NIST-JARVIS infrastructure for Improved Materials Design

1. NIST-JARVIS infrastructure for Improved
Materials Design
Kamal Choudhary
https://jarvis.nist.gov/
NIST, Gaithersburg, MD, USA
CECAM workshop, 10/11/2022
1
Joint Automated Repository for Various Integrated Simulations

2. Acknowledgement and Collaboration
2
A. Biacchi
(NIST)
D. Wines
(NIST)
R. Gurunathan
(NIST)
B. DeCost
(NIST)
Bobby sumpter
(ORNL)
A. Agarwal
(Northwestern
University)
S. Kalidindi
(GAtech)
A. Reid
(NIST)
Ruth Pachter
(AFRL)
Karen Sauer
(George
Mason University)
K. Garrity
(NIST)
David Vanderbilt
(Rutgers
University)
Sergei
Kalinin
(ORNL)
F. Tavazza
(NIST)

3. Outline
3
• Motivation [4]
• Introduction [5-8]
• Electronic structure databases [9-19]
• ALIGNN (scalar & vector-value) [20-32]
• AtomVision [33-36]
• AtomQC [37-43]
• ChemNLP [44-46]
• Summary [47]
Contents

4. Motivation
4
• Accelerate traditional computational
and experimental methods
• Automate experimental data analysis,
• Discover new materials,
• Develop new methods,
• Find new physical equations/phenomenon,
• Enhance collaboration,
• Uncertainty quantification, reproducibility,…
Modularity: discrete, continuous, images, text Materials Genome Initiative 2011
Crystals Molecules TEM images
Band-structure XRD spectra

5. Databases, Tools, Events, Outreach
5
https://jarvis.nist.gov
“You guys are doing something really beneficial…”
“I find JARVIS-DFT very useful for my research…”
User-comments:
Established: January 2017
(MGI funded)
Published: >40 articles
Users: >10000+ users worldwide
Downloads: >500K
Events:
• Quantum Matters in Materials Science (QMMS)
• Artificial Intelligence for Materials Science (AIMS)
• JARVIS-School
jarvis.nist.gov: Requires login credentials, free registration
Choudhary et al., npj Computational Materials 6, 173 (2020).

6. 2017 2018 2019 2020 2021
JARVIS-FF
(Evaluate FF)
JARVIS-DFT
2D
(OptB88vdW,
Exf. En.)
JARVIS-DFT
Optoelectronics
(TBmBJ)
JARVIS-DFT
Elastic Tensor
3D & 2D
JARVIS-ML
CFID
descriptors
JARVIS-FF
(Evaluate FF,
defects)
JARVIS-DFT
Topological
SOC spillage
3D
JARVIS-DFT
/ML
K-point
convergence
JARVIS-DFT
Solar SLME
JARVIS-DFT
Topological SOC
spillage 2D
(Mag/Non-Mag.)
JARVIS-DFT/ML
2D Heterostructures
JARVIS-DFT/ML
DFPT
Dielec., Piezo., IR
JARVIS-DFT/ML
Thermoelectrics
3D & 2D
Seebeck, PF
JARVIS-DFT EFG
NQR, NMR
JARVIS-AQCE 2D
JARVIS-DFT
WTBH
Topological SOC
spillage 3D Mag.,
non-mag, Exp.
JARVIS-AtomQC
VQE/VQD
JARVIS-DAC
MOFs
AtomVison
(STEM/STM)
JARVIS-TB
TB3PY
JARVIS-
ALIGNN
JARVIS-
OPTIMADE
6
2022
JARVIS-
SuperConductors
ALIGNN-FF
ALIGNN-Spectra
(DOS/XANES/Dielec.
JARVIS-QMC
JARVIS-AHC
JARVIS-ChemNLP

7. Tools

8. JARVIS-DFT: Electronic structure calculations
• Schrödinger equation for electrons: wave–particle duality,
• Schrödinger equation of a fictitious system (the "Kohn–Sham system") of non-interacting
particles (typically electrons) that generate the same density as any given system of interacting
particles
• Uses density vs wavefunction quantity
• Although a complete theory, several approximations such as:
1) K-points, 2) vdW interactions, 3) kinetic energy deriv., 4) spin-orbit coupling, 5) e-ph coupling
(Convergence, OptB88vdW, TBmBJ, SOC topology, Superconducting prop. )
       
r
r
E
r
r
V
m
i
i
i
Eff 
 








 2
2
2

XC
ee
Ne
Eff V
V
V
T
V 




 E
H 
Walter Kohn (2013)
Exchange-correlation
8
Many DFT databases with GGA-PBE, fixed k-point, no-SOC, …

9. JARVIS-DFT
9
Motivation: Functional and structural materials design using quantum mechanical methods
~70000 materials, millions of calculated properties, compared with experiments if possible
https://jarvis.nist.gov/jarvisdft/

