-
Notifications
You must be signed in to change notification settings - Fork 1
/
paper.bib
241 lines (228 loc) · 22.5 KB
/
paper.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
@article{tyvanchuk_crystal_2024,
title = {The crystal and electronic structure of \textit{{RE}}23Co6.7In20.3 (\textit{{RE}} = {Gd}–{Tm}, {Lu}): A new structure type based on intergrowth of {AlB}2- and {CsCl}-type related slabs},
volume = {976},
issn = {0925-8388},
url = {https://www.sciencedirect.com/science/article/pii/S0925838823045449},
doi = {10.1016/j.jallcom.2023.173241},
shorttitle = {The crystal and electronic structure of \textit{{RE}}23Co6.7In20.3 (\textit{{RE}} = {Gd}–{Tm}, {Lu})},
abstract = {New ternary rare-earth indides {RE}23Co6.7In20.3 ({RE} = {Gd}–{Tm}, {Lu}) have been synthesized by arc-melting the elements under argon and subsequent annealing at 870 K for 1200 h. Single-crystal X-ray diffraction revealed Er23Co6.7In20.3 to crystallize in a new structure type in {oP}100, space group Pbam and Wyckoff sequence h11g13da with a = 23.203(5), b = 28.399(5), c = 3.5306(6) Å. The crystal structures of {RE}23Co6.7In20.3 ({RE} = Tb, Ho, Er and Tm) were determined from single crystal and powder X-ray diffraction data and further investigated by {DFT} methods. The compounds belong to a large family of ternary rare-earth indides with intergrowth of the {AlB}2- and {CsCl}-type related slabs. In the Er23Co6.7In20.3 structure, four types of fragments {REIn} and {RET} of {CsCl}-type, as well as {RET}2 and {REIn}2 of {AlB}2-type, are present simultaneously. A simple Python tool was developed to determine the coordination number for each crystallographic site with various methods and tested on the complex structure of {RE}23Co6.7In20.3.},
pages = {173241},
journaltitle = {Journal of Alloys and Compounds},
shortjournal = {Journal of Alloys and Compounds},
author = {Tyvanchuk, Yuriy and Babizhetskyy, Volodymyr and Baran, Stanisław and Szytuła, Andrzej and Smetana, Volodymyr and Lee, Sangjoon and Oliynyk, Anton O. and Mudring, Anja-Verena},
urldate = {2024-08-29},
date = {2024-03-05},
keywords = {Bonding, Electronic structure, Indide, Intermetallics, Rare earth},
file = {ScienceDirect Snapshot:/Users/imac/Zotero/storage/I9T7BI7X/S0925838823045449.html:text/html},
}
@article{lee_machine_2024,
title = {Machine learning descriptors in materials chemistry used in multiple experimentally validated studies: Oliynyk elemental property dataset},
volume = {53},
issn = {2352-3409},
url = {https://www.data-in-brief.com/article/S2352-3409(24)00149-5/fulltext},
doi = {10.1016/j.dib.2024.110178},
shorttitle = {Machine learning descriptors in materials chemistry used in multiple experimentally validated studies},
journaltitle = {Data in Brief},
shortjournal = {Data in Brief},
author = {Lee, Sangjoon and Chen, Clio and Garcia, Griheydi and Oliynyk, Anton},
urldate = {2024-08-29},
date = {2024-04-01},
note = {Publisher: Elsevier},
keywords = {Feature engineering, Machine learning, Materials chemistry, Materials informatics},
file = {Full Text PDF:/Users/imac/Zotero/storage/LT3CRPZS/Lee et al. - 2024 - Machine learning descriptors in materials chemistr.pdf:application/pdf},
}
@article{barua_interpretable_2024,
title = {Interpretable Machine Learning Model on Thermal Conductivity Using Publicly Available Datasets and Our Internal Lab Dataset},
volume = {36},
issn = {0897-4756},
url = {https://doi.org/10.1021/acs.chemmater.4c01696},
doi = {10.1021/acs.chemmater.4c01696},
