Ameya D. Jagtap

Dr. Ameya D. Jagtap

Assistant Professor (Tenure-Track)

Department of Aerospace Engineering,

Worcester Polytechnic Institute (WPI), USA.

WPI Aerospace Engineering Faculty Website

Param-Intelligence (π) Lab

Emails: ajagtap@wpi.edu, ameyadjagtap@gmail.com.

“In theory, there is no difference between theory and practice. But in practice, there is.”

- Yogi Berra

About Me

I am an Assistant Professor (tenure-track) in the Department of Aerospace Engineering at Worcester Polytechnic Institute (WPI), USA. Prior to joining WPI, I served as an Assistant Professor of Applied Mathematics (Research) at Brown University for three and a half years. My academic journey includes earning both my PhD and Master's degrees in Aerospace Engineering from the esteemed Indian Institute of Science (IISc) in India. Following this, I engaged in postdoctoral research at the Tata Institute of Fundamental Research—Center for Applicable Mathematics (TIFR-CAM) in India. Subsequently, I transitioned to Brown University to continue my postdoctoral research within the Division of Applied Mathematics.

My research is uniquely positioned at the intersection of mechanical/aerospace engineering, applied mathematics, and computation. I am particularly dedicated to advancing scientific machine learning algorithms that seamlessly integrate data and physics, offering versatile applications across computational physics. My areas of expertise encompass scientific machine learning, deep learning, data- and physics-driven deep learning techniques, uncertainty quantification, and propagation, as well as multi-scale/multi-physics simulations (solids, fluids, and acoustics). I bring proficiency in spectral/finite element methods, WENO/DG schemes, and domain decomposition techniques, among others. Beyond these, I am actively engaged in more traditional machine learning algorithms such as deep generative models, and novel artificial neural network architectures, such as quantum and graph neural networks. To this end, my interests also extend to spiking neural networks and other bio-inspired computing techniques.

Experience:

Assistant Professor (Tenure-Track) : Department of Aerospace Engineering, Worcester Polytechnic Institute, USA. July 2024 - Present.
Assistant Professor of Applied Mathematics (Research) : Division of Applied Mathematics, Brown University, USA. Jan. 2021 - June 2024
Postdoctoral Research Associate : Division of Applied Mathematics, Brown University, USA. Jan. 2019 - Dec. 2020
Postdoctoral Fellow : Centre for Applicable Mathematics, Tata Institute of Fundamental Research, India. Sept. 2016 - Dec. 2018
Junior Research Associate : Department of Aerospace Engineering, Indian Institute of Science, India. Aug. 2015 - Jan. 2016
Visiting Researcher : University of Luxembourg, Luxembourg, May 01 - July 31, 2013.
Visiting Researcher : Technical University of Braunschweig, Germany, Mar 01 - April 31, 2012.

Education

Doctor of Philosophy (Ph.D), Aerospace Engineering, Indian Institute of Science, India (2016).
Master of Engineering (M.E.), Aerospace Engineering, Indian Institute of Science, India (2010).
AMAeSI (Bachelor in Aeronautical Engineering), The Aeronautical Society of India, India (2008).
Bachelor of Science (BSc - Mathematics), University of Madras, India (2008).
Diploma in Mechanical Engineering (T. Eng.), Institution of Mechanical Engineers, India (2003).

Editorial Board Member

I'm an editorial board member of the following international journals.

Neural Networks, Elsevier (IF: 7.8) [Journal Link]
Neurocomputing, Elsevier (IF: 6.0) [Journal Link]
Journal of Machine Learning Research (IF: 5.177) [Journal Link]
Frontiers in Neuroinformatics (IF: 3.5) [Journal Link]
Frontiers in Computational Neuroscience (IF: 3.2) [Journal Link]

News & Updates

List of Top 2% Scientists in the World by Stanford University USA!

Honored to be included among the top 2% of scientists worldwide! This achievement would not have been possible without the dedication and hard work of my incredible collaborators and students. Thank you all for your invaluable contributions!

Recently Accepted Papers

Jassem Abbasi, Ben Moseley, Takeshi Kurotori, Ameya D. Jagtap, Anthony R. Kovscek, Aksel Hiorth, and Pal Østebø Andersen, History-Matching of Imbibition Flow in Multiscale Fractured Porous Media Using Physics-Informed Neural Networks (PINNs), Computer Methods in Applied Mechanics and Engineering, Vol. 437 (2025) 117784. [Journal]
S. Brahmachary, S M. Joshi, A. Panda, K. Koneripalli, A. Kumar Sagotra, H Patel, A. Sharma, Ameya D. Jagtap, K. Kalyanaraman, Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism, Neurocomputing, 622 (2025) 129272 [Journal] [arXiv].
A. Peyvan, V. Oommen, Ameya D. Jagtap, G. E. Karniadakis, RiemannONets: Interpretable Neural Operators for Riemann Problems, Computer Methods in Applied Mechanics and Engineering, Volume 426, 116996 (2024) [Journal] [arXiv]
T. Kossaczka, Ameya D. Jagtap, Matthias Ehrhardt, Deep smoothness WENO scheme for two-dimensional hyperbolic conservation laws: A deep learning approach for learning smoothness indicators, Physics of Fluids 36, 036603 (2024) [Journal]
S. Goswami, Ameya D. Jagtap, H. Babaee, B. T. Susi, and G.E. Karniadakis, Learning stiff chemical kinetics using extended deep neural operators, Computer Methods in Applied Mechanics and Engineering, Volume 419 (2024) 116674. [Journal] [arXiv]
Z. Hu, Ameya D. Jagtap, G. E. Karniadakis, K. Kawaguchi, Augmented Physics-Informed Neural Networks (APINNs): A gating network-based soft domain decomposition methodology. Engineering Applications of Artificial Intelligence, Volume 126 (2023) 107183. [Journal] [arXiv]
M. Penwarden, Ameya D. Jagtap, S. Zhe, G.E.Karniadakis, M. Kirby, A unified scalable framework for causal sweeping strategies for physics-informed neural networks (PINNs) and their temporal decompositions, Journal of Computational Physics, Volume 493 (2023) 112464 [Journal] [arXiv]

(A unified framework for causality-enforcing PINNs with efficient temporal decompostions.)

Ameya D. Jagtap, G.E. Karniadakis, How important are activation functions for regression and classification? A survey, performance comparison, and future directions, Journal of Machine Learning for Modeling and Computing, Volume 4, Issue 1, 2023, pp. 21-75 [Journal][arXiv] (The first comprehensive survey of activation functions for both classification and regression problems)
T. De Ryck, