Research
I work on point defects in two-dimensional materials, mainly hexagonal boron nitride, and on making first-principles calculations cheaper and more predictive with machine learning.
Current work
- Now
Persistent photoconductivity in hBN
Defect discovery and photoinduced doping in hexagonal boron nitride, aimed at deep-UV optoelectronics.
PhysicsAI/MLhBN2D materialsPoint defectsPersistent photoconductivityDFTGWBSEML interatomic potentialsMolecular dynamics
Earlier work
- 2025
Deep-learning prediction of ab initio parameters
A pipeline, from an MLP to a graph neural network, that infers Hubbard U and related parameters from atomic and electronic descriptors.
AI/MLPhysicsGraph neural networksMachine learningDFT+UHybrid functionals
- 2023–2024
BMach, Bayesian optimization of Hubbard U
A Bayesian framework that calibrates Hubbard U and hybrid-functional parameters at a small fraction of the cost of direct high-level methods.
AI/MLPhysicsBayesian optimizationGaussian processesMachine learningDFT+UHybrid functionals
- PhD, completed 2025
Machine-learning-driven modeling of far-infrared semiconductors
InSb, InAs, InAsSb alloys and CdTe/InSb heterointerfaces from first principles.
PhysicsElectronicsSemiconductorsInfrared materialsInSbInAsSb alloysHeterointerfacesAlloysDFTDFT+UHybrid functionalsGWDFPTBand alignmentBayesian optimizationMachine learning
Publications
- 2026
Beyond Return Ratios: Identification, Partial Identification, and Mechanism Evidence in Leveraged ETFs
Ritwik Das. SSRN working paper, 28 August 2026 (2026).Preprint
AccessDOI
FinanceQuantitative financeETFsLeveraged ETFsReturn ratiosIdentification
- 2025
Machine Learning-Driven First-Principles Modeling of Far-Infrared Materials
Ritwik Das. PhD thesis, Université Paris-Saclay, C2N (CNRS). NNT 2025UPAST100 (2025).
PhysicsAI/MLBayesian optimizationGaussian processesMachine learningDFT+UHybrid functionalsGWInSbInAsSb alloysHeterointerfacesBand alignmentVirtual crystal approximationAlloysInfrared materialsSemiconductors
- 2025
High-fidelity electronic structure and properties of InSb: G0W0 and Bayesian-optimized hybrid functionals and DFT + U approaches
Ritwik Das, Anne-Sophie Grimault-Jacquin, Frédéric Aniel. Physical Review B 112, 075136 (2025).
PhysicsAI/MLInSbSemiconductorsInfrared materialsGWHybrid functionalsDFT+UBayesian optimizationMachine learning
- 2025
Structural, Electronic Properties and Band Gap Bowing Parameters of CuPt-Ordered InAsxSb1−x Alloys: First-Principles Insights from HSE, G0W0, mBJ, and DFT+U
R. Das, A.-S. Grimault-Jacquin, F. Aniel. Submitted to Physical Review Materials (2025).Submitted
PhysicsElectronicsInAsSb alloysAlloysSemiconductorsInfrared materialsHybrid functionalsGWDFT+U
- 2024
The full list is on Google Scholar.
Talks
- 18 March 2026
- 2023
Bayesian Machine: Optimizing the Hubbard U Parameter in DFT+U With Machine Learning
Conference contribution, European Materials Research Society (E-MRS) Conference.