Orientation Adaptive Minimal Learning Machine for Directions of Atomic Forces

Pihlajamäki, Antti; Linja, Joakim; Hämäläinen, Joonas; Nieminen, P.; Malola, Sami; Kärkkäinen, Tommi; Häkkinen, Hannu

doi:10.14428/esann/2021.es2021-34

Cited by 3 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, a variation of MLM, which specifically addresses the directions of the atomic forces, was proposed: Orientation Adaptive Minimal Learning Machine (OAMLM) [45].…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…This dot product is the cosine of the angle between two vectors, as we are working with unit vectors, and it is evaluated by OAMLM during the prediction phase [45]. The g…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…However, D out is different. As mentioned in the reference [45], OAMLM has two weight matrices: B c to predict dot products and B g to predict alignment successes. To acquire those D out in equation ( 10) is substituted with D c or D g correspondingly.…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…However, instead of minimizing the distance differences we minimize the difference between the predicted dot products and dot products of the rotated reference unit force vectors R i,j tj and yet unknown vector v. There is no specific method to do this. In the reference [45] the v was found numerically by using Sequential Quadratic Programming (SQP) to optimize cost function…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…We call this a numeric loss function. Here we do not make initial selection of the used reference data as in the original paper [45] but we simply use all references.…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

See 4 more Smart Citations

Orientation Adaptive Minimal Learning Machine: Application to Thiolate-Protected Gold Nanoclusters and Gold-Thiolate Rings

Pihlajamäki¹,

Malola²,

Kärkkäinen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) force fields are one of the most common applications of ML methods in the field of physical and chemical science. In the optimal case, they are able to reach accuracy close to the first principles methods with significantly lowered computational cost. However, often the training of the ML methods rely on full atomic structures alongside their potential energies, and applying the force information is difficult especially in the case of kernel-based methods. Here we apply distance-based ML methods to predict force norms and estimate the directions of the force vectors of the thiolate-protected Au 38 (SCH 3 ) 24 nanocluster. The method relies only on local structural information without energy evaluations. We apply the atomic ML forces on the structure optimization of the gold-thiolate rings and partial optimization of two known structural isomers of the Au 38 (SCH 3 ) 24 nanocluster. The results demonstrate that the method is well-suited for the structural optimizations of the gold-thiolate systems, where the atomic bonding has a covalent nature in the ligand shell and at the metal-ligand interface.

show abstract

“…Recently, a variation of MLM, which specifically addresses the directions of the atomic forces, was proposed: Orientation Adaptive Minimal Learning Machine (OAMLM) [45].…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…This dot product is the cosine of the angle between two vectors, as we are working with unit vectors, and it is evaluated by OAMLM during the prediction phase [45]. The g…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

Section: B Distance-based ML Toolsmentioning

confidence: 99%

Section: B Distance-based ML Toolsmentioning

confidence: 99%

“…We call this a numeric loss function. Here we do not make initial selection of the used reference data as in the original paper [45] but we simply use all references.…”

Section: B Distance-based ML Toolsmentioning

confidence: 99%

See 3 more Smart Citations

Orientation Adaptive Minimal Learning Machine: Application to Thiolate-Protected Gold Nanoclusters and Gold-Thiolate Rings

Pihlajamäki¹,

Malola²,

Kärkkäinen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Gold–Thiolate Nanocluster Dynamics and Intercluster Reactions Enabled by a Machine Learned Interatomic Potential

McCandler,

Pihlajamäki,

Malola

et al. 2024

ACS Nano

View full text Add to dashboard Cite

Monolayer protected metal clusters comprise a rich class of molecular systems and are promising candidate materials for a variety of applications. While a growing number of protected nanoclusters have been synthesized and characterized in crystalline forms, their dynamical behavior in solution, including prenucleation cluster formation, is not well understood due to limitations both in characterization and first-principles modeling techniques. Recent advancements in machine-learned interatomic potentials are rapidly enabling the study of complex interactions such as dynamical behavior and reactivity on the nanoscale. Here, we develop an Au−S−C−H atomic cluster expansion (ACE) interatomic potential for efficient and accurate molecular dynamics simulations of thiolate-protected gold nanoclusters (Au n (SCH 3 ) m ). Trained on more than 30,000 density functional theory calculations of gold nanoclusters, the interatomic potential exhibits ab initio level accuracy in energies and forces and replicates nanocluster dynamics including thermal vibration and chiral inversion. Long dynamics simulations (up to 0.1 μs time scale) reveal a mechanism explaining the thermal instability of neutral Au 25 (SR) 18 clusters. Specifically, we observe multiple stages of isomerization of the Au 25 (SR) 18 cluster, including a chiral isomer. Additionally, we simulate coalescence of two Au 25 (SR) 18 clusters and observe series of clusters where the formation mechanisms are critically mediated by ligand exchange in the form of [Au−S] n rings.

show abstract