abstract = {Machine learning ({ML}), a subdiscipline of artificial intelligence studies, has gained importance in predicting or suggesting efficient thermoelectric materials. Previous {ML} studies have used different literature sources or density functional theory calculations as input. In this work, we develop a {ML} pipeline trained with multivariable inputs on a massive public dataset of ∼200,000 data utilizing a high-performance computing cluster to predict the thermal conductivity (κ) using four test sets: three publicly available datasets and a dataset built using previously published data from our own group. By taking advantage of this massive dataset, our model presents an opportunity to further expand the understanding of the selection of features with various thermoelectric materials. Among the several supervised {ML} models implemented, the {eXtreme} Gradient Boosting algorithm ({XGBoost}) turned out to be the best method during the 5-fold cross-validation method, with their averaged evaluation coefficients of R2 = 0.96, root mean squared error ({RMSE}) = 0.38 W m−1K−1, and mean absolute error ({MAE}) = 0.23 W m−1K−1. Additionally, with the aid of feature selection and importance analysis, useful chemical features were chosen that ultimately led to reasonably good accuracy in the series of test sets measured as per the evaluation coefficients of R2, {RMSE}, and {MAE}, with values ranging from 0.72 to 0.89, 0.52 to 1.08, and 0.40 to 0.66 W m−1K−1, respectively. Checking the worst outliers led to the discovery of some errors in the literature. Postmodel prediction, the {SHapley} Additive {exPlanations} ({SHAP}) algorithm was implemented on the {XGBoost} model to analyze the features that were the key drivers for the model’s decisions. Overall, the developed interpretable methodology produces the prediction of κ of a large variety of materials through the influence of chemical and physical property features. The conclusions drawn apply to the research and applications of thermoelectric and heat insulation materials.},
pages = {7089--7100},
number = {14},
journaltitle = {Chemistry of Materials},
shortjournal = {Chem. Mater.},
author = {Barua, Nikhil K. and Hall, Evan and Cheng, Yifei and Oliynyk, Anton O. and Kleinke, Holger},
urldate = {2024-08-29},
date = {2024-07-23},
note = {Publisher: American Chemical Society},
file = {Full Text PDF:/Users/imac/Zotero/storage/UQ6UBCJS/Barua et al. - 2024 - Interpretable Machine Learning Model on Thermal Co.pdf:application/pdf},
}
@article{larsen_atomic_2017,
title = {The atomic simulation environment—a Python library for working with atoms},
volume = {29},
issn = {0953-8984},
url = {https://dx.doi.org/10.1088/1361-648X/aa680e},
doi = {10.1088/1361-648X/aa680e},
abstract = {The atomic simulation environment ({ASE}) is a software package written in the Python programming language with the aim of setting up, steering, and analyzing atomistic simulations. In {ASE}, tasks are fully scripted in Python. The powerful syntax of Python combined with the {NumPy} array library make it possible to perform very complex simulation tasks. For example, a sequence of calculations may be performed with the use of a simple ‘for-loop’ construction. Calculations of energy, forces, stresses and other quantities are performed through interfaces to many external electronic structure codes or force fields using a uniform interface. On top of this calculator interface, {ASE} provides modules for performing many standard simulation tasks such as structure optimization, molecular dynamics, handling of constraints and performing nudged elastic band calculations.},
pages = {273002},
number = {27},
journaltitle = {Journal of Physics: Condensed Matter},
shortjournal = {J. Phys.: Condens. Matter},
