Download as PDF, PPTX
More Related Content
The MGI and AI
- 1. The MGI and AI JamesA Warren Director, Materials Genome Program Material Measurement Laboratory National Institute of Standards and Technology Executive Secretary, NSTC Subcommittee on MGI www.mgi.gov
- 3. The Materials Genome Initiative AMulti-Agency Effort
- 4. It’s an Initiative DOE,NSF, NIST, DOD, NASA, FDA, NIH… 2.5 years into a new adminstration
- 5. To decrease time-to-marketby 50% while <$$ Develop a Materials Innovation Infrastructure Achieve National goals in energy, security, and human welfare with advanced materials Equip the next generation materials workforce Materials Genome Initiative for Global Competitiveness
- 6. To decrease time-to-marketby 50% while <$$ Develop a Materials Innovation Infrastructure Achieve National goals in energy, security, and human welfare with advanced materials Equip the next generation materials workforce Materials Genome Initiative for Global Competitiveness
- 7.
- 8. Data Models Simulation Experiment Quantum MacroMicroNano Materialsw/ Targeted Properties The MGI Approach
- 9. Data Models Simulation Experiment Quantum MacroMicroNano Materialsw/ Targeted Properties The MGI Approach Creating and Capturing Knowledge of Materials
- 10. The Decade ofMGI? These ideas are not new
- 11. Milanese Loop Alloy HighStrength 18K Gold Anodizable 7000 Aluminum -Custom Magnetic Stainless Steel -2X harder -60% stronger Al -30% lighter than 316L Apple watch -Announced September 2014 Baseline: 316L Stainless Steel -Cold-forged to 40% harder -Special purity mirror finish
- 12. MGI IN SUM •The MGI Is about improving our ability to design and deploy new materials (faster) • Need better (or just any) data and models • The MGI is essentially a direct consequence of our improvements in computational power and associated models, coupled to the disruptive consequences of the Internet. • There are a limited number of ways to get the “knowledge” that is the fuel for the MGI • High Throughput Computations, w/ published data and software • High Throughput Experiments • Get it from everywhere (Mine the literature, mine published data, if only it were published!)—- Change Publication and feed the models
- 13.
- 14. Data Models Simulation Experiment Quantum MacroMicroNano Materialsw/ Targeted Properties Today’s Approach to Computational Materials Design
- 15. Data Repositories Models Data Models Code ExperimentsSimulations Metadata MGI Simulation Experiment Quantum MacroMicroNano How dowe do it? Materials w/ Targeted Properties
- 16. Data Community-based Curated Repositories Models MGI Ecosystems Materials w/Targeted Properties
- 17. Data Repositories Models Enable & EnhanceExchange (repositories, disciplines, industries; standards) Assess & Improve Quality (Data & Models) New Methods and Metrologies (data driven analysis and models) Materials w/ Targeted Properties
- 18. This talk hasto be constantly revised
- 19. Gordon Research Conferences2019 Coupling Computation, Data Science and Experiments in Physical Metallurgy & ICME World Congress GRC (3 weeks ago) 20 1-hour talks 50% of talks had some AI/ML A number of very very good scientists were a bit bemused, but ultimately convinced (at least that they should pay attention) (Last week) More than 20 abstracts had “learning” in ICME 2019 conference
- 20. Defense Materials Manufacturingand its Infrastructure (DMMI) Workshop on: Data analytics and what it means to the Materials Community National Academy of Sciences building, July 16‐17th 2019, Room NAS120 at 2101 Constitution Avenue, NW. The Academies will convene a workshop to discuss issues in defense materials and manufacturing. The topics to be discussed is Data analytics and what it means to the Materials Community. The following abstract will define the workshop: The 2013 NRC report on "Frontiers in Massive Data Analysis" makes the following statements about big data: "Experiments, observations, and numerical simulations in 2 weeks ago
- 21.
- 22. Some Reflections Importance ofModels in general AI is a method for creating a model (descriptors and predictions) AI might be viewed as a method for “coarse graining” Physics is a model creation machine Correlation versus causation & Notions of induction and ground truth THIS IS WHAT MAKES AI+SCIENCE SPECIAL (versus recommendations for what to buy with your socks) In other words, we can be DATA POOR (and we often are) because we (often) have good models (But we still need data)
- 23. Lass et al(ICME and AI thoughts) Secondary Processing Secondary Processing Secondary Processing
- 24.
- 25. What’s stopping us? Weneed more data and we need interoperation
- 26.
- 27.
- 28. ACADEMIC INCENTIVES THE MOONSOF SATURN Galileo no doubt planned to publish this new discovery in his next book, but in the meantime, how could he preserve his priority and prevent others from claiming the discovery as their own? His solution was to circulate an anagram, s m a i s m r m i l m e p o e t a l e u m i b u n e n u g t t a u i r a s. Others would know that he had discovered something and when he had discovered it, but they would not known what the discovery was. The number of letters in the anagram, 37, was too small to allow him later to fudge and change the solution to describe a discovery made by someone else in the meantime. Before the days of scientific papers (invented in the 1660s) this was an effective (if not always foolproof) method of claiming priority. http://galileo.rice.edu/sci/observations/saturn.html
- 29. ACADEMIC INCENTIVES THE MOONSOF SATURN Galileo no doubt planned to publish this new discovery in his next book, but in the meantime, how could he preserve his priority and prevent others from claiming the discovery as their own? His solution was to circulate an anagram, s m a i s m r m i l m e p o e t a l e u m i b u n e n u g t t a u i r a s. Others would know that he had discovered something and when he had discovered it, but they would not known what the discovery was. The number of letters in the anagram, 37, was too small to allow him later to fudge and change the solution to describe a discovery made by someone else in the meantime. Before the days of scientific papers (invented in the 1660s) this was an effective (if not always foolproof) method of claiming priority. http://galileo.rice.edu/sci/observations/saturn.html We need to both change the rules and give people tools to make that easier
- 30.
- 31. A few ofthe recommendations
- 32. Mixed Bag Recommendation 1:Strengthen the MDI core in repository, registry, and tool development Recommendation 2: Sustain and grow MDI-dedicated funding programs Recommendation 3: Create, execute, and monitor incentive mechanisms Recommendation 4: Develop demonstration projects and cross- disciplinary community efforts that enhance and accelerate adoption of the MDI ….
- 33.
- 34.
- 35. The Way Out TheUltimate Incentive
- 36. The Way Out TheUltimate Incentive Science
- 37. The Way Out TheUltimate Incentive Science AI Is the Spark that will Ignite the Data Infrastructure Revolution
- 38.