SEHC: A high-throughput materials computing framework with automatic self-evaluation filtering
Source abstract
Abstract
Abstract Efficiency is one of the key problems in the design of high-throughput materials computing. In this paper, we provide a Self-Evaluation High-throughput Computing framework (SEHC). The framework introduces an automatic self-evaluation filtering mechanism, which is based on machine learning, for high-throughput computing architectures to stop unexpected materials calculation tasks in advance during high-throughput calculation. The time-consuming high-throughput computing process is disassembled into several finer-grained high-throughput Stages. Multiple high-throughput Stages with the same standard design specifications can be assembled into a Pipeline model. Combined with the public service like data storage and system monitoring, the SEHC with a “Stage-Pipeline-Framework” three-tier structure is formed. To search for diamond-like structures with higher group velocity in a space of 254 compounds, a SEHC-based prototype was implemented. The experiment result shows that this prototype achieved a significant improvement in efficiency by reducing the amount of invalid computation remarkably.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Machine Learning in Materials Science · Electronic and Structural Properties of Oxides · Ferroelectric and Negative Capacitance Devices
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (59)
Show source-provided references
1. Materials genome enables research and development revolution
2. ABINIT: First-principles approach to materials and nanosystem properties10.1016/j.cpc.2009.07.007 ↗
3. Iterative minimization techniques for ab initio total-energy calculations: molecular dynamics and conjugate gradients10.1103/RevModPhys.64.1045 ↗
4. The Monte Carlo method for the solution of charge transport in semiconductors with applications to covalent materials10.1103/RevModPhys.55.645 ↗
5. A combinatorial approach to materials discovery10.1126/science.268.5218.1738 ↗
6. Identification of cathode materials for lithium batteries guided by first-principles calculations10.1038/33647 ↗
7. Combined electronic structure and evolutionary search approach to materials design10.1103/PhysRevLett.88.255506 ↗
8. Predictions of new crystalline states for assemblies of nanoparticles: perovskite analogues and 3-D arrays of self-assembled nanowires10.1021/nl034230y ↗
9. Predicting crystal structures with data mining of quantum calculations10.1103/PhysRevLett.91.135503 ↗
10. High-throughput and data mining with ab initio methods10.1088/0957-0233/16/1/039 ↗
11. Accuracy of ab initio methods in predicting the crystal structures of metals: a review of 80 binary alloys10.1016/j.calphad.2005.01.002 ↗
12. Predicting crystal structure by merging data mining with quantum mechanics10.1038/nmat1691 ↗
13. Combinatorial solid-state chemistry of inorganic materials10.1038/nmat1157 ↗
14. A fully integrated high-throughput screening methodology for the discovery of new polyolefin catalysts: discovery of a new class of high temperature single-site group (IV) copolymerization catalysts10.1021/ja020868k ↗
15. Toward computational screening in heterogeneous catalysis: Pareto-optimal methanation catalysts10.1016/j.jcat.2006.02.016 ↗
16. AFLOW: an automatic framework for high-throughput materials discovery10.1016/j.commatsci.2012.02.005 ↗
17. A search model for topological insulators with high-throughput robustness descriptors10.1038/nmat3332 ↗
18. New developments in the Inorganic Crystal Structure Database (ICSD): accessibility in support of materials research and design10.1107/S0108768102006948 ↗
19. N. Zacharias, D.G. Monet, S.E. Levine, et al. The Naval Observatory Merged Astrometric Dataset (NOMAD)[C]. Americal Astronomical Society 205th Meeting. 2005.
20. AFLOWLIB. ORG: A distributed materials properties repository from high-throughput ab initio calculations10.1016/j.commatsci.2012.02.002 ↗
21. The Cambridge Structural Database: a quarter of a million crystal structures and rising10.1107/S0108768102003890 ↗
22. Some studies in machine learning using the game of checkers10.1147/rd.441.0206 ↗
23. Automated design of both the topology and sizing of analog electrical circuits using genetic programming
24. A predictive machine learning approach for microstructure optimization and materials design
25. Machine-learning-assisted materials discovery using failed experiments10.1038/nature17439 ↗
26. Accelerated materials property predictions and design using motif-based fingerprints10.1103/PhysRevB.92.014106 ↗
27. Fast and accurate modeling of molecular atomization energies with machine learning10.1103/PhysRevLett.108.058301 ↗
28. Optimizing transition states via kernel-based machine learning10.1063/1.4707167 ↗
29. Atom-centered symmetry functions for constructing high-dimensional neural network potentials10.1063/1.3553717 ↗
30. Adaptive machine learning framework to accelerate ab initio molecular dynamics10.1002/qua.24836 ↗
31. Structure classification and melting temperature prediction in octet AB solids via machine learning10.1103/PhysRevB.91.214302 ↗
32. Classification of octet AB-type binary compounds using dynamical charges: a materials informatics perspective
33. Formability of ABO 3 perovskites10.1016/j.jallcom.2003.10.017 ↗
34. Prediction model of band gap for inorganic compounds by combination of density functional theory calculations and machine learning techniques10.1103/PhysRevB.93.115104 ↗
35. Informatics-aided bandgap engineering for solar materials10.1016/j.commatsci.2013.10.016 ↗
36. Plugge · 2010 · 3
37. A software framework for classification models of geographical data10.1016/j.cageo.2012.02.006 ↗
38. Ab initio molecular dynamics for liquid metals10.1103/PhysRevB.47.558 ↗
39. Scikit-learn: machine learning in python
40. Hastie · 2009 · 9
41. Comparison of values of Pearson's and Spearman's correlation coefficients on the same sets of data10.2478/v10117-011-0021-1 ↗
42. Staelin C. Parameter selection for support vector machines. Hewlett-Packard Company, Tech. Rep. HPL-2002-354R1, 2003.
43. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
44. The learning-curve sampling method applied to model-based clustering
45. Crockford D. The application/json media type for javascript object notation (json)[J]. 2006.10.17487/rfc4627 ↗
46. Hosmer · 2013
47. Scholkopf · 2002
48. Classification and regression by randomForest
49. Ensemble learning
50. Principal component analysis10.1016/0169-7439(87)80084-9 ↗
51. Bader · 1990
52. Moitra A. Introduction to Electronic Structure Calculations using VASP[J].
53. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set10.1103/PhysRevB.54.11169 ↗
54. Projector augmented-wave method10.1103/PhysRevB.50.17953 ↗
55. Strongly constrained and appropriately normed semilocal density functional10.1103/PhysRevLett.115.036402 ↗
56. Special points for Brillouin-zone integrations10.1103/PhysRevB.13.5188 ↗
57. Electrical transport properties of filled CoSb 3 skutterudites: a theoretical study10.1007/s11664-009-0703-9 ↗
58. Transoptic, http://www.mgi.shu.edu.cn/Portals/675/transoptic.zip.
59. Discovery of high-performance thermoelectric chalcogenides through reliable high-throughput material screening10.1021/jacs.8b04704 ↗