Manu Jayadharan
Portrait of Manu Jayadharan

Manu Jayadharan, PhD

Applied mathematician and computational scientist
Postdoctoral Fellow, Engineering Sciences & Applied Mathematics
Northwestern University

I work at the intersection of scientific machine learning, dynamical systems, and numerical methods, with a focus on developing algorithms to discover real-world models. I design numerically stable, data-driven methods for discovering and solving differential equations and implement them as open-source software. My background spans high-performance numerical solvers for PDEs, industry-scale quantitative modeling at Citigroup, and data-driven model discovery, with applications in biological, physical, and financial domains.

At Northwestern I work with Dr. Niall Mangan, and I am an affiliated researcher at the NSF–Simons National Institute for Theory and Mathematics in Biology (NITMB) and the Trienens Institute for Sustainability and Energy. I hold a PhD in Mathematics from the University of Pittsburgh (2021) and worked as a Quantitative Analyst (AVP) at Citigroup from 2021 to 2023.

What I work on

SODAs recovery of algebraic relationships on the IEEE-39 power grid under noise

Equation discovery from data

Stable, interpretable algorithms for learning differential-algebraic equations from noisy measurements: SODAs (Proc. Royal Society A, 2026) and the open-source package DAE-FINDER. Shown: recovery of power-grid constraints on the IEEE-39 benchmark under measurement noise.

SVD analysis of a candidate library with 15% noise

Inverse problems & ill-conditioning

Why dictionary-based model discovery fails, diagnosed through inverse-problem theory, and how to fix it. Shown: SVD diagnostics of a chemical-reaction-network candidate library at 15% noise.

Animated poroelastic flow simulation from BiotDD

Multiphysics PDE solvers

Fast finite-element solvers for coupled Poisson–Nernst–Planck electrochemical systems and domain decomposition for Biot poroelasticity. Shown: my MPI-parallel poroelastic flow simulation (BiotDD).

Workflow diagram: scientist steers AI agents through skill sets and validation protocols

Agentic AI for scientific computing

Protocols, validation frameworks, and reusable agentic skill sets for using frontier AI agents in scientific computing, with a new graduate course at Northwestern in Fall 2026.

More about my research →

News

Selected publications

Full publication list →