10. JARVIS-DFT MatProj. OQMD
#Materials (Struct., Ef, Eg ) 70870 144595 (41697 common) 1022663
DFT functional/methods vdW-DFT-OptB88, TBmBJ, DFT+SOC GGA-PBE, PBE+U, GLLBSC GGA-PBE, PBE+U
K-point/cut-off Converged for each material Fixed (1000-3000) kp/atom, 520 eV Fixed kp/atom, cutoff
SCF convergence criteria Energy & Forces Energy Energy
Elastic tensors & point phonons 17402 14072 -
Piezoelectric, IR spectra 4801 3402 -
Dielectric tensors (w/o ion) 4801 (15860) 3402 -
Electric field gradients 11865 - -
XANES spectra - 22000 -
2D monolayers 1011 - -
Raman spectra 400 50 -
Seebeck, Power F 23210 48000 -
Solar SLME 8614 - -
Spin-orbit Coupling Spillage 11383 - -
WannierTB 1771 - -
STM images 1432 - -

11. K-point convergence
11
• Energy per cell convergence of 0.001 eV/cell for each material
• Most DFT high-throughput workflows use per reciprocal atom (pra) =>1000

12. vdW interactions: 3D, 2D, 1D & 0D materials
• vdW materials: high lattice error, is converse true?
• Van der Waals (vdW) bonding in x, y, z-directions; exfoliation energy
• If the error => 5%, we predict them to be low-D materials,
• 1100 mats. with OptB88vdW functionals, tight DFT convergence
• Improved lattice parameters with OptB88vdW
ICSD
ICSD
PBE
l
l
l 


12
3D: Si 2D: MoS2
0D: BiI3
1D-MoBr3
Nature: Scientific Reports, 7, 5179 (2017)
Nature:Scientific Data 5, 180082 (2018)
Phys. Rev. B, 98, 014107 (2018)

13. MetaGGA & optoelectronic properties
13
• Bandgap, frequency dependent dielectric function from OptB88vdW (OPT) and Modified Becke-Johnson formalisms (MBJ)
• MBJ gives excellent bandgap with low computational cost, also better dielectric function with linear optics
Nature:Scientific Data 5, 180082 (2018)
~20000 TBmBJ bandgaps and dielectric function
MAE bandgap (eV):
• MatProj: 1.45
• AFLOW: 1.23
• OQMD: 1.14
• OptB88vdW: 1.33
• TBmBJ: 0.51
• HSE06: 0.41
(wrt 54 exp. data)

14. Solar cells & linear optics
14
Scientific Data 5, 180082 (2018)
Chemistry of Materials, 31, 15, 5900 (2019).
Spectroscopic Limited Maximum Efficiency (SLME)

15. Spin-orbit coupling & Topological Materials
New class of materials
(electronic bandgap perspective)
15
Email: kamal.choudhary@nist.gov
https://phys.org/news/2014-01-quantum-natural-3d-counterpart-graphene.html
https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSzMKD5ICIkR9neJRre3prqIjp_iqLMu6TQp7mXKJqmmh-HqjFB
(2016 Nobel prize)
Metal
Semiconductor
Insulator

16. Spin-orbit Spillage
• Majority of the topological materials driven by spin-orbit coupling (SOC)
• Simple idea: Compare wavefunctions of a material with and without SOC?
• Spillage initially proposed for insulators only, now extended to metals also
• Advantages over symmetry-based approaches:
disordered and magnetic mats.
• For trivial materials, spillage 0.0, non-trivial materials ≥ 0.25
16
https://www.ctcms.nist.gov/~knc6/jsmol/JVASP-1067
𝜂 𝐤 = 𝑛𝑜𝑐𝑐(𝐤) − Tr 𝑃 ෨
𝑃 ; 𝑃 𝐤 = ෍
𝑛=1
)
𝑛𝑜𝑐𝑐(𝐤
ۧ
|𝜓𝑛𝐤 ൻ𝜓𝑛𝐤|
Sci. Rep., 9, 8534 (2019)
NPJ Comp. Mat., 6, 49 (2020)
Phys Rev B, 103, 054602 (2021)

17. Topological Insulator, Bi2Se3
Weyl semi-metal, MoTe2
Dirac Semi-metal, Na3Bi
Topological crystalline insulator, SnTe
E
X
A
M
P
L
E
S

18. 18
BCS Superconductors & E-Ph coupling
Debye
Temp
DOS at
EFermi
https://arxiv.org/abs/2205.00060
Superconductors: Materials to conduct electricity without energy loss when they are cooled below a critical temperature, Tc
MgB2 (Tc = 39 K): Highest Tc ambient condition conventional superconductor

19. Other electronic structure databases
19
JARVIS-TB3Py
Tight-binding models
JARVIS-QMC
Quantum Monte Carlo

20. 20
ALIGNN
Atomistic Line Graph Neural Network

21. Introduction: deep learning for materials
21

22. 22
From ANNs to Graph Convolution Networks
𝑧[𝑙]
= 𝑊
[𝑙]
𝑎
[𝑙−1]
+ 𝑏
[𝑙]
𝑎[1]
= σ( 𝑧[𝑙]
); 𝑎[0]
= 𝑋
1) Forward propagation
2) 𝐶𝑜𝑠𝑡, 𝐽(𝑊, 𝑏) = 𝑓(𝑦 − ෤
𝑦)
X1
X2
Hidden
Layer
Input
Layer
Output
layer
෤
𝑦
3) Gradient descent (∇J):
minimize cost with W,b
4) Backpropagation:
chain rule to get,
𝜕𝐽
𝜕𝑊
1) Convolution:
element-wise multiplication & sum
2) Pool: Max, Average, Sum
3) Fully Connected: Standard NN
Shared weights (Learnable filters),
regularized version of NNs
መ
𝐴 = ෩
𝐷−
1
2 𝐴෩
𝐷−
1
2 𝐻𝑙+1 = σ 𝑊 መ
𝐴𝐻𝑙
Adjacency matrix, A
1 0 1
0 1 0
1 0 1
1) Adjacency matrix, N x N (N: #nodes),
2) D: degree of node
3) Update node representation using
message passing, GPU efficient
4) Update equation is local, neighborhood
of a node only, independent of graph size
Standard NN ConvolutionNN GraphConvNN
Types: un/weighted, un/directed, line,
Hetero/Homogenous, Multigraph

23. 23
Line Graph
Explicitly represent pairwise and triplet (bond angle) interactions using line graph
Possible to extend for n-body, e.g. line graph of line graph
nisaba.nist.gov Tesla V100

24. 24
ALIGNN Model
Initial
atom,
bond,
angle
features
Feature-wise
sum
across
atoms
Property
prediction
Compose multiple ALIGNN and EdgeGatedGCN layers: learnable local atom environment representation
Global crystal representation: Feature-wise average across atoms in the crystal
Final property regression model: linear model for regression, logistic regression for classification

25. 25
Performance on the Materials Project Dataset
Trained on 69239 materials (DFT data)
#Epochs: 300
Batch_size: 64
• ~44 % improvement by ALIGNN with similar/better training speed
• Similar performance enhancement on QM9 molecule dataset
• Also available on MatBench: https://matbench.materialsproject.org

26. 26
Performance on the JARVIS-DFT Dataset
Trained on ~55k materials
 Total energy, Formation energy , Ehull
 Bandgap (OPT), Bandgap (MBJ)
 Kv, Gv
 Mag. mom
 єx (OPT/MBJ), єy (OPT), єz (OPT), є
(DFPT:elec+ionic)
 Max. piezo. stress coeff (eij)
 Solar-SLME (%)
 Topological-Spillage
 2D-Exfo. energy
 Kpoint-length
 Plane-wave cutoff
 Max. Electric field gradient
 avg. me, avg. mh
 n-Seebeck, n-PF, p-Seebeck, p-PF

27. 27
Evac with ALIGNN Energy model
No ML training defect structures/data ! Directly predicting with energy/atom model
Total 508 datapoints, MAE wrt Exp. for subset: 0.3 eV
(Elemental solids+Alloys+Oxides+2D monolayers)
~34 % improvement with scissor shift
https://arxiv.org/abs/2205.08366
pretrained.py --model_name jv_optb88vdw_total_energy_alignn--file_format poscar --file_path POSCAR

28. 28
BCS Superconductors
• Prediction on 10 % test data
• 8293 out of 431778 materials in COD as superconductors
• First predicting Eliashberg function, then Tc  6 % improvement
• ALIGNN for both scalar and spectral learning
Best

29. 29
Phonon density of states

30. 30
Unified GNN Force-field
Simulate any combination of 89
elements from the periodic
table

31. 31
Unified GNN Force-field
Example NVT :
Interface of
2H-MoS2(001)/
Al2O3(0001)
Genetic algorithm
EV-curves

32. 32
CO2 Isotherms: AI for Climate Change
DL model for predicting CO2 adsorption in MOFs (using hMOF GCMC data)
Choudhary et al., Computational Materials Science 210, 111388 (2022)

33. 33
AtomVision
A deep learning framework for atomistic image data

34. 34
Scanning Tunneling Microscope Image
Tersoff-Hamann Approach

35. 35
Scanning Transmission Electron Microscope Image
PPdSe: JVASP-6316
C: JVASP-667 FeTe: JVASP-6667
Convolution approximation: accurate for thin films mainly (here 2D mats.)
Based on Rutherford scattering model

