TY - JOUR
T1 - Efficiency, accuracy, and transferability of machine learning potentials
T2 - Application to dislocations and cracks in iron
AU - Zhang, Lei
AU - Csányi, Gábor
AU - van der Giessen, Erik
AU - Maresca, Francesco
N1 - Publisher Copyright:
© 2024
PY - 2024/5/15
Y1 - 2024/5/15
N2 - Machine learning interatomic potentials (ML-IAPs) enable quantum-accurate, classical molecular dynamics simulations of large systems, beyond reach of density functional theory (DFT). Yet, their efficiency and ability to predict systems larger than DFT supercells are not fully explored, posing a question regarding transferability to large-scale simulations with defects (e.g. dislocations, cracks). Here, we apply a three-step validation approach to body-centered-cubic iron. First, accuracy and efficiency are assessed by optimizing ML-IAPs based on four state-of-the-art ML packages. The Pareto front of computational speed versus testing root-mean-square-error (RMSE) is computed. Second, benchmark properties relevant to plasticity and fracture are evaluated. Their relative root-mean-square-error (Q) with respect to DFT is found to correlate with RMSE. Third, transferability of ML-IAPs to dislocations and cracks is investigated by using per-atom model uncertainty quantification. The core structures and Peierls barriers of screw, M111 and three edge dislocations are compared with DFT. Traction–separation curve and critical stress intensity factor (KIc) are also predicted. Cleavage on the pre-existing crack plane is found to be the zero-temperature atomistic fracture mechanism of pure body-centered-cubic iron under mode-I loading, independent of ML package and training database. Quantitative predictions of dislocation glide paths and KIc can be sensitive to database, ML package, cutoff radius, and are limited by DFT accuracy. Our results highlight the importance of validating ML-IAPs by using indicators beyond RMSE. Moreover, significant computational speed-ups can be achieved by using the most efficient ML-IAP package, yet the assessment of the accuracy and transferability should be performed with care.
AB - Machine learning interatomic potentials (ML-IAPs) enable quantum-accurate, classical molecular dynamics simulations of large systems, beyond reach of density functional theory (DFT). Yet, their efficiency and ability to predict systems larger than DFT supercells are not fully explored, posing a question regarding transferability to large-scale simulations with defects (e.g. dislocations, cracks). Here, we apply a three-step validation approach to body-centered-cubic iron. First, accuracy and efficiency are assessed by optimizing ML-IAPs based on four state-of-the-art ML packages. The Pareto front of computational speed versus testing root-mean-square-error (RMSE) is computed. Second, benchmark properties relevant to plasticity and fracture are evaluated. Their relative root-mean-square-error (Q) with respect to DFT is found to correlate with RMSE. Third, transferability of ML-IAPs to dislocations and cracks is investigated by using per-atom model uncertainty quantification. The core structures and Peierls barriers of screw, M111 and three edge dislocations are compared with DFT. Traction–separation curve and critical stress intensity factor (KIc) are also predicted. Cleavage on the pre-existing crack plane is found to be the zero-temperature atomistic fracture mechanism of pure body-centered-cubic iron under mode-I loading, independent of ML package and training database. Quantitative predictions of dislocation glide paths and KIc can be sensitive to database, ML package, cutoff radius, and are limited by DFT accuracy. Our results highlight the importance of validating ML-IAPs by using indicators beyond RMSE. Moreover, significant computational speed-ups can be achieved by using the most efficient ML-IAP package, yet the assessment of the accuracy and transferability should be performed with care.
KW - Dislocation
KW - Fracture
KW - Machine learning potential
KW - Model uncertainty
UR - http://www.scopus.com/inward/record.url?scp=85188787404&partnerID=8YFLogxK
U2 - 10.1016/j.actamat.2024.119788
DO - 10.1016/j.actamat.2024.119788
M3 - Article
AN - SCOPUS:85188787404
SN - 1359-6454
VL - 270
JO - Acta Materialia
JF - Acta Materialia
M1 - 119788
ER -