abstract = {With the growth of computational resources, the scope of electronic structure simulations has increased greatly. Artificial intelligence and robust data analysis hold the promise to accelerate large-scale simulations and their analysis to hitherto unattainable scales. Machine learning is a rapidly growing field for the processing of such complex data sets. It has recently gained traction in the domain of electronic structure simulations, where density functional theory (DFT) takes the prominent role of the most widely used electronic structure method. Thus, DFT calculations represent one of the largest loads on academic high-performance computing systems across the world. Accelerating these with machine learning can reduce the resources required and enables simulations of larger systems. Hence, the combination of DFT and machine learning has the potential to rapidly advance electronic structure applications such as in silico materials discovery and the search for new chemical reaction pathways. We provide the theoretical background of both DFT and machine learning on a generally accessible level. This serves as the basis of our comprehensive review, including research articles up to December 2020 in chemistry and materials science that employ machine-learning techniques. In our analysis, we categorize the body of research into main threads and extract impactful results. We conclude our review with an outlook on exciting research directions in terms of a citation analysis.},
file = {/Users/wasmer/Nextcloud/Zotero/Fiedler et al_2022_Deep dive into machine learning density functional theory for materials science.pdf;/Users/wasmer/Zotero/storage/62FHUUPB/PhysRevMaterials.6.html}
}
...
...
@@ -6328,7 +6328,7 @@
urldate = {2022-07-10},
abstract = {A long-standing goal of science is to accurately solve the Schr\textbackslash "odinger equation for large molecular systems. The poor scaling of current quantum chemistry algorithms on classical computers imposes an effective limit of about a few dozen atoms for which we can calculate molecular electronic structure. We present a machine learning (ML) method to break through this scaling limit and make quantum chemistry calculations of very large systems possible. We show that Euclidean Neural Networks can be trained to predict the electron density with high fidelity from limited data. Learning the electron density allows us to train a machine learning model on small systems and make accurate predictions on large ones. We show that this ML electron density model can break through the quantum scaling limit and calculate the electron density of systems of thousands of atoms with quantum accuracy.},
keywords = {CCSD(T),charge density,e3nn,ENN,equivariant,GNN,ML,ML-DFT,ML-ESM,molecules,prediction of electrondensity,script,target: density,transfer learning,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Rackers et al_2022_Cracking the Quantum Scaling Limit with Machine Learned Electron Densities2.pdf;/Users/wasmer/Zotero/storage/NL7QJTKF/2201.html}
}
...
...
@@ -6344,7 +6344,7 @@
urldate = {2023-01-20},
abstract = {A long-standing goal of science is to accurately simulate large molecular systems using quantum mechanics. The poor scaling of current quantum chemistry algorithms on classical computers, however, imposes an effective limit of about a few dozen atoms on traditional electronic structure calculations. We present a machine learning (ML) method to break through this scaling limit for electron densities. We show that Euclidean Neural Networks can be trained to predict molecular electron densities from limited data. By learning the electron density, the model can be trained on small systems and make accurate predictions on large ones. In the context of water clusters, we show that an ML model trained on clusters of just 12 molecules contains all the information needed to make accurate electron density predictions on cluster sizes of 50 or more, beyond the scaling limit of current quantum chemistry methods.},
langid = {english},
keywords = {CCSD(T),e3nn,equivariant,GNN,ML-DFT,molecules,prediction of electron density,with-code},
keywords = {CCSD(T),charge density,e3nn,ENN,equivariant,GNN,ML,ML-DFT,ML-ESM,molecules,prediction of electron density,script,target: density,transfer learning,with-code},
file = {/Users/wasmer/Nextcloud/Zotero/Rackers et al_2023_A Recipe for Cracking the Quantum Scaling Limit with Machine Learned Electron.pdf}
file = {/Users/wasmer/Nextcloud/Zotero/Rüßmann_2018_Spin scattering of topologically protected electrons at defects3.pdf;/Users/wasmer/Zotero/storage/T7V45S9S/850306.html}
}
@article{ryczkoDeepLearningDensityfunctional2019,
...
...
