Kamal Choudhary (Fed)

My research interests are focused on atomistic materials design using classical, quantum, and machine learning methods. In particular, I have developed JARVIS database and tools (https://jarvis.nist.gov/) that hosts publicly available datasets for millions of material properties.

Some of my research projects:

• JARVIS-DFT: High-throughput density functional theory (DFT) database for more than 80000 materials. Link: https://jarvis.nist.gov/jarvisdft/
• JARVIS-ALIGNN: Atomistic Line Graph Neural Network for fast property predictions, force-field and inverse design. Link: https://jarvis.nist.gov/jalignn/
• JARVIS-AtomVision: Computer vision applications for atomistic images. Link: https://github.com/usnistgov/atomvision
• JARVIS-QuantumComputation: Quantum computation for materials. Link: https://github.com/usnistgov/atomqc
• JARVIS-FF: High-throughput evaluation of force-fields used in classical molecular dynamics simulation. Link: https://jarvis.nist.gov/jarvisff 
• JARVIS-ML: Classical force-field inspired descriptors (CFID) for materials Link: https://jarvis.nist.gov/jarvisml
• JARVIS-ChemNLP: Natural language processing for material science applications Link: https://github.com/usnistgov/chemnlp
• JARVIS-Leaderboard: Large scale benchmarking for materials design methods. Link: https://pages.nist.gov/jarvis_leaderboard/
• JARVIS-Tools: Software code/scripts for automation, analysis and data-dissemination for JARVIS. Link: https://github.com/usnistgov/jarvis
• JARVIS-Tools-Notebooks: Google colab note book collections Link https://github.com/JARVIS-Materials-Design/jarvis-tools-notebooks
• Google-scholar link
• Github

NIST MML Accolade 2017