Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors
Under thin film deposition, when used in conjunction with the semiconductor atomic layer deposition (ALD) method, the choice of precursor determines the properties and quality of the thin film. Organometallic precursors such as alkaline earth metals (Sr and Ba) and group 4 transition metals (Zr and...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Materials Today Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2590049824000110 |
| _version_ | 1797258666804510720 |
|---|---|
| author | Seungpyo Kang Joonchul Kim Taehyun Park Joonghee Won Chul Baik Jungim Han Kyoungmin Min |
| author_facet | Seungpyo Kang Joonchul Kim Taehyun Park Joonghee Won Chul Baik Jungim Han Kyoungmin Min |
| author_sort | Seungpyo Kang |
| collection | DOAJ |
| description | Under thin film deposition, when used in conjunction with the semiconductor atomic layer deposition (ALD) method, the choice of precursor determines the properties and quality of the thin film. Organometallic precursors such as alkaline earth metals (Sr and Ba) and group 4 transition metals (Zr and Hf) with cyclopentadienyl and tetrakis (ethylmethylamino) ligands have recently gained attention for their stable deposition within high-temperature windows in the ALD. The design of organometallic precursors with an ab initio molecular dynamics (AIMD) simulations-based approach ensures high accuracy but comes with significant computational costs. In this study, we aim to develop a machine-learning interatomic potential (MLIP) through moment tensor potential (MTP) for fast and accurate potential development of Sr, Ba, Zr, and Hf precursors. To establish the reliable training database for MTP construction, we conducted AIMD simulations on each precursor across a range of temperature settings, resulting in a variety of atomic structures. Constructed MTPs enable efficient utilization of molecular dynamics (MD) simulations as well as calculations that achieve an accuracy that approximates density functional theory (DFT). MTP construction coupled with active learning ensures that the MTP for each precursor is reliable and that databases can be expanded. High prediction accuracy is demonstrated by a mean absolute error (MAE) of less than 0.04 eV/atom in all structures. In addition, generalization performance is confirmed for general structures (structures with the same chemical elements but different proportions) and is extended to cluster structures. The constructed MTP exhibits an MAE of less than 0.15 eV/atom, even for untrained cluster structures. These results demonstrate adequate representation and scalability as a basis for the development of MLIPs capable of atomic simulations of organometallic precursors under various thermodynamic conditions. |
| first_indexed | 2024-03-07T18:36:18Z |
| format | Article |
| id | doaj.art-821a4947782242b8b34100e8d4606a9e |
| institution | Directory Open Access Journal |
| issn | 2590-0498 |
| language | English |
| last_indexed | 2024-04-24T22:57:10Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials Today Advances |
| spelling | doaj.art-821a4947782242b8b34100e8d4606a9e2024-03-18T04:34:31ZengElsevierMaterials Today Advances2590-04982024-03-0121100474Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursorsSeungpyo Kang0Joonchul Kim1Taehyun Park2Joonghee Won3Chul Baik4Jungim Han5Kyoungmin Min6School of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-gu, Seoul, 06978, Republic of KoreaSchool of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-gu, Seoul, 06978, Republic of KoreaSchool of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-gu, Seoul, 06978, Republic of KoreaPOC TU, Samsung Advanced Institute of Technology, Suwon, Gyeonggi-do, 16678, Republic of KoreaPOC TU, Samsung Advanced Institute of Technology, Suwon, Gyeonggi-do, 16678, Republic of KoreaPOC TU, Samsung Advanced Institute of Technology, Suwon, Gyeonggi-do, 16678, Republic of Korea; Corresponding author.School of Mechanical Engineering, Soongsil University, 369 Sangdo-ro, Dongjak-gu, Seoul, 06978, Republic of Korea; Corresponding author.Under thin film deposition, when used in conjunction with the semiconductor atomic layer deposition (ALD) method, the choice of precursor determines the properties and quality of the thin film. Organometallic precursors such as alkaline earth metals (Sr and Ba) and group 4 transition metals (Zr and Hf) with cyclopentadienyl and tetrakis (ethylmethylamino) ligands have recently gained attention for their stable deposition within high-temperature windows in the ALD. The design of organometallic precursors with an ab initio molecular dynamics (AIMD) simulations-based approach ensures high accuracy but comes with significant computational costs. In this study, we aim to develop a machine-learning interatomic potential (MLIP) through moment tensor potential (MTP) for fast and accurate potential development of Sr, Ba, Zr, and Hf precursors. To establish the reliable training database for MTP construction, we conducted AIMD simulations on each precursor across a range of temperature settings, resulting in a variety of atomic structures. Constructed MTPs enable efficient utilization of molecular dynamics (MD) simulations as well as calculations that achieve an accuracy that approximates density functional theory (DFT). MTP construction coupled with active learning ensures that the MTP for each precursor is reliable and that databases can be expanded. High prediction accuracy is demonstrated by a mean absolute error (MAE) of less than 0.04 eV/atom in all structures. In addition, generalization performance is confirmed for general structures (structures with the same chemical elements but different proportions) and is extended to cluster structures. The constructed MTP exhibits an MAE of less than 0.15 eV/atom, even for untrained cluster structures. These results demonstrate adequate representation and scalability as a basis for the development of MLIPs capable of atomic simulations of organometallic precursors under various thermodynamic conditions.http://www.sciencedirect.com/science/article/pii/S2590049824000110Organometallic precursorsMachine learning interatomic potentialMoment tensor potentialAb initio molecular dynamics |
| spellingShingle | Seungpyo Kang Joonchul Kim Taehyun Park Joonghee Won Chul Baik Jungim Han Kyoungmin Min Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors Materials Today Advances Organometallic precursors Machine learning interatomic potential Moment tensor potential Ab initio molecular dynamics |
| title | Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| title_full | Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| title_fullStr | Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| title_full_unstemmed | Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| title_short | Toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| title_sort | toward fast and accurate machine learning interatomic potentials for atomic layer deposition precursors |
| topic | Organometallic precursors Machine learning interatomic potential Moment tensor potential Ab initio molecular dynamics |
| url | http://www.sciencedirect.com/science/article/pii/S2590049824000110 |
| work_keys_str_mv | AT seungpyokang towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT joonchulkim towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT taehyunpark towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT joongheewon towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT chulbaik towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT jungimhan towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors AT kyoungminmin towardfastandaccuratemachinelearninginteratomicpotentialsforatomiclayerdepositionprecursors |