Diese Präsentation wurde erfolgreich gemeldet.
Wir verwenden Ihre LinkedIn Profilangaben und Informationen zu Ihren Aktivitäten, um Anzeigen zu personalisieren und Ihnen relevantere Inhalte anzuzeigen. Sie können Ihre Anzeigeneinstellungen jederzeit ändern.
Machine learning for materials design:
opportunities, challenges, and methods
Anubhav Jain
Energy Technologies Area
Lawren...
• Batteries
– stable and high-energy electrodes, solid state
electrolytes
• Thermal energy storage & conversion
– High zT ...
• Often, materials are
known for several decades
before their functional
applications are known
– MgB2 sitting on lab shel...
4
Some opportunities for accelerating materials design using
machine learning techniques
Accelerated
materials
design
ML
s...
• Experiments are generally time-consuming and
labor-intensive
– Days to months to get measurements with large
investment ...
• Computations can be faster and require less
researcher time
– Today, some materials design problems can be
modeled in th...
• Machine learning can be the fastest of all and
could play a major role in supporting experiments
and computation, e.g. t...
8
Example application: machine learning as a surrogate for
DFT computations
1. S. Smith, J., Isayev, O. & E. Roitberg, A. ...
9
Example from our group: developing and testing surrogate
models over diverse materials data problems
(paper in preparati...
10
Some opportunities for accelerating materials design using
machine learning techniques
Accelerated
materials
design
ML
...
• Typically, the choice of what materials to
perform experiments on (or to compute) is
chosen by the researcher
• Advantag...
• In a “self-driving” laboratory,
an algorithm chooses the
next
experiment/computation
and performs it
automatically
• “Ac...
13
Example application: shape-memory allows with low
transition temperature and hysteresis
Gubernatis, J. E. & Lookman, T....
14
Example from our group: Rocketsled for automated
computational searches
Rocketsled can help find optimal solutions usin...
15
Some opportunities for accelerating materials design using
machine learning techniques
Accelerated
materials
design
ML
...
• Most materials science data and knowledge only
exists in unstructured format (e.g., as text in
journal publications)
• C...
17
Example: synthesis planning based on text mining
1.
1. Kim, E. et al. Data Descriptor : Machine-learned and codified sy...
18
Example from our group: using NN to predict “gaps” in
materials discoveries
Using word2vec on a database of 3 million m...
• Data availability
– Typical materials data sets range from ~dozen
examples to a few thousand; rare to have 100,000
data ...
• Data Heterogeneity
– There is no single data type (e.g., image data, spectral
data, graph data)
– Different materials pr...
• ML model Extrapolation
– Almost all industry ML focuses on interpolation-type
problems (data on almost all representativ...
• Kristin Persson (ESDR) – materials databases, ML
• Shyam Dwaraknath (ESDR) –ML for characterization
• Juli Mueller (CRD)...
Nächste SlideShare
Wird geladen in …5
×

von

Machine learning for materials design: opportunities, challenges, and methods Slide 1 Machine learning for materials design: opportunities, challenges, and methods Slide 2 Machine learning for materials design: opportunities, challenges, and methods Slide 3 Machine learning for materials design: opportunities, challenges, and methods Slide 4 Machine learning for materials design: opportunities, challenges, and methods Slide 5 Machine learning for materials design: opportunities, challenges, and methods Slide 6 Machine learning for materials design: opportunities, challenges, and methods Slide 7 Machine learning for materials design: opportunities, challenges, and methods Slide 8 Machine learning for materials design: opportunities, challenges, and methods Slide 9 Machine learning for materials design: opportunities, challenges, and methods Slide 10 Machine learning for materials design: opportunities, challenges, and methods Slide 11 Machine learning for materials design: opportunities, challenges, and methods Slide 12 Machine learning for materials design: opportunities, challenges, and methods Slide 13 Machine learning for materials design: opportunities, challenges, and methods Slide 14 Machine learning for materials design: opportunities, challenges, and methods Slide 15 Machine learning for materials design: opportunities, challenges, and methods Slide 16 Machine learning for materials design: opportunities, challenges, and methods Slide 17 Machine learning for materials design: opportunities, challenges, and methods Slide 18 Machine learning for materials design: opportunities, challenges, and methods Slide 19 Machine learning for materials design: opportunities, challenges, and methods Slide 20 Machine learning for materials design: opportunities, challenges, and methods Slide 21 Machine learning for materials design: opportunities, challenges, and methods Slide 22
Nächste SlideShare
What to Upload to SlideShare
Weiter
Herunterladen, um offline zu lesen und im Vollbildmodus anzuzeigen.

0 Gefällt mir

Teilen

Herunterladen, um offline zu lesen

Machine learning for materials design: opportunities, challenges, and methods

Herunterladen, um offline zu lesen

Presentation given at ETA-CRD Energy Probe workshop, May 13, 2019, Berkeley, CA

Ähnliche Bücher

Kostenlos mit einer 30-tägigen Testversion von Scribd

Alle anzeigen

Ähnliche Hörbücher

Kostenlos mit einer 30-tägigen Testversion von Scribd

Alle anzeigen
  • Gehören Sie zu den Ersten, denen das gefällt!

Machine learning for materials design: opportunities, challenges, and methods

  1. 1. Machine learning for materials design: opportunities, challenges, and methods Anubhav Jain Energy Technologies Area Lawrence Berkeley National Laboratory Berkeley, CA Energy Probe workshop, May 13, 2019
  2. 2. • Batteries – stable and high-energy electrodes, solid state electrolytes • Thermal energy storage & conversion – High zT thermoelectrics, high heat capacity liquids • Photovoltaics – Improved efficiency of absorber, reduced degradation in coatings, controlling ion migration in front glass, lifetime of organic / hybrid materials 2 Almost every technology could be improved with better materials!
  3. 3. • Often, materials are known for several decades before their functional applications are known – MgB2 sitting on lab shelves for 50 years before its identification as a superconductor in 2001 • Even after discovery, optimization and commercialization still take decades 3 Typically, both new materials discovery and optimization take decades Materials data from: Eagar T., King M. Technology Review 1995
  4. 4. 4 Some opportunities for accelerating materials design using machine learning techniques Accelerated materials design ML surrogates for expt / comp. “Self-driving laboratories” Opportunities in natural language processing
  5. 5. • Experiments are generally time-consuming and labor-intensive – Days to months to get measurements with large investment of researcher time – Not too long ago, one essentially needed to do everything experimentally 5 ML surrogates for experiments and computation: background
  6. 6. • Computations can be faster and require less researcher time – Today, some materials design problems can be modeled in the computer[1] – But, CPU-time is still a major issue 6 ML surrogates for experiments and computation: background [1] Jain, A., Shin, Y. & Persson, K. A. Computational predictions of energy materials using density functional theory. Nature Reviews Materials 1, 15004 (2016).
  7. 7. • Machine learning can be the fastest of all and could play a major role in supporting experiments and computation, e.g. to identify the most promising regions of chemical space prior to even computation / theory 7 ML surrogates for experiments and computation: background
  8. 8. 8 Example application: machine learning as a surrogate for DFT computations 1. S. Smith, J., Isayev, O. & E. Roitberg, A. ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chemical Science 8, 3192–3203 (2017). 2. Aspuru-Guzik, A., & Persson, K. Materials Acceleration Platform—Accelerating Advanced Energy Materials Discovery by Integrating High-Throughput Methods with Artificial Intelligence. The ML model can be 5-6 orders of magnitude faster! Potential to run ~1 million tests for the price of 1
  9. 9. 9 Example from our group: developing and testing surrogate models over diverse materials data problems (paper in preparation)
  10. 10. 10 Some opportunities for accelerating materials design using machine learning techniques Accelerated materials design ML surrogates for expt / comp. “Self-driving laboratories” Opportunities in natural language processing
  11. 11. • Typically, the choice of what materials to perform experiments on (or to compute) is chosen by the researcher • Advantage: takes advantage of domain expertise of researcher (potentially decades of knowledge) • Potential issues: – Bias (exploring near already known systems) – Time (takes time to think of what to study) 11 “Self-driving” laboratories: background
  12. 12. • In a “self-driving” laboratory, an algorithm chooses the next experiment/computation and performs it automatically • “Active learning” ML • At each stage, the algorithm balances exploration and exploitation 12 “Self-driving” laboratories: background Gubernatis, J. E. & Lookman, T. Machine learning in materials design and discovery: Examples from the present and suggestions for the future. Phys. Rev. Materials 2, 120301 (2018).
  13. 13. 13 Example application: shape-memory allows with low transition temperature and hysteresis Gubernatis, J. E. & Lookman, T. Machine learning in materials design and discovery: Examples from the present and suggestions for the future. Phys. Rev. Materials 2, 120301 (2018). Using an adaptive design strategy, one can reduce the number of measurements needed to find all Pareto-optimal shape memory alloys
  14. 14. 14 Example from our group: Rocketsled for automated computational searches Rocketsled can help find optimal solutions using much fewer computations overall (less CPU) and parallelized over supercomputers (less time) Dunn, A., Brenneck, J. & Jain, A. Rocketsled: a software library for optimizing high-throughput computational searches. J. Phys. Mater. 2, 034002 (2019).
  15. 15. 15 Some opportunities for accelerating materials design using machine learning techniques Accelerated materials design ML surrogates for expt / comp. “Self-driving laboratories” Opportunities in natural language processing
  16. 16. • Most materials science data and knowledge only exists in unstructured format (e.g., as text in journal publications) • Can we make use of knowledge in text format? 16 Natural language processing: background
  17. 17. 17 Example: synthesis planning based on text mining 1. 1. Kim, E. et al. Data Descriptor : Machine-learned and codified synthesis parameters of oxide materials. Scientific Data 1–9 (2017). 2. Kim, E. et al. Materials Synthesis Insights from Scientific Literature via Text Extraction and Machine Learning. Chemistry of Materials acs.chemmater.7b03500-acs.chemmater.7b03500 (2017).
  18. 18. 18 Example from our group: using NN to predict “gaps” in materials discoveries Using word2vec on a database of 3 million materials science abstracts, we can predict which words should co-occur with one another. This can be used to predict materials that should be studied for functional applications (“gaps” in the research literature) Tshitoyan V., Dagdelen J., Weston L., Dunn A., Rong Z., Kononova O., Persson K., Ceder G., Jain A. Unsupervised word embeddings capture latent knowledge from materials science literature. Accepted / in press, Nature
  19. 19. • Data availability – Typical materials data sets range from ~dozen examples to a few thousand; rare to have 100,000 data points – No standard data sets to build models on (e.g. ImageNet) 19 Challenges
  20. 20. • Data Heterogeneity – There is no single data type (e.g., image data, spectral data, graph data) – Different materials problems have their own data types and often ones unknown in computer science (e.g., periodic crystal structures) 20 Challenges
  21. 21. • ML model Extrapolation – Almost all industry ML focuses on interpolation-type problems (data on almost all representative examples is in place) – Materials science requires extrapolation of very complex physics – Standard cross-validation likely insufficient (e.g., cluster-based cross-validation better?) – ML interpretability would build confidence in extrapolation 21 Challenges
  22. 22. • Kristin Persson (ESDR) – materials databases, ML • Shyam Dwaraknath (ESDR) –ML for characterization • Juli Mueller (CRD) – active learning • Dani Ushizima (CRD) – classifying materials image data • Tess Smidt (CRD) – crystal structure models for ML • Emory Chan (MSD) – automated experiments • Colin Ophus (MSD) – TEM image labeling • Gerbrand Ceder (MSD) – text mining / NLP of synthesis 22 Some relevant groups at LBNL

Presentation given at ETA-CRD Energy Probe workshop, May 13, 2019, Berkeley, CA

Aufrufe

Aufrufe insgesamt

972

Auf Slideshare

0

Aus Einbettungen

0

Anzahl der Einbettungen

10

Befehle

Downloads

63

Geteilt

0

Kommentare

0

Likes

0

×