author = {Larsen, Ask Hjorth and Mortensen, Jens Jørgen and Blomqvist, Jakob and Castelli, Ivano E. and Christensen, Rune and Dułak, Marcin and Friis, Jesper and Groves, Michael N. and Hammer, Bjørk and Hargus, Cory and Hermes, Eric D. and Jennings, Paul C. and Jensen, Peter Bjerre and Kermode, James and Kitchin, John R. and Kolsbjerg, Esben Leonhard and Kubal, Joseph and Kaasbjerg, Kristen and Lysgaard, Steen and Maronsson, Jón Bergmann and Maxson, Tristan and Olsen, Thomas and Pastewka, Lars and Peterson, Andrew and Rostgaard, Carsten and Schiøtz, Jakob and Schütt, Ole and Strange, Mikkel and Thygesen, Kristian S. and Vegge, Tejs and Vilhelmsen, Lasse and Walter, Michael and Zeng, Zhenhua and Jacobsen, Karsten W.},
urldate = {2024-08-29},
date = {2017-06},
langid = {english},
note = {Publisher: {IOP} Publishing},
file = {IOP Full Text PDF:/Users/imac/Zotero/storage/R2HBZEV6/Larsen et al. - 2017 - The atomic simulation environment—a Python library.pdf:application/pdf},
}
@article{hall_crystallographic_1991,
title = {The crystallographic information file ({CIF}): a new standard archive file for crystallography},
volume = {47},
issn = {1600-5724},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1107/S010876739101067X},
doi = {10.1107/S010876739101067X},
shorttitle = {The crystallographic information file ({CIF})},
pages = {655--685},
number = {6},
journaltitle = {Acta Crystallographica Section A},
author = {Hall, S. R. and Allen, F. H. and Brown, I. D.},
urldate = {2024-08-29},
date = {1991},
langid = {english},
note = {\_eprint: https://onlinelibrary.wiley.com/doi/pdf/10.1107/S010876739101067X},
file = {Full Text PDF:/Users/imac/Zotero/storage/QU4JZMZE/Hall et al. - 1991 - The crystallographic information file (CIF) a new.pdf:application/pdf;Snapshot:/Users/imac/Zotero/storage/Z8KVTFL6/S010876739101067X.html:text/html},
}
@article{ong_python_2013,
title = {Python Materials Genomics (pymatgen): A robust, open-source python library for materials analysis},
volume = {68},
issn = {0927-0256},
url = {https://www.sciencedirect.com/science/article/pii/S0927025612006295},
doi = {10.1016/j.commatsci.2012.10.028},
shorttitle = {Python Materials Genomics (pymatgen)},
abstract = {We present the Python Materials Genomics (pymatgen) library, a robust, open-source Python library for materials analysis. A key enabler in high-throughput computational materials science efforts is a robust set of software tools to perform initial setup for the calculations (e.g., generation of structures and necessary input files) and post-calculation analysis to derive useful material properties from raw calculated data. The pymatgen library aims to meet these needs by (1) defining core Python objects for materials data representation, (2) providing a well-tested set of structure and thermodynamic analyses relevant to many applications, and (3) establishing an open platform for researchers to collaboratively develop sophisticated analyses of materials data obtained both from first principles calculations and experiments. The pymatgen library also provides convenient tools to obtain useful materials data via the Materials Project’s {REpresentational} State Transfer ({REST}) Application Programming Interface ({API}). As an example, using pymatgen’s interface to the Materials Project’s {RESTful} {API} and phasediagram package, we demonstrate how the phase and electrochemical stability of a recently synthesized material, Li4SnS4, can be analyzed using a minimum of computing resources. We find that Li4SnS4 is a stable phase in the Li–Sn–S phase diagram (consistent with the fact that it can be synthesized), but the narrow range of lithium chemical potentials for which it is predicted to be stable would suggest that it is not intrinsically stable against typical electrodes used in lithium-ion batteries.},
pages = {314--319},
journaltitle = {Computational Materials Science},
shortjournal = {Computational Materials Science},
author = {Ong, Shyue Ping and Richards, William Davidson and Jain, Anubhav and Hautier, Geoffroy and Kocher, Michael and Cholia, Shreyas and Gunter, Dan and Chevrier, Vincent L. and Persson, Kristin A. and Ceder, Gerbrand},
