bib/bibliography.bib

@@ -3829,7 +3829,7 @@ Subject\_term\_id: computational-methods;electronic-structure;theory-and-computa
   urldate = {2025-01-08},
   abstract = {Deep learning (DL) is one of the fastest-growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual data modalities. DL allows analysis of unstructured data and automated identification of features. The recent development of large materials databases has fueled the application of DL methods in atomistic prediction in particular. In contrast, advances in image and spectral data have largely leveraged synthetic data enabled by high-quality forward models as well as by generative unsupervised DL methods. In this article, we present a high-level overview of deep learning methods followed by a detailed discussion of recent developments of deep learning in atomistic simulation, materials imaging, spectral analysis, and natural language processing. For each modality we discuss applications involving both theoretical and experimental data, typical modeling approaches with their strengths and limitations, and relevant publicly available software and datasets. We conclude the review with a discussion of recent cross-cutting work related to uncertainty quantification in this field and a brief perspective on limitations, challenges, and potential growth areas for DL methods in materials science.},
   langid = {english},
-  keywords = {/unread,AML,CNN,Computational methods,generative models,GNN,list of software,lists,ML,NLP,reinforcement-learning,representation learning,review,review-of-AML,uncertainty quantification},
+  keywords = {AML,CNN,Computational methods,generative models,GNN,list of software,lists,ML,NLP,reinforcement-learning,representation learning,review,review-of-AML,uncertainty quantification},
   file = {/Users/wasmer/Nextcloud/Zotero/Choudhary et al. - 2022 - Recent advances and applications of deep learning methods in materials science.pdf}
 }
@@ -4069,7 +4069,7 @@ Subject\_term\_id: computational-methods;electronic-structure;theory-and-computa
   urldate = {2024-09-30},
   abstract = {The application of machine-learning techniques to atomistic modeling of physics, chemistry and materials science is blooming, and machine learning is becoming a},
   langid = {english},
-  keywords = {/unread,AML,collection,ML,review-of-AML,software,special issue},
+  keywords = {AML,collection,ML,review-of-AML,software,special issue},
   file = {/Users/wasmer/Zotero/storage/V88JWUZY/Software-for-Atomistic-Machine-Learning.html}
 }
@@ -16605,7 +16605,7 @@ Subject\_term\_id: condensed-matter-physics;history;quantum-physics},
   doi = {10.1063/5.0228461},
   url = {https://doi.org/10.1063/5.0228461},
   urldate = {2024-09-30},
-  keywords = {/unread,AML,best-of-list,ML,review-of-AML,software},
+  keywords = {AML,best-of-list,ML,review-of-AML,software},
   file = {/Users/wasmer/Nextcloud/Zotero/Rupp et al. - 2024 - Guest editorial Special Topic on software for atomistic machine learning.pdf;/Users/wasmer/Zotero/storage/WDZTVFQU/Guest-editorial-Special-Topic-on-software-for.html}
 }
@@ -20347,7 +20347,7 @@ Subject\_term\_id: electronic-properties-and-materials;quantum-hall;superconduct
   author = {Wasmer, Johannes and Rüßmann, Philipp and Kovacik, Roman},
   date = {2023-12-25},
   doi = {10.5281/zenodo.10430514},
-  url = {https://zenodo.org/records/10430514},
+  url = {https://github.com/JuDFTteam/aiida-jutools},
   urldate = {2024-10-08},
   abstract = {Tools for simplifying daily work with the AiiDA workflow engine},
   organization = {Zenodo},
@@ -20356,18 +20356,7 @@ Subject\_term\_id: electronic-properties-and-materials;quantum-hall;superconduct
   file = {/Users/wasmer/Zotero/storage/28HAV2UB/10430514.html}
 }
-@online{wasmerBestAtomisticMachine2023,
-  title = {Best of {{Atomistic Machine Learning}}},
-  author = {Wasmer, Johannes and Evans, Matthew and Blaiszik, Ben and Riebesell, Janosh},
-  date = {2023-12-25},
-  doi = {10.5281/zenodo.10934602},
-  url = {https://doi.org/10.5281/zenodo.10934602},
-  urldate = {2024-05-29},
-  abstract = {A ranked list of awesome atomistic machine learning projects.},
-  keywords = {/unread,ai4science,atomistic-machine-learning,awesome-list,best-of-list,chemistry-datasets,community-resource,computational-chemistry,computational-materials-science,density-functional-theory,drug-discovery,electronic-structure,interatomic-potentials,living-document,materials-datasets,materials-discovery,materials-informatics,molecular-dynamics,quantum-chemistry,scientific-machine-learning,surrogate-models}
-}
-
-@report{wasmerBestAtomisticMachine2023a,
+@report{wasmerBestAtomisticMachine2023,
   title = {Best of {{Atomistic Machine Learning}}},
   author = {Wasmer, Johannes and Riebesell, Janosh and Evans, Matthew and Blaiszik, Ben},
