Manu Jayadharan, PhD

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

CV Google Scholar GitHub LinkedIn ORCID Email

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

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.

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.

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).

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

• Nov 2026 Co-organizing a three-part minisymposium, Advances in Discovering Interpretable Models from Fully and Partially Observed Data, with Jared P. Whitehead at the SIAM Conference on Mathematics of Data Science (MDS26) in Salt Lake City. See the program →
• 2026 Teaching a new project-based graduate course, Agentic AI for Scientific Computing, at Northwestern Applied Mathematics in Fall 2026.
• 2026 SODAs, our sparse-optimization algorithm for discovering differential-algebraic systems from data, published in Proceedings of the Royal Society A.
• 2026 Senior-author preprint on ill-conditioning in dictionary-based equation learning (arXiv:2603.11330) under review at SIAM J. Life Sciences.
• Aug 2025 Invited talk, From Data to Differential Equations, at the Indian Institute of Space Science and Technology.
• Jul 2025 Invited talk on SODAs at the SIAM Annual Meeting (AN25).
• 2025 Paper on multiscale mortar mixed FEM for the Biot system published in Computer Methods in Applied Mechanics and Engineering.
• Sep 2023 Joined Northwestern University as a Postdoctoral Fellow in Applied Mathematics.

Conference & workshop organization

Advances in Discovering Interpretable Models from Fully and Partially Observed Data

Three-part minisymposium (MS19 / MS40 / MS62) · SIAM Conference on Mathematics of Data Science (MDS26)
Salt Palace Convention Center, Salt Lake City, Utah · Sessions November 16–17, 2026 (conference November 16–20, 2026)

Co-organized with Jared P. Whitehead (Brigham Young University). As scientific datasets continue to grow, data-driven methods are opening new opportunities to discover interpretable mathematical models from both fully and partially observed systems. This minisymposium brings together researchers working on methodological development, theory, numerical analysis, uncertainty quantification, and applications across systems biology, neuroscience, geophysics, mechanical systems, image recognition, and the social sciences — at the intersection of interpretable modeling, scientific machine learning, inverse problems, equation discovery, system identification, and data assimilation. I speak in Part I on the numerical stability of sparse-optimization–based equation discovery.

Full program & speaker index →

Full program — 12 talks across three sessions

MS19 — Part I · Monday, November 16, 9:30–11:30 a.m.

• Manu Jayadharan, Northwestern University — Numerical Stability of Sparse Optimization Based Equation Discovery
• Dmitry Batenkov, Basis Research Institute — Discovery of Dynamical Models for Interpreting Animal Movements in Natural Environments
• Amir Arzani, University of Utah — Sparse Global Optimization for Interpretable Dynamical Systems Identification and Reduced-Order Modeling
• Teresa Portone, Sandia National Laboratories — A Staged Approach to Developing Data-Driven Closure Models

MS40 — Part II · Monday, November 16, 2:15–4:15 p.m.

• Tiara R. Eddington, Brigham Young University — System Identification via Optimization in Data Assimilation
• Chuanqi Chen, University of Wisconsin–Madison — Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Conditional Gaussian Koopman Network
• Casey Diekman, New Jersey Institute of Technology — Inferring Mechanisms of Circadian Regulation of Cardiac Dynamics from ECG Recordings
• Mojgan Alishiri, University of Utah — Multistage Integral Neural Operator (MINO) for Interpretable Kernel Discovery

MS62 — Part III · Tuesday, November 17, 9:30–11:30 a.m.

• Sean Reiter, New York University — Amortized State Filtering with Generative Models
• Deepak Mishra, Indian Institute of Space Science and Technology — Learning on Graphs and Manifolds: Geometric Deep Learning for Spatiotemporal Data
• Andrey A. Popov, University of Hawai‘i at Mānoa — Particle Filtering for Online System Identification
• Ryne Beeson, Princeton University — Tropical Cyclone Forecasting with Physics-Based Machine Learning and Data Assimilation

Selected publications

• M. Jayadharan, N. M. Mangan, et al., “SODAs: Sparse Optimization for Discovery of Differential-Algebraic Systems from Data,” Proceedings of the Royal Society A, 2026.
• M. Jayadharan, I. Yotov, “Multiscale mortar mixed finite element methods for the Biot system of poroelasticity,” Comput. Methods Appl. Mech. Engrg., 2025.
• M. Jayadharan, M. Kern, M. Vohralík, I. Yotov, “A space-time multiscale mortar mixed finite element method for parabolic equations,” SIAM J. Numer. Anal., 2023.
• Y. Feng, N. M. Mangan, M. Jayadharan†, “Ill-conditioning in dictionary-based dynamic-equation learning,” under review at SIAM J. Life Sciences, 2026.

Full publication list →