration is important to fracture behavior under highly oxidized and hydrophilic conditions, offering a reference for mechanical reliability assessment and simulation design in oxidized graphene systems.
8/ However, these results apply to a specific DFT-based training set and the investigated graphene oxide composition range, and additional verification is needed for generalization to other oxidation patterns or a broader chemical space.
9/ In addition, the accuracy of an MLIP depends on the scope of the training data and the quality of the reference DFT. [1][2]

How to apply this

Try creating a DFT-tuned MLIP for graphene oxide or similar oxidized carbon systems and calculate the mechanical response to changes in oxidation degree.

1. Prepare graphene oxide structures with various oxidation degrees and OH/O ratios to build a DFT calculation training set.
2. Fine-tune a foundation model such as MACE with reference energies and forces to train the MLIP.
3. Perform tensile simulations at unseen oxidation degrees and compositions to calculate stress-strain curves.
4. Compare the results with DFT or experimental trends in elastic modulus and fracture strength to check whether the model does not overestimate.

Data needed: You need graphene oxide models with different structures, atomic structures with varying oxidation degree and OH/O ratio, and DFT energy and force data for training.
Checking the result: Check the energy and force errors on hold-out structures, and compare whether the Young’s modulus and fracture strength trends under independent oxidation conditions match DFT or experimental trends.
What can go wrong: If the training data cover only a narrow oxidation range, extrapolation errors can grow under different compositions or hydration states, which may distort the mechanical strength and fracture mode.

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

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

A DFT-Tuned MACE Potential Reproduces the Oxidation-Dependent Tensile Behavior of Graphene Oxide More Accurately

How to apply this

Related concepts and practice

Sources