TY - JOUR
T1 - A practical guide to machine learning interatomic potentials – Status and future
AU - Jacobs, Ryan
AU - Morgan, Dane
AU - Attarian, Siamak
AU - Meng, Jun
AU - Shen, Chen
AU - Wu, Zhenghao
AU - Xie, Clare Yijia
AU - Yang, Julia H.
AU - Artrith, Nongnuch
AU - Blaiszik, Ben
AU - Ceder, Gerbrand
AU - Choudhary, Kamal
AU - Csanyi, Gabor
AU - Cubuk, Ekin Dogus
AU - Deng, Bowen
AU - Drautz, Ralf
AU - Fu, Xiang
AU - Godwin, Jonathan
AU - Honavar, Vasant
AU - Isayev, Olexandr
AU - Johansson, Anders
AU - Martiniani, Stefano
AU - Ong, Shyue Ping
AU - Poltavsky, Igor
AU - Schmidt, K. J.
AU - Takamoto, So
AU - Thompson, Aidan P.
AU - Westermayr, Julia
AU - Wood, Brandon M.
AU - Kozinsky, Boris
N1 - Publisher Copyright:
© 2025 Elsevier Ltd
PY - 2025/3
Y1 - 2025/3
N2 - The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spirit of this review is to help such researchers by serving as a practical, accessible guide to the state-of-the-art in MLIPs. This review paper covers a broad range of topics related to MLIPs, including (i) central aspects of how and why MLIPs are enablers of many exciting advancements in molecular modeling, (ii) the main underpinnings of different types of MLIPs, including their basic structure and formalism, (iii) the potentially transformative impact of universal MLIPs for both organic and inorganic systems, including an overview of the most recent advances, capabilities, downsides, and potential applications of this nascent class of MLIPs, (iv) a practical guide for estimating and understanding the execution speed of MLIPs, including guidance for users based on hardware availability, type of MLIP used, and prospective simulation size and time, (v) a manual for what MLIP a user should choose for a given application by considering hardware resources, speed requirements, energy and force accuracy requirements, as well as guidance for choosing pre-trained potentials or fitting a new potential from scratch, (vi) discussion around MLIP infrastructure, including sources of training data, pre-trained potentials, and hardware resources for training, (vii) summary of some key limitations of present MLIPs and current approaches to mitigate such limitations, including methods of including long-range interactions, handling magnetic systems, and treatment of excited states, and finally (viii) we finish with some more speculative thoughts on what the future holds for the development and application of MLIPs over the next 3–10+ years.
AB - The rapid development and large body of literature on machine learning interatomic potentials (MLIPs) can make it difficult to know how to proceed for researchers who are not experts but wish to use these tools. The spirit of this review is to help such researchers by serving as a practical, accessible guide to the state-of-the-art in MLIPs. This review paper covers a broad range of topics related to MLIPs, including (i) central aspects of how and why MLIPs are enablers of many exciting advancements in molecular modeling, (ii) the main underpinnings of different types of MLIPs, including their basic structure and formalism, (iii) the potentially transformative impact of universal MLIPs for both organic and inorganic systems, including an overview of the most recent advances, capabilities, downsides, and potential applications of this nascent class of MLIPs, (iv) a practical guide for estimating and understanding the execution speed of MLIPs, including guidance for users based on hardware availability, type of MLIP used, and prospective simulation size and time, (v) a manual for what MLIP a user should choose for a given application by considering hardware resources, speed requirements, energy and force accuracy requirements, as well as guidance for choosing pre-trained potentials or fitting a new potential from scratch, (vi) discussion around MLIP infrastructure, including sources of training data, pre-trained potentials, and hardware resources for training, (vii) summary of some key limitations of present MLIPs and current approaches to mitigate such limitations, including methods of including long-range interactions, handling magnetic systems, and treatment of excited states, and finally (viii) we finish with some more speculative thoughts on what the future holds for the development and application of MLIPs over the next 3–10+ years.
UR - http://www.scopus.com/inward/record.url?scp=85218629103&partnerID=8YFLogxK
U2 - 10.1016/j.cossms.2025.101214
DO - 10.1016/j.cossms.2025.101214
M3 - Review article
AN - SCOPUS:85218629103
SN - 1359-0286
VL - 35
JO - Current Opinion in Solid State and Materials Science
JF - Current Opinion in Solid State and Materials Science
M1 - 101214
ER -