urldate = {2024-08-29},
date = {2013-02-01},
keywords = {Design, High-throughput, Materials, Project, Thermodynamics},
file = {Full Text:/Users/imac/Zotero/storage/B8ALJEE7/Ong et al. - 2013 - Python Materials Genomics (pymatgen) A robust, op.pdf:application/pdf;ScienceDirect Snapshot:/Users/imac/Zotero/storage/QMNM7QY4/S0927025612006295.html:text/html},
}
@article{waroquiers_chemenv_2020,
title = {{ChemEnv}: a fast and robust coordination environment identification tool},
volume = {76},
issn = {2052-5206},
url = {https://journals.iucr.org/b/issues/2020/04/00/lo5066/},
doi = {10.1107/S2052520620007994},
shorttitle = {{ChemEnv}},
abstract = {Coordination or local environments have been used to describe, analyze and understand crystal structures for more than a century. Here, a new tool called {ChemEnv}, which can identify coordination environments in a fast and robust manner, is presented. In contrast to previous tools, the assessment of the coordination environments is not biased by small distortions of the crystal structure. Its robust and fast implementation enables the analysis of large databases of structures. The code is available open source within the pymatgen package and the software can also be used through a web app available on http://crystaltoolkit.org through the Materials Project.},
pages = {683--695},
number = {4},
journaltitle = {Acta Crystallographica Section B: Structural Science, Crystal Engineering and Materials},
shortjournal = {Acta Cryst B},
author = {Waroquiers, D. and George, J. and Horton, M. and Schenk, S. and Persson, K. A. and Rignanese, G.-M. and Gonze, X. and Hautier, G.},
urldate = {2024-10-28},
date = {2020-08-01},
langid = {english},
note = {Publisher: International Union of Crystallography},
file = {Full Text PDF:/Users/imac/Zotero/storage/F3I5JFSQ/Waroquiers et al. - 2020 - ChemEnv a fast and robust coordination environmen.pdf:application/pdf},
}
@article{sullivan_pyvista_2019,
title = {{PyVista}: 3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit ({VTK})},
volume = {4},
issn = {2475-9066},
url = {https://joss.theoj.org/papers/10.21105/joss.01450},
doi = {10.21105/joss.01450},
shorttitle = {{PyVista}},
abstract = {Sullivan et al., (2019). {PyVista}: 3D plotting and mesh analysis through a streamlined interface for the Visualization Toolkit ({VTK}). Journal of Open Source Software, 4(37), 1450, https://doi.org/10.21105/joss.01450},
pages = {1450},
number = {37},
journaltitle = {Journal of Open Source Software},
author = {Sullivan, C. Bane and Kaszynski, Alexander A.},
urldate = {2024-10-28},
date = {2019-05-19},
langid = {english},
file = {Full Text PDF:/Users/imac/Zotero/storage/L2H42VVR/Sullivan and Kaszynski - 2019 - PyVista 3D plotting and mesh analysis through a s.pdf:application/pdf},
}
@article{wojdyr_gemmi_2022,
title = {{GEMMI}: A library for structural biology},
volume = {7},
rights = {http://creativecommons.org/licenses/by/4.0/},
issn = {2475-9066},
url = {https://joss.theoj.org/papers/10.21105/joss.04200},
doi = {10.21105/joss.04200},
shorttitle = {{GEMMI}},
abstract = {{GEMMI} is a cross-platform library, accompanied by a set of small programs, developed primarily for use in the field of macromolecular crystallography ({MX}). Parts of this library are useful also in structural bioinformatics and in chemical crystallography.},
pages = {4200},
number = {73},
journaltitle = {Journal of Open Source Software},
shortjournal = {{JOSS}},
author = {Wojdyr, Marcin},
urldate = {2024-10-28},
date = {2022-05-04},
langid = {english},
file = {Wojdyr - 2022 - GEMMI A library for structural biology.pdf:/Users/imac/Zotero/storage/UBQA3VQV/Wojdyr - 2022 - GEMMI A library for structural biology.pdf:application/pdf},
}
@article{harris_array_2020,