@@ -8214,6 +8214,56 @@
file = {/Users/wasmer/Nextcloud/Zotero/Yamada et al_2019_Predicting Materials Properties with Little Data Using Shotgun Transfer Learning.pdf;/Users/wasmer/Zotero/storage/4F8PQPMD/acscentsci.html}
title = {Finite-Temperature Magnetic Properties of \$\{\textbackslash mathrm\{\vphantom{\}\}}{{Sm}}\vphantom\{\}\vphantom\{\}\_\{2\}\{\textbackslash mathrm\{\vphantom{\}\}}{{Fe}}\vphantom\{\}\vphantom\{\}\_\{17\}\{\textbackslash mathrm\{\vphantom{\}\}}{{N}}\vphantom\{\}\vphantom\{\}\_\{x\}\$ Using an \$\textbackslash mathit\{ab\}\$ \$\textbackslash mathit\{initio\}\$ Effective Spin Model},
author = {Yamashita, Shogo and Suzuki, Daiki and Yoshioka, Takuya and Tsuchiura, Hiroki and Novák, Pavel},
abstract = {In this study we investigate the finite-temperature magnetic properties of Sm2Fe17Nx (x=0,3) using an effective spin model constructed based on the information obtained by first-principles calculations. We find that assuming the plausible trivalent Sm3+ configuration results in a model that can satisfactorily describe the magnetization curves of Sm2Fe17N3. By contrast, the model based on the divalent Sm2+ configuration is suitable to reproduce the magnetization curves of Sm2Fe17. These results expand the understanding of how electronic structure affects the magnetic properties of these compounds.},
keywords = {/unread,PGI-1/IAS-1 guests},
file = {/Users/wasmer/Nextcloud/Zotero/Yamashita et al_2020_Finite-temperature magnetic properties of.pdf;/Users/wasmer/Zotero/storage/GHKC49PH/PhysRevB.102.html}
}
@article{yamashitaFirstPrinciplesStudyFinite2022,
title = {First-{{Principles Study}} for {{Finite Temperature Magnetrocrystaline Anisotropy}} of {{L10-Type Ordered Alloys}}},
author = {Yamashita, Shogo and Sakuma, Akimasa},
date = {2022-09-15},
journaltitle = {Journal of the Physical Society of Japan},
abstract = {We conducted the first-principles calculations for the temperature dependence of magnetic anisotropy energy K(T) for L10-type FePt, MnAl, and FeNi by using the coherent potential approximation for spin transverse fluctuation. The temperature dependence of magnetocrystalline anisotropy (MA) for FePt and MnAl almost follows the relation K(T) ∼ M(T)n (2 {$<$} n {$<$} 3) [M(T) is the magnetization], which has been suggested to be reproduced using the XXZ spin model, i.e., the Heisenberg model including the two-site anisotropy term − ∑ ⟨𝑖𝑗⟩ 𝐷 𝑖𝑗 𝑆 𝑧 𝑖 𝑆 𝑧 𝑗 −∑⟨ij⟩DijSizSjz . However, the temperature dependence of MA for FeNi cannot be fitted by the simple relation K(T) ∼ M(T)n. To analyze these results, we examined MA by using the XXZ spin model including the single-site anisotropy term − ∑ 𝑖 𝐷 𝑖 ( 𝑆 𝑧 𝑖 ) 2 −∑iDi(Siz)2 with the mean field approximation. We confirm that the results from first-principles calculations are well explained by this spin model. We believe that the first-principles result for FeNi is the first case that can be reproduced using the spin model with Di {$<$} 0 and Dij {$>$} 0.},
keywords = {/unread,PGI-1/IAS-1 guests},
file = {/Users/wasmer/Nextcloud/Zotero/Yamashita_Sakuma_2022_First-Principles Study for Finite Temperature Magnetrocrystaline Anisotropy of.pdf}
title = {Theoretical Investigation of Electronic Structure and Orbital Moment of the {{Sm}} Ions in {{SmFe12}} Using Generalized Gradient Approximation {{Theoretical Investigation}} of {{Electronic Structure}} and {{Orbital Moment}} of the {{Sm Ions}} in {{SmFe12}} Using {{Generalized Gradient Approximation}} +{{U MethodU}}\$ Method},
author = {Yamashita, Shogo and Yoshioka, Takuya and Tsuchiura, Hiroki and Novák, Pavel},
date = {2022-01},
pages = {1--4},
doi = {10.1109/INTERMAG39746.2022.9827808},
abstract = {In this study, we evaluated the electronic structure and the orbital moments of the Sm ions in \$\textbackslash mathbfSmFe\_12\$ using the GGA \$+U\$ method. This method often leads to metastable states, especially when the atoms with strongly correlated electrons are present. To test the stability of the states we have used three different initial conditions for the \$+U\$ calculations and also studied the dependence of results on \$U\$. The calculated orbital moments are approximately 4.0 \$\textbackslash mu\_\textbackslash mathbfB\$, which is lower than the maximum value of the isolated trivalent state. Then, the quenching of the orbital moment was estimated based on our results.},
file = {/Users/wasmer/Nextcloud/Zotero/Yamashita et al_2022_Theoretical investigation of electronic structure and orbital moment of the Sm.pdf;/Users/wasmer/Zotero/storage/BJS78D9L/authors.html}
