Table of Contents

• Introduction
• Basics
• ES tutorial
• FF/MC related tutorial
• JARVIS-School
• AI tutorial
• QC tutorial
• NanoHub tutorial
• References
• How to contribute
• Correspondence
• Funding support
• License

JARVIS-Tools Notebooks (Introduction)

The JARVIS-Tools Notebooks is a collection of Jupyter/ Google-Colab notebooks to provide tutorials on various methods for materials design. It consists of several types of applications such as for electronic structure (ES), force-field (FF), Monte Carlo (MC), artificial intelligence (AI), quantum computation (QC) and experiments (EXP). This project is a part of the NIST-JARVIS infrastructure. A few more detailed tutorial are also available at: JARVIS-Tools.

Basics

A few preliminary notebooks before diving into materials design

1. Python beginners notebook
2. For absolute Beginners in ML using Python
3. Silicon atomic structure and analysis example

Electronic structure

Density functional theory, Tight-binding and Beyond-DFT methods using various software

1. Analyzing_data_in_the_JARVIS_DFT_dataset
2. Analyzing_data_in_the_JARVIS_Leaderboard
3. Basic quantum espresso run
4. JARVIS_Optoelectronics_Computational_screening_of_high_performance_optoelectronic_materials_using_OptB88vdW_and_TB_mBJ_formalisms
5. JARVIS_TopologicalSpillage_High_throughput_Discovery_of_Topologically_Non_trivial_Materials_using_Spin_orbit_Spillage
6. JARVIS_Solar_Accelerated_Discovery_of_Efficient_Solar_Cell_Materials_Using_Quantum_and_Machine_Learning_Methods
7. Si_bandstructure&densityof_states
8. JARVIS_Wannier90Example
9. BoltztrapExample
10. Making 2D heterostructures
11. JARVIS_DFT_FormationEnergiesAccuracyCheck
12. Downloading raw analysis data and input/output files
13. JARVIS_DFT_2D_High_throughput_Identification_and_Characterization_of_Two_dimensional_Materials_using_Density_functional_theory
14. JARVIS_CONVERG_Convergence_and_machine_learning_predictions_of_Monkhorst_Pack_k_points_and_plane_wave_cut_off_in_high_throughput_DFT_calculations
15. JARVIS_DFPT_High_throughput_Density_Functional_Perturbation_Theory_and_Machine_Learning_Predictions_of_Infrared,_Piezoelectric_and_Dielectric_Responses
16. JARVIS_TE_Data_driven_discovery_of_3D_and_2D_thermoelectric_materials
17. JARVIS_ELAST_Elastic_properties_of_bulk_and_low_dimensional_materials_using_van_der_Waals_density_functional
18. Get JARVIS-DFT final structures in ASE or Pymatgen format
19. JARVIS_Solar_Accelerated_Discovery_of_Efficient_Solar_Cell_Materials_Using_Quantum_and_Machine_Learning_Methods
20. JARVIS_TopologicalSpillage_High_throughput_Discovery_of_Topologically_Non_trivial_Materials_using_Spin_orbit_Spillage
21. JARVIS_Optoelectronics_Computational_screening_of_high_performance_optoelectronic_materials_using_OptB88vdW_and_TB_mBJ_formalisms
22. JARVIS_QuantumEspressoColab_Designing_High_Tc_Superconductors_with_BCS_inspired_Screening,_Density_Functional_Theory_and_Deep_learning
23. JARVIS_WTBH_Database_of_Wannier_tight_binding_Hamiltonians_using_high_throughput_density_functional_theory
24. Comapre_MP_JV
25. ParsingWebpages(JARVIS_DFT)
26. ConvexHull
27. DimensionalityAndExfoliationEnergy
28. Element_filter_for_JARVIS_DFT_dataset
29. Run GPAW on Google-colab and calculate interface energy with jarvis-tools
30. ParsingWebpages(JARVIS_DFT)
31. WTBH_MagneticMats.ipynb
32. QMCPACK_Basic_Example

Force-field

1. JARVIS_LAMMPS
2. MLFF SNAP training
3. ALIGNN-FF for energy and forces
4. ALLEGRO training for Silicon
5. Analyzing_MOF_datasets

Artificial intelligence/Machine learning

AI models for chemical formula, atomic structures, image and text for both forward and inverse design. Some of the methods include descriptor/feature based, graph based and transformers based designs.