title = {Array programming with {NumPy}},
volume = {585},
rights = {2020 The Author(s)},
issn = {1476-4687},
url = {https://www.nature.com/articles/s41586-020-2649-2},
doi = {10.1038/s41586-020-2649-2},
abstract = {Array programming provides a powerful, compact and expressive syntax for accessing, manipulating and operating on data in vectors, matrices and higher-dimensional arrays. {NumPy} is the primary array programming library for the Python language. It has an essential role in research analysis pipelines in fields as diverse as physics, chemistry, astronomy, geoscience, biology, psychology, materials science, engineering, finance and economics. For example, in astronomy, {NumPy} was an important part of the software stack used in the discovery of gravitational waves1 and in the first imaging of a black hole2. Here we review how a few fundamental array concepts lead to a simple and powerful programming paradigm for organizing, exploring and analysing scientific data. {NumPy} is the foundation upon which the scientific Python ecosystem is constructed. It is so pervasive that several projects, targeting audiences with specialized needs, have developed their own {NumPy}-like interfaces and array objects. Owing to its central position in the ecosystem, {NumPy} increasingly acts as an interoperability layer between such array computation libraries and, together with its application programming interface ({API}), provides a flexible framework to support the next decade of scientific and industrial analysis.},
pages = {357--362},
number = {7825},
journaltitle = {Nature},
author = {Harris, Charles R. and Millman, K. Jarrod and van der Walt, Stéfan J. and Gommers, Ralf and Virtanen, Pauli and Cournapeau, David and Wieser, Eric and Taylor, Julian and Berg, Sebastian and Smith, Nathaniel J. and Kern, Robert and Picus, Matti and Hoyer, Stephan and van Kerkwijk, Marten H. and Brett, Matthew and Haldane, Allan and del Río, Jaime Fernández and Wiebe, Mark and Peterson, Pearu and Gérard-Marchant, Pierre and Sheppard, Kevin and Reddy, Tyler and Weckesser, Warren and Abbasi, Hameer and Gohlke, Christoph and Oliphant, Travis E.},
urldate = {2024-10-28},
date = {2020-09},
langid = {english},
note = {Publisher: Nature Publishing Group},
keywords = {Computational neuroscience, Computational science, Computer science, Software, Solar physics},
file = {Full Text PDF:/Users/imac/Zotero/storage/KEQSGBA9/Harris et al. - 2020 - Array programming with NumPy.pdf:application/pdf},
}
@article{virtanen_scipy_2020,
title = {{SciPy} 1.0: fundamental algorithms for scientific computing in Python},
volume = {17},
rights = {2020 The Author(s)},
issn = {1548-7105},
url = {https://www.nature.com/articles/s41592-019-0686-2},
doi = {10.1038/s41592-019-0686-2},
shorttitle = {{SciPy} 1.0},
abstract = {{SciPy} is an open-source scientific computing library for the Python programming language. Since its initial release in 2001, {SciPy} has become a de facto standard for leveraging scientific algorithms in Python, with over 600 unique code contributors, thousands of dependent packages, over 100,000 dependent repositories and millions of downloads per year. In this work, we provide an overview of the capabilities and development practices of {SciPy} 1.0 and highlight some recent technical developments.},
pages = {261--272},
number = {3},
journaltitle = {Nature Methods},
shortjournal = {Nat Methods},
author = {Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E. and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and van der Walt, Stéfan J. and Brett, Matthew and Wilson, Joshua and Millman, K. Jarrod and Mayorov, Nikolay and Nelson, Andrew R. J. and Jones, Eric and Kern, Robert and Larson, Eric and Carey, C. J. and Polat, İlhan and Feng, Yu and Moore, Eric W. and {VanderPlas}, Jake and Laxalde, Denis and Perktold, Josef and Cimrman, Robert and Henriksen, Ian and Quintero, E. A. and Harris, Charles R. and Archibald, Anne M. and Ribeiro, Antônio H. and Pedregosa, Fabian and van Mulbregt, Paul},