36. 36
Image classification and semantic segmentation
2D Bravais lattice classification (DenseNet):
1) hexagonal, 2) square, 3) rectangle, 4) rhombus, 5) parallelogram
Baseline accuracy 1/5 = 20 %
Semantic segmentation using U-Net:
Atom vs background, pixelwise classification

37. 37
AtomQC
Atomistic Calculations on Quantum Computers

38. Background: Feynman’s seminal papers
38
http://physics.whu.edu.cn/dfiles/wenjian/1_00_QIC_Feynman
“Nature is quantum, goddamn it! So if we
want to simulate it, we need a quantum
computer.”

39. Variational Quantum Eigensolver (VQE) &
Variation Quantum Deflation(VQD)
39
http://openqemist.1qbit.com/docs/vqe_microsoft_qsharp.html
Notes:
• Quantum computers are good in preparing states, not good at sum, optimizers, multiplying etc.
• QC to prepare a wavefunction ansatz of the system and estimate the expectation value
VQD: Deflate other eigensatets once ground state is found using VQE
VQE: a hybrid classical-quantum algorithm using Ritz variational principle

40. Typical Flowchart
40
https://github.com/usnistgov/jarvis
https://github.com/usnistgov/atomqc
K. Choudhary, J. Phys.: Condens. Matter 33 (2021) 385501
Wannier functions:
• Complete orthonormalized basis set,
• Acts as a bridge between a delocalized plane wave representation and a localized atomic orbital basis
• All major density functional theory (DFT) codes support generation WFs for a material
𝐻 = ෍ ℎ𝑃𝑃
𝑃∈ 𝐼,𝑋,𝑌,𝑍 ⨂𝑛
𝐻𝑗 = 𝐻 + ෍ 𝛽𝑖|𝜓(𝜽0
∗)ۧ 𝜓(𝜽0
∗)|
𝑗−1
𝑖=0
𝐺(𝑘, ꞷ𝑛) = [ꞷ𝑛 + 𝜇 − 𝐻(𝑘) − 𝛴(ꞷ𝑛)]−1
http://www.wannier.org/

41. Circuit Trials
41
RealAmplitudes PauliTwoDesign
EfficientSU2
jarvis.core.circuits.QuantumCircuitLibrary
RY and RZ: parametrized circuits with parameters ө, Wires and boxes with ‘X’ :Controlled-X gate.
Wires with two solid squares: Controlled-Z gates

42. FCC Aluminum Example
42
a) Monitoring VQE optimization progress with several local optimizers such COBYLA, L_BFGS_B, SLSQP, CG, and SPSA
for Al electronic WTBH and at X-point.
b) Electronic bandstructure calculated from classical diagonalization (Numpy-based exact solution) and VQD algorithm for
Al.
c) Phonon bandstructure for Al

43. Dynamical Mean Field Theory
43
Imaginary part of Al’s DMFT hybridization function for a few components considering zero self-energy. a)Δ00, b)Δ01,
c)Δ10, d)Δ11
• Dynamical mean-field theory (DMFT): commonly used
techniques for solving predicting electronic structure of
correlated systems using impurity solver models.
• DMFT maps a many-body lattice problem to a many-
body local problem with impurity models.
• In DMFT one of the central quantities of interest is the
Green’s function such as
𝐺(𝑘, ꞷ𝑛) = [ꞷ𝑛 + 𝜇 − 𝐻(𝑘) − 𝛴(ꞷ𝑛)]−1
• Spectral function (𝐴) & DMFT hybridization function (𝛥)
𝐴(ꞷ) = −
1
𝜋
෍ 𝐼𝑚(𝐺(ꞷ + 𝑖𝛿))
𝑘
𝛥(ꞷ + 𝑖𝛿) = ꞷ − (𝐺)−1
• Next, integrate with quantum impurity solvers
𝛴 = 0

44. 44
ChemNLP
A Natural Language Processing based Library for Materials Chemistry Text Data

45. 45
ChemNLP
arXiv dataset 1.8 million articles
arXiv:2209.08203

46. 46
ChemNLP

47. 47
Summary
• NIST-JARVIS infrastructure with multiple components
• Electronic structure methods and database
• Deep-learning and quantum computation
• Several events to engage (sign-up today!)
• Continuously growing…
https://jarvis.nist.gov
https://github.com/usnistgov/jarvis
https://github.com/usnistgov/alignn
https://github.com/usnistgov/atomvision
https://github.com/usnistgov/chemnlp
https://github.com/usnistgov/atomqc
Email: kamal.choudhary@nist.gov
@dr_k_choudhary
@knc6
Slides:https://www.slideshare.net/KAMALCHOUDHARY4