   date = {2023},
@@ -20382,6 +20371,17 @@ Subject\_term\_id: electronic-properties-and-materials;quantum-hall;superconduct
   file = {/Users/wasmer/Zotero/storage/7N6RJXIT/1020061.html}
 }
+@online{wasmerBestAtomisticMachine2023a,
+  title = {Best of {{Atomistic Machine Learning}}},
+  author = {Wasmer, Johannes and Evans, Matthew and Blaiszik, Ben and Riebesell, Janosh},
+  date = {2023-12-25},
+  doi = {10.5281/zenodo.10934602},
+  url = {https://github.com/JuDFTteam/best-of-atomistic-machine-learning},
+  urldate = {2024-05-29},
+  abstract = {A ranked list of awesome atomistic machine learning projects.},
+  keywords = {/unread,ai4science,atomistic-machine-learning,awesome-list,best-of-list,chemistry-datasets,community-resource,computational-chemistry,computational-materials-science,density-functional-theory,drug-discovery,electronic-structure,interatomic-potentials,living-document,materials-datasets,materials-discovery,materials-informatics,molecular-dynamics,quantum-chemistry,scientific-machine-learning,surrogate-models}
+}
+
 @unpublished{wasmerComparisonStructuralRepresentations2021,
   type = {Poster},
   title = {Comparison of Structural Representations for Machine Learning-Accelerated Ab Initio Calculations},
@@ -20398,30 +20398,34 @@ Subject\_term\_id: electronic-properties-and-materials;quantum-hall;superconduct
 @thesis{wasmerDevelopmentSurrogateMachine2021,
   type = {mathesis},
-  title = {Development of a Surrogate Machine Learning Model for the Acceleration of Density Functional Calculations with the {{Korringa-Kohn-Rostoker}} Method},
-  author = {Wasmer, Johannes and Rüßmann, Philipp and Blügel, Stefan},
-  date = {2021-10-27},
-  institution = {RWTH Aachen University},
-  url = {https://iffgit.fz-juelich.de/phd-project-wasmer/theses/master-thesis},
-  urldate = {2022-08-08},
-  langid = {english},
-  pagetotal = {99},
-  keywords = {AiiDA,aiida-kkr,AML,Coulomb matrix,descriptor comparison,impurity embedding,juKKR,KKR,master-thesis,ML,PGI-1/IAS-1,SOAP,thesis},
-  file = {/home/johannes/Nextcloud/Zotero/false;/Users/wasmer/Nextcloud/Zotero/Wasmer_2021_Development of a surrogate machine learning model for the acceleration of.pdf;/Users/wasmer/Zotero/storage/AC483X2N/master-thesis.html}
-}
-
-@thesis{wasmerDevelopmentSurrogateMachine2021a,
   title = {Development of a Surrogate Machine Learning Model for the Acceleration of Density Functional Calculations with the {{Korringa-Kohn-Rostoker}} Method},
   author = {Wasmer, Johannes and Berkels, Benjamin and Rüssmann, Philipp and Blügel, Stefan},
   date = {2021},
   number = {FZJ-2023-05854},
   institution = {Masterarbeit, RWTH Aachen University, 2022},
-  url = {https://juser.fz-juelich.de/record/1020053},
-  urldate = {2024-06-05},
+  location = {Aachen},
+  doi = {10.34734/FZJ-2023-05854},
+  url = {https://doi.org/10.34734/FZJ-2023-05854},
+  urldate = {2025-01-26},
   abstract = {Density functional theory (DFT) has become an indispensable tool in materials science. Specialized DFT methods like the Korringa-Kohan Rostoker Green Function (KKR) method are predestined to investigate the technologically relevant effects of crystallographic defects on the electronic and magnetic structure of host materials. This thesis lays the groundwork for answering the question of whether surrogate machine learning (ML) models have the potential to accelerate such DFT calculations since their computational complexity severely limits them to systems sizes of about a thousand atoms in practice. To that end, a versatile suite of software tools that facilitates the generation and analysis of high-throughput computing DFT datasets with the JuKKR DFT codes and the AiiDA workflow engine is presented. We demonstrate its use by generating a database of 8,760 converged KKR DFT calculations of single impurity embeddings into elemental crystals with 60 different chemical elements and varying lattice constants and that preserves the full data provenance of each calculation. Finally, we use the single-impurity database to compare the Coulomb Matrix and the Smooth Overlap of Atomic Positions (SOAP) as structural descriptors of the local atomic environment for materials defects. Their potential use in surrogate ML models is showcased in a simple example of host crystal structure prediction that achieves 93 percent accuracy. Wasmer, Johannes; Blügel, Stefan; Rüssmann, Philipp; Berkels, Benjamin},
   langid = {english},
-  keywords = {/unread},
-  file = {/Users/wasmer/Zotero/storage/NTW3FHQ6/1020053.html}
+  keywords = {AiiDA,aiida-kkr,AML,database generation,dataset,descriptors,FZJ,HTC,impurity embedding,JuDFT,juKKR,KKR,ML,ML-Density,ML-DFT,periodic table,PGI,PGI-1,prediction of electron potential,RWTH,SOAP,thesis,transition metals,workflows},
+  file = {/Users/wasmer/Nextcloud/Zotero/Wasmer et al. - 2021 - Development of a surrogate machine learning model for the acceleration of density functional calcula.pdf;/Users/wasmer/Zotero/storage/NTW3FHQ6/1020053.html}
+}
+
+@online{wasmerPhDProjectWasmer2022,
+  type = {GitLab},
+  title = {{{PhD}} Project {{Wasmer}} Notes},
+  shorttitle = {{{PhD}} Project {{Wasmer}}},
+  author = {Wasmer, Johannes},
+  date = {2022-04-01},
+  url = {https://iffgit.fz-juelich.de/phd-project-wasmer},
+  urldate = {2025-01-27},
+  abstract = {Notes on the PhD project “Development of a surrogate machine learning model for the acceleration of first-principles calculations” at FZJ PGI-1, started April 2022, by Johannes Wasmer.},
+  langid = {english},
+  organization = {iffGit},
+  keywords = {/unread,AML,FZJ,ML,ML-DFT,open science,PGI,PGI-1,research notes,thesis},
+  file = {/Users/wasmer/Zotero/storage/MYZ5H6CE/phd-project-wasmer.html}
 }
 @unpublished{wasmerPhysicsPhysicsAIHybrids2024,
@@ -20458,6 +20462,19 @@ Subject\_term\_id: electronic-properties-and-materials;quantum-hall;superconduct
   keywords = {/unread,conference contribution,FZJ,Jij,ML,PGI,PGI-1/IAS-1}
 }
+@unpublished{wasmerSiScLab20222022,
+  title = {{{SiSc Lab}} 2022, {{Project}} 6. {{A}} Machine Learning Playground in Quantum Mechanical Simulation.},
+  author = {Wasmer, Johannes and Chen, Po-Yen and Burdulea, Ilinca and A, Lixia and Rüßmann, Philipp and Blügel, Stefan and Naumann, Uwe},
+  date = {2022-11-01},
+  doi = {10.5281/zenodo.10440416},
+  url = {https://zenodo.org/records/10440416},
+  urldate = {2025-01-27},
+  abstract = {This is a copy of the practical course SiSc Laboratory (SiScLab; course homepage at the organizing chair) in the master program Simulation Sciences at RWTH Aachen University, in the term WS 2022/23, for project 6,~~~A machine learning playground in quantum mechanical simulation at Forschungszentrum Jülich, Institute of Advanced Simulation, division PGI-1/IAS-1 Quantum Theory of Materials, in the group Materials for quantum information technology. The course repository is here. The organization and meetings page is here. Project description. Density functional theory (DFT) is one of the most widely used simulation techniques. About a third of world supercomputing time is spent each year on such calculations. DFT approximates the solution to the Schrödinger equation, to elucidate the electronic structure of materials and molecules. While it makes quantum many-body problems in a lot of systems of interest tractable, it still is computationally demanding. It typically scales in O(N\textasciicircum 3) with the number of electrons in the system, limiting its application to systems with a few thousand atoms at most. Over the last 15 years, the development of surrogate models based on machine learning (ML) has steadily gained momentum in the field of atomistic simulation. In ab initio molecular dynamics for instance, machine-learned interatomic potentials at a fraction of the cost and comparable accuracy of mechanistic methods have already become mainstream. Now these surrogate models also start to increasingly be developed to predict the underlying electronic structure properties of atomic systems directly. In this project, the students will be given the chance to play around with a wide array of state-of-the-art models in this field, from traditional kernel methods to deep graph convolution networks. They will be provided with a computational infrastructure and training datasets from DFT calculations. The challenges ladder they will climb has the rungs a) understanding the electronic structure data, b) understanding the reasoning behind the various surrogate ML modeling approaches, c) discovering common features of the atomic systems to come up with clever optimizations of the model architectures, and d) achieving reasonable prediction accuracy for the targeted electronic structure properties. The project goals will be adjusted, in a reasonable range given the limited time frame, according to the speed of progress and the particular interests of the students. Expected prerequisites: Applied Quantum Mechanics, basic Python skills. Desired, but optional: Physics track, some hands-on ML experience. Advisors : Johannes Wasmer, Philipp Rüßmann , Stefan Blügel},
+  langid = {english},
+  keywords = {/unread,atomistic machine learning,atomistic modeling,density functional theory,feature engineering,machine learning,machine learning potentials,magnetic interactions,property prediction},
+  file = {/Users/wasmer/Zotero/storage/CIJVT5BS/10440416.html}
+}
+
 @online{weiGraphLearningIts2023,
   title = {Graph {{Learning}} and {{Its Applications}}: {{A Holistic Survey}}},
   shorttitle = {Graph {{Learning}} and {{Its Applications}}},