This talk describes opportunities for students, companies and academics to work in a Materials Informatics Skunkworks, presently located at the University of Wisconsin - Madison. For more information please contact Dane Morgan at ddmorgan@wisc.edu.

1. Opportunities with the UW
Materials Informatics Skunkworks
Information about who we are, what we do, how to work
with us, how to join us
Dane Morgan
University of Wisconsin, Madison
Department of Materials Science and Engineering
ddmorgan@wisc.edu
W: 608-265-5879
C: 608-234-2906
November 18, 2015 1

2. What is Materials Informatics?
Materials informatics is a field of study that
applies the tools and principles of information
extraction from data (informatics) to materials
science and engineering to better understand
the use, selection, development, and discovery
of materials.
– Mining for materials information in large data sets
– Applying new information technologies to enable
new materials science
2

3. Materials Informatics is Not New!
Mendeleev 1871
Ashby map 3

4. Turning Point for Materials Informatics
Data availabilityData Production Informatics Tools
-6
-5.5
-5
-4.5
-4
-3.5
-3
0 10 20 30 40
PredictedLogk*(cm/s)
E above hull (meV/atom)
LaBO3
YBO3
PrBO3
(Sr,Ba)BO3
4

5. The Undergraduate “Materials
Informatics Skunkworks”
We are establishing ~10-20 undergraduates working together
to provide materials informatics research for companies
• Help researchers in academia and industry develop and
utilize this new field
• Provide training in rapidly growing field of informatics to
undergraduates to enhance employment opportunities and
key workforce development
• Be supported financially/academically through credits,
internships, senior design/capstone projects, funded
projects from industry
• Be supported intellectually through group culture of
teamwork and knowledge continuity (more senior train
more junior members) with limited faculty involvement for
advanced issues
5

6. Focus Area: Machine Learning for
Knowledge Discovery in Large Data Sets
Use machine learning techniques to
• Organize your data by putting all relevant,
cleaned input and output into one place
• Understand your data by finding the most
important factors controlling output values
• Expand your data by interpolating and
extrapolating
• Optimize your data by finding correlations
between input and output data to optimize
desired output
6

7. Example
• Organize: Build a database of all the relevant factors (impurity
concentrations, processing conditions, testing conditions, …)
and output performance.
• Understand: Which impurities matter most. Size of impurity
effects vs. other contributions.
• Expand: Interpolate/extrapolate to other impurity
concentrations to assess performance under conditions we
have not yet explored.
• Optimize: Determine impurity concentrations that lead to
optimal performance.
I know impurities impact my device lifetime, so …
7

8. Example: Predicting Impurity Diffusion in
FCC Alloys
• 15 FCC hosts x 100
impurities = 1500
systems, ~15m core-
hours (~$500k to
produce, ~2 years).
• We have computed
values for ~10%
• How can we quickly
(and cheaply) get to
~100% coverage?
8
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
UNPUBLISHED DATA – CONFIDENTIAL – DO NOT DISSEMINATE

9. Materials Informatics Approach –
Regression and Prediction
• Assume Activation energy = F(elemental properties)
• Elemental properties = melting temperature, bulk modulus,
electronegativity, …
• F is determined using a one of many possible methods: linear
regression, neural network, decision tree, kernel ridge
regression, …
• Fit F with calculated data, test it with cross-validation, then
predict new data.
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
Train F(properties)
M Al Ca Ni Cu Sr Rh Pd Ag Yb Ir Pt Au Pb Ac Th
X 13 20 28 29 38 45 46 47 70 77 78 79 82 89 90
H 1
He 2
Li 3
Be 4
B 5
C 6
N 7
O 8
F 9
Ne 10
Na 11
Mg 12
Al 13
Si 14
P 15
S 16
Cl 17
Ar 18
K 19
Ca 20
Sc 21
Ti 22
V 23
Cr 24
Mn 25
Fe 26
Co 27
Ni 28
Cu 29
Zn 30
Ga 31
Ge 32
As 33
Se 34
Br 35
Kr 36
Rb 37
Sr 38
Y 39 N/A N/A
Zr 40
Nb 41
Mo 42 N/A
Tc 43 N/A N/A
Ru 44 N/A N/A
Rh 45 N/A N/A
Pd 46 N/A
Ag 47
Cd 48
In 49
Sn 50
Sb 51
Te 52
I 53
Xe 54
Cs 55
Ba 56
La 57 N/A N/A
Ce 58
Pr 59
Nd 60
Pm 61
Sm 62
Eu 63
Gd 64
Tb 65
Dy 66
Ho 67
Er 68
Tm 69
Yb 70
Lu 71
Hf 72
Ta 73
W 74
Re 75
Os 76
Ir 77
Pt 78
Au 79
Hg 80
Tl 81
Pb 82
Bi 83
Po 84
At 85
Rn 86
Fr 87
Ra 88
Ac 89
Th 90
Pa 91
U 92
Np 93
Pu 94
Y. Zeng and K. Bai, Journal of Alloys and Compounds 624, p. 201-209 (2015).
9

10. Model Predictive Ability
• Leave one out
cross validation
• Predictive RMS =
0.24 eV – predicts
diffusion of new
impurity within
~10x at 1000K
• Time to predict
new system < 1s!
0 1 2 3 4 5 6
DFT Activation Energy [eV]
0
1
2
3
4
5
6
PredictedActivationEnergy[eV]
Al
Cu
Ni
Pd
Pt
Au
Ca
Ir
Pb
Leave One Out Cross Validation
y = 0.9909x
R
2
= 0.9312
UNPUBLISHED DATA – CONFIDENTIAL – DO NOT DISSEMINATE
10

11. Who Did the Work?
Undergraduate Informatics Team!
Benjamin Anderson
Liam Witteman
Team guru and postdoc
Henry Wu
Aren Lorenson
Haotian Wu
Zachary Jensen
11

12. For Researchers Interested in Working
with the Materials Informatics
Skunkworks
12

13. What the Informatics Skunkworks
Might Provide You
WORKFORCE
A team of talented students who are ready to work quickly with
your company to get the most out of your data
DATA ANALYTICS
Technical skills to help you organize, understand and expand data
sets and utilize data to optimize materials development
13

14. What You Might Provide the
Informatics Skunkworks
FINANCIAL/COURSE CREDIT SUPPORT
Internships, Co-ops, Senior design/Capstone projects, Research
projects, Research funding or course credits
SHARED DATA
Data sets of materials related performance and property data that
are large (> ~50), can be shared (ideally published), and are worth
mining
14

15. For Students Interested in Joining the
Materials Informatics Skunkworks
15

16. Joining the Materials Informatics Skunkworks
Who is welcome?
• Anyone – we focus on undergraduates but graduate students and postdocs are
welcome. We are centered at UW Madison but would love to branch out to
other schools.
• Prerequisites – an excitement about the topic and a willingness to work hard on
it. No informatics skilled needed. We strongly encourage those interested in at
least a year, ideally longer, commitments. But we also encourage those
interested in doing shorter term class and capstone projects.
What would I do?
• We work with you to define a data set and problem and get you the necessary
tools to do the work.
• You apply informatics tools to materials problems, learn from and train other
students, help organize events, and join in the fun.
How do I join?
• Send an email to Dane Morgan at ddmorgan@wisc.edu and we can discuss how
to get you involved.
16

17. Why Join Materials Informatics Skunkworks?
• Have fun doing creative, new, and impactful science!
• Learn about materials informatics, one of the hottest new areas in materials
science.
• Learn computer science methods from informatics, machine learning, data
mining, knowledge discovery, etc. that are changing our world, from diagnosing
cancer to self-driving cars.
• Learn critical skills in teamwork and initiative by independently driving your own
work as part of larger team projects.
• Learn modern programming and IT tools, including python coding, GitHub and
team code development, teamwork with Slack, Matlab, Excel, etc.
• Generate impactful publishable undergraduate research that is critical to
support applications for jobs and graduate school.
• Accomplish more than you can working alone by joining a team whose DNA is
sharing and teamwork for the benefit of everyone involved.
• Strengthen your resume by working with an established team that is part of a
world-class research group and will soon have published scientific papers, a
strong online, and wide notoriety.
• Engage your personal creativity – materials informatics is a transformative new
field and you can help work with us to define it.
17

18. Thank You for Your Attention
18