Scientific machine learning
Scientific machine learning (SciML) aims to combine the structure and guarantees of physics-based models with the flexibility of modern machine learning. My interests include differentiable simulation, surrogate and reduced-order modeling, and learning-enhanced numerical methods for inference and uncertainty quantification.
Featured projects
Hybrid ML-PDE for accelerated simulation
A project on differentiable weak-form and source-term corrections for PDE solvers, integrating finite element/DG structure with trainable operators.
Disentangled latent spaces for scientific modeling
A project on auxiliary-guided latent representations for interpretable generative modeling, dark-matter structure analysis, and deep priors for Bayesian inverse problems.
Selected journal publications
- Arkaprabha Ganguli and Emil M Constantinescu. Disentangled deep priors for Bayesian inverse problems. Submitted, 2026. [arXiv] [PDF]
- Arkaprabha Ganguli, Anirban Samaddar, Florian Kéruzoré, Nesar Ramachandra, Julie Bessac, Sandeep Madireddy, and Emil M Constantinescu. Uncovering physical drivers of dark matter halo structures with auxiliary-variable-guided generative models. Submitted, 2026. [arXiv] [PDF]
- Shinhoo Kang and Emil M Constantinescu. Differentiable DG with neural operator source term correction. Submitted, 2025. [arXiv]
- Pi-Yueh Chuang, Ahmed Attia, and Emil M Constantinescu. Distributional sensitivity analysis: Enabling differentiability in sample-based inference. Submitted, 2025. [arXiv]
- Haoyuan Chen, Emil M Constantinescu, Vishwas Rao, and Cristiana Stan. Improving the predictability of the Madden-Julian oscillation at subseasonal scales with Gaussian process models. JAMES - Machine learning application to Earth system modeling, Vol. 17(5); Pages e2023MS004188, 2025. [DOI] [arXiv]
- Arkaprabha Ganguli, Nesar Ramachandra, Julie Bessac, and Emil M Constantinescu. Enhancing interpretability in generative modeling: Statistically disentangled latent spaces guided by generative factors in scientific datasets. Springer Machine Learning, Vol. 114(9); Pages 197, 2025. [DOI] [arXiv]
- Shinhoo Kang and Emil M Constantinescu. Learning subgrid-scale models with neural ordinary differential equations. Computers and Fluids, In Press, Vol. 261; Pages 105919, 2023. [DOI] [arXiv]
- Romit Maulik Vishwas Rao, Jiali Wang, Gianmarco Mengaldo, Emil M Constantinescu, Bethany Lusch, Prasanna Balaprakash, Ian Foster, Rao Kotamarthi. AIEADA 1.0: Efficient high-dimensional variational data assimilation with machine-learned reduced-order models,. GMDD, 2022. [DOI] [arXiv] [PDF]
- Emil M Constantinescu and Mihai Anitescu. Physics-based covariance models for Gaussian processes with multiple outputs. International Journal for Uncertainty Quantification, Vol. 3(1); Pages 47-71, 2013. [DOI]
Proceedings / presentations
- Junoh Jung and Emil M Constantinescu. Learning differentiable weak-form corrections to accelerate finite element simulations. To appear, 2026. [arXiv] [PDF]
- Arkaprabha Ganguli, Anirban Samaddar, Florian Kéruzoré, Nesar Ramachandra, Julie Bessac, Sandeep Madireddy, and Emil M Constantinescu. Uncovering physical drivers of dark matter halo structures with auxiliary-variable-guided generative models. Machine Learning and the Physical Sciences, part of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2025. [arXiv] [PDF]
- Piyush Garg, Emil M Constantinescu, Bethany Lusch, Troy Arcomano, Jiali Wang, and Rao Kotamarthi. Physics-informed domain-aware atmospheric radiative transfer emulator for all sky conditions. 2023 Tackling Climate Change with Machine Learning Workshop, part of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.
- Haoyuan Chen, Emil M Constantinescu, Vishwas Rao, and Cristiana Stan. Uncertainty quantification of the Madden-Julian oscillation with Gaussian processes. 2023 Tackling Climate Change with Machine Learning Workshop, part of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023.
- Vishwas Hebbur Venkata Subba Rao, Romit Maulik, Emil M Constantinescu, and Mihai Anitescu. A machine learning method for computing rare event probabilities. ICCS 2020 (International Conference on Computational Science 2020), Vol. LNCS 12142; Pages 169–182, 2020. [DOI] [arXiv]