1. Analyzing data in JARVIS-Leaderboard
2. ML_Chem_Formula_Descriptors
3. Basic_Machine_learning_training_example_with_CFID_descriptors
4. JARVIS_ML_TrainingGPU
5. JARVIS_CFID_LightGBM_GPUvsCPU
6. JARVIS_ML_TensorFlowExample
7. JARVIS_Leaderboard_MatMiner
8. CIF To Graph_example
9. JARVIS_ALIGNN_Basic_Training_example
10. ALIGNN-FF pretrained model/calculator usage
11. JARVIS_Leaderboard_contribution_ALIGNN
12. JARVIS_Leaderboard_MLFF/ALIGNN-FF for Silicon
13. JARVIS_Leaderboard_KGCNN
14. ALIGNN Superconductor training
15. Train ALLEGRO-FF for Silicon
16. Train NEQUIP-FF for Silicon
17. Train CHGNet-FF for Silicon
18. MatGL-FF_Mlearn for Silicon
19. SNAP-FF_Mlearn for Silicon
20. Pretrained CHGNet Prediction
21. Pretrained OpenCatalystProject Model
22. ALIGNN-Pretrained property-predictor models
23. ALIGNN-PhononDos
24. Inverse design of superconductors with CDVAE
25. JARVIS_STEM_2D
26. AtomVision_Leaderboard_Example
27. AtomVision_Example
28. ChemNLP example
29. ChemNLP HuggingFace example
30. AtomGPT training example
31. AtomGPT HuggingFace inference example
32. Open catalyst project load model
33. Vacancy formation ML
34. Interface Materials Design/InterMat example
35. ALIGNN-FF Unified force-field structure relaxation
36. Basic external tutorial on linear models

Quantum computation

1. With new qiskit package version: Quantum computation and Qiskit based electronic bandstructure
2. With old qiskit package version: Quantum computation and Qiskit based electronic bandstructure

NanoHub FAIR workflow workshop/JARVIS-School @ Purdue university

https://nanohub.org/FAIR_workshop_2024

1. Learn a basic DFT calculation

Basic quantum espresso run

2. Once you run a lot of these, you can make a database, and analyze trends (AKA Exploratory Data Analysis)

Analyzing_data_in_the_JARVIS_DFT_dataset

3. These datasets can also be used to develop fast surrogate machine learning models

JARVIS_Leaderboard_contribution_ALIGNN

4. Beyond single property prediction models, they can be used to train machine-learning force-fields as well

ALIGNN-FF for energy and forces

5. While the above MLFF was trained for single element system, a more generalized model was developed with JARVIS-DFT diverse dataset, and the developed model can be used for fast atomic structure optimization and phonon etc. property predictions

ALIGNN-FF Unified force-field structure relaxation

6. While the above ML models were for forward design, we can use AtomGPT for inverse design as well

AtomGPT training example

AtomGPT HuggingFace inference example

7. Other optional notebooks for the tutorial session

AtomVision_Example

JARVIS_LAMMPS

Quantum computation and Qiskit based electronic bandstructure

AIMS2024 tutorial and presentation slides

https://github.com/usnistgov/aims2024_workshop

JARVIS-School

More info

APS2023 tutorial

More info

AIMS2022 tutorial

More info

References

The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design & various other publications

How to contribute

For detailed instructions, please see Contribution instructions

Correspondence

Please report bugs as Github issues(preferred) or email to kamal.choudhary@nist.gov.

Funding support

NIST-MGI (https://www.nist.gov/mgi).

Code of conduct

Please see Code of conduct

License

NIST License