Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science
Source abstract
Abstract
Our ability to collect “big data” has greatly surpassed our capability to analyze it, underscoring the emergence of the fourth paradigm of science, which is data-driven discovery. The need for data informatics is also emphasized by the Materials Genome Initiative (MGI), further boosting the emerging field of materials informatics. In this article, we look at how data-driven techniques are playing a big role in deciphering processing-structure-property-performance relationships in materials, with illustrative examples of both forward models (property prediction) and inverse models (materials discovery). Such analytics can significantly reduce time-to-insight and accelerate cost-effective materials discovery, which is the goal of MGI.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning in Materials Science · Graph Theory and Algorithms · Computational Drug Discovery Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Northwestern University Department of Electrical Engineering and Computer Science, , Evanston, Illinois 60208, USA
Funding
National Institute of Standards and Technology · Air Force Office of Scientific Research · Defense Advanced Research Projects Agency
References (72)
Show source-provided references
1. 2009
2. Making materials science and engineering data more valuable research products10.1186/s40192-014-0022-8 ↗
3. Big data are shaping the future of materials science10.1557/mrs.2013.187 ↗
4. Materials data science: Current status and future outlook10.1146/annurev-matsci-070214-020844 ↗
5. Materials informatics: The materials ‘gene’ and big data10.1146/annurev-matsci-070214-021132 ↗
6. Computational design of hierarchically structured materials10.1126/science.277.5330.1237 ↗
7. Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters10.1186/2193-9772-3-8 ↗
8. Combinatorial screening for new materials in unconstrained composition space with machine learning10.1103/PhysRevB.89.094104 ↗
9. A predictive machine learning approach for microstructure optimization and materials design10.1038/srep11551 ↗
10. John and Pat Langley. Estimating continuous distributions in Bayesian classifiers
11. Naive Bayes classifiers that perform well with continuous variables
12. 1989
13. Edwards, Allen, L.: An introduction to linear regression and correlation. (A series of books in psychology.) W. H. Freeman and Comp., San Francisco 1976. 213 S., Tafelanh., s 7.0010.1002/bimj.4710190121 ↗
14. Instance-based learning algorithms10.1007/bf00153759 ↗
15. 1995
16. 1994
17. 1995
18. The power of decision tables10.1007/3-540-59286-5_57 ↗
19. 2005
20. 1993
21. The alternating decision tree learning algorithm
22. Logistic model trees10.1007/s10994-005-0466-3 ↗
23. Speeding up logistic model tree induction
24. Induction of model trees for predicting continuous classes
25. 1992 · 343
26. Experiments with a new boosting algorithm
27. Bagging predictors10.1007/bf00058655 ↗
28. The random subspace method for constructing decision forests10.1109/34.709601 ↗
29. Random forests10.1023/A:1010933404324 ↗
30. Rotation forest: A new classifier ensemble method10.1109/TPAMI.2006.211 ↗
31. Predicting crystal structures with data mining of quantum calculations10.1103/PhysRevLett.91.135503 ↗
32. Predicting crystal structure by merging data mining with quantum mechanics10.1038/nmat1691 ↗
33. Finding natures missing ternary oxide compounds using machine learning and density functional theory10.1021/cm100795d ↗
34. Knowledge discovery and data mining in pavement inverse analysis10.3846/16484142.2013.777941 ↗
35. Application of statistical and machine learning techniques for correlating properties to composition and manufacturing processes of steels
36. On-the-fly machine-learning for high-throughput experiments: Search for rare-earth-free permanent magnets10.1038/srep06367 ↗
37. Machine learning approaches for elastic localization linkages in high-contrast composite materials10.1201/b18620-2 ↗
38. Materials prediction via classification learning10.1038/srep13285 ↗
39. Crystal structure representations for machine learning models of formation energies10.1002/qua.24917 ↗
40. Learning deep architectures for ai10.1561/2200000006 ↗
41. Mining big data: Current status, and forecast to the future10.1145/2481244.2481246 ↗
42. Big Data and High Performance Computing
43. Scalable parallel optics data clustering using graph algorithmic techniques10.1145/2503210.2503255 ↗
44. Numarck: Machine learning algorithm for resiliency and checkpointing10.1109/SC.2014.65 ↗
45. Distributed graphlab: A framework for machine learning and data mining in the cloud10.14778/2212351.2212354 ↗
46. Silverback: Scalable association mining for temporal data in columnar probabilistic databases
47. A tale of two data-intensive paradigms: Applications, abstractions, and architectures10.1109/BigData.Congress.2014.137 ↗
48. Reducing infrequent-token perplexity via variational corpora
49. Amazon.com recommendations: Item-to-item collaborative filtering10.1109/MIC.2003.1167344 ↗
50. Large-scale parallel collaborative filtering for the netflix prize
51. Voxsup: A social engagement framework10.1145/2339530.2339779 ↗
52. Data mining applications in healthcare
53. Lung cancer survival prediction using ensemble data mining on seer data10.1155/2012/920245 ↗
54. Development of a 5 year life expectancy index in older adults using predictive mining of electronic health record data10.1136/amiajnl-2012-001360 ↗
55. Real-time disease surveillance using twitter data: Demonstration on flu and cancer10.1145/2487575.2487709 ↗
56. Mining diabetes complication and treatment patterns for clinical decision support
57. Mining social media streams to improve public health allergy surveillance
58. 2015
59. Toward enhanced understanding and projections of climate extremes using physics-guided data mining techniques10.5194/npg-21-777-2014 ↗
60. Running map inference on million node graphical models: A high performance computing perspective
61. 2015
62. Gapped BLAST and PSI-BLAST: A new generation of protein database search programs10.1093/nar/25.17.3389 ↗
63. PSIBLAST_PairwiseStatSig: Reordering PSI-BLAST hits using pairwise statistical significance10.1093/bioinformatics/btp089 ↗
64. Pairwise statistical significance of local sequence alignment using sequence-specific and position-specific substitution matrices10.1109/TCBB.2009.69 ↗
65. Anatomy of a hash-based long read sequence mapping algorithm for next generation DNA sequencing10.1093/bioinformatics/btq648 ↗
66. big data, hadoop and cloud computing in genomics10.1016/j.jbi.2013.07.001 ↗
67. Muses: A multilingual sentiment elicitation system for social media data10.1109/MIS.2013.52 ↗
68. Social role identification via dual uncertainty minimization regularization
69. 2014
70. See http://smds.nims.go.jp/fatigue/index_en.html for National Institute of Materials Science, accessed on Jan 12, 2016.
71. 1986
72. Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization