Scientific Machine Learning
Learning dynamics from data with structure baked in, neural ODEs/SDEs, physics-informed learning, differentiable simulation, and operator learning / neural operators.
Neural ODEsPINNsNeural OperatorsDifferentiable Sim
Open to collaborations & discussions
Aman Pawar
PhD Researcher in the MP-AIX Programme
Max Planck Institute · Magdeburg & Tübingen, Germany
I build mathematically grounded machine learning for complex dynamical systems, bringing together probabilistic inference, scientific computing, and causality to make models that are accurate, principled, and uncertainty-aware.
MP-AIX
PhD · Max Planck Institute
1 + 4
Patents granted & filed
9.4 / 10
M.Tech CGPA · IISc
OxML ’24
Oxford ML Summer School
About
Principled ML for systems that move, react, and evolve.
Scientific ML
Bayesian inference
Causal discovery
Operator learning
Uncertainty quantification
Read the research
I’m a PhD researcher in the MP-AIX programme at the Max Planck Institute for Dynamics of Complex Technical Systems, jointly advised by Prof. Peter Benner and Prof. Philipp Hennig (University of Tübingen). My work sits at the meeting point of scientific machine learning, Bayesian inference, and causality.
My doctoral research centres on probabilistic causal inference in complex dynamical systems, learning the mechanisms behind data, quantifying what we don’t know, and turning operator- and equation-level structure into models that generalise. Before the PhD I completed an M.Tech at the Indian Institute of Science and worked with Siemens Healthineers, Ola Electric, AIIMS-Delhi, and IIT Delhi, with several patents in AI for healthcare and edge systems along the way.
I care about translating foundational models into robust, deployable systems, across clinical, industrial, and vehicle-scale platforms, and about doing science that is careful, reproducible, and useful.
Research
Five threads, one goal: models we can trust.
Real-world systems, biological, physical, clinical, are dynamical, noisy, and only partially observed. I develop machine-learning methods that respect that structure: models grounded in differential equations and operators, made honest by Bayesian uncertainty, and made explanatory by causality. The goal is not just prediction, but understanding we can trust and act on.
Probabilistic ML & Bayesian Inference
Treating computation and modelling as inference: Bayesian inverse problems, probabilistic numerics, and calibrated uncertainty quantification.
Bayesian InferenceProbabilistic NumericsUncertainty Quantification
Causal Discovery & Inference
Recovering mechanisms, not just correlations, causal structure learning and treatment-effect estimation in complex, dynamical, confounded settings (my PhD focus).
Causal DiscoveryTreatment EffectsInterventions
Graph Neural Networks & Representation Learning
Structured representations for relational and spatiotemporal systems using GNNs and attention, from multi-agent dynamics to clinical time-series.
GNNsGraph AttentionRepresentation Learning
Machine Learning for Science & Health
Putting the methods to work: electronic health records, medical imaging, and scientific applications where reliability and interpretability matter.
EHRMedical ImagingHealthcare AI
Selected work
All projects
Featured projects
Synthetic Instrumental Variables
Learning to synthesize valid instrumental variables from observed covariates with a graph-attention network, for less-biased treatment-effect estimation under unobserved confounding (2SLS, evaluated on LaLonde).
Causal InferenceGraph AttentionPyTorch Geometric2SLS
Causal Discovery in Spatio-Temporal Systems
Self-supervised spatio-temporal GNN embeddings feeding a constraint-based (PC) discovery step to recover directed spatial–temporal dependencies beyond Granger causality, on the METR-LA sensor network.
Causal DiscoveryST-GNNPyTorchPC Algorithm
Graph-Informed Signature Kernels
Signature-kernel conditional-independence testing (rough-path theory) combined with GNN-derived biomedical knowledge graphs for sample-efficient causal discovery in clinical time-series (MIMIC-III).
Kernel MethodsRough PathsHealthcare AI
News
All news
Latest updates
Jul 24, 2026Upcoming
Heading to MLSS Tübingen 2026
I’ll be attending the Machine Learning Summer School in Tübingen, looking forward to a couple of weeks of talks, posters, and conversations with the community. Photos and notes to follow here.
Jul 1, 2026Milestone
Started my PhD in the MP-AIX programme at the Max Planck Institute
I’ve joined the Max Planck Institute for Dynamics of Complex Technical Systems as a doctoral researcher in the MP-AIX programme, advised by Prof. Peter Benner and Prof. Philipp Hennig, working on probabilistic causal inference in complex dynamical systems.
May 31, 2026
Wrapped up research at AIIMS-Delhi (AI Centre of Excellence)
Co-developed and validated “Arogya Sankalp”, an AI-powered oral-cancer screening app for frontline health workers, and drafted a clinical randomized-controlled-trial proposal for the Evidence-for-AI-in-Health initiative.
Affiliations & communities
Get in touch
Let’s talk research, collaborations, or positions.
I’m always glad to hear from fellow researchers and students, about scientific & probabilistic ML, causal inference, ML for science and health, or potential collaborations.
pawar@mpi-magdeburg.mpg.de