urldate = {2024-10-28},
date = {2020-03},
langid = {english},
note = {Publisher: Nature Publishing Group},
keywords = {Biophysical chemistry, Computational biology and bioinformatics, Technology},
file = {Full Text PDF:/Users/imac/Zotero/storage/LQLV3NQJ/Virtanen et al. - 2020 - SciPy 1.0 fundamental algorithms for scientific c.pdf:application/pdf},
}
@article{hunter_matplotlib_2007,
title = {Matplotlib: A 2D Graphics Environment},
volume = {9},
issn = {1558-366X},
url = {https://ieeexplore.ieee.org/document/4160265},
doi = {10.1109/MCSE.2007.55},
shorttitle = {Matplotlib},
abstract = {Matplotlib is a 2D graphics package used for Python for application development, interactive scripting,and publication-quality image generation across user interfaces and operating systems},
pages = {90--95},
number = {3},
journaltitle = {Computing in Science \& Engineering},
author = {Hunter, John D.},
urldate = {2024-10-28},
date = {2007-05},
note = {Conference Name: Computing in Science \& Engineering},
keywords = {application development, Computer languages, Equations, Graphical user interfaces, Graphics, Image generation, Interpolation, Operating systems, Packaging, Programming profession, Python, scientific programming, scripting languages, User interfaces},
file = {IEEE Xplore Abstract Record:/Users/imac/Zotero/storage/HBZMAHB8/4160265.html:text/html},
}
@misc{jaffal_composition_2024,
title = {Composition and structure analyzer/featurizer for explainable machine-learning models to predict solid state structures},
url = {https://chemrxiv.org/engage/chemrxiv/article-details/670aa269cec5d6c142f3b11a},
doi = {10.26434/chemrxiv-2024-rrbhc},
abstract = {Traditional and non-classical machine learning models for solid-state structure prediction have predominantly relied on compositional features (derived from properties of constituent elements) to predict the existence of structure and its properties. However, the lack of structural information can be a source of suboptimal property mapping and increased predictive uncertainty. To address the challenge, we introduce a strategy that generates and combines both compositional and structural features with minimal programming expertise required. Our approach utilizes open-source, interactive Python programs named Composition Analyzer Featurizer ({CAF}) and Structure Analyzer Featurizer ({SAF}). {CAF} generates numerical compositional features from a list of formulas provided in an Excel file, while {SAF} extracts numerical structural features from a .cif file by generating a supercell. 133 features from {CAF} and 94 features from {SAF} were used either individually or in combination to cluster nine structure types in equiatomic {AB} intermetallics. The performance was comparable to those with features state-of-the art featurizers in advanced machine learning models. Our {SAF}+{CAF} features provided a cost-efficient and reliable solution, even with the {PLS}-{DA} method, where a significant fraction of the most contributing features were the same as those identified in the more computationally intensive {XGBoost} models.},
publisher = {{ChemRxiv}},
author = {Jaffal, Emil and Lee, Sangjoon and Shiryaev, Danila and Vtorov, Alex and Barua, Nikhil and Kleinke, Holger and Oliynyk, Anton},
urldate = {2024-10-28},
date = {2024-10-15},
langid = {english},
keywords = {crystal structure, feature engineering, machine learning, materials infomatics, software},
file = {Full Text PDF:/Users/imac/Zotero/storage/XTFPKIMX/Jaffal et al. - 2024 - Composition and structure analyzerfeaturizer for .pdf:application/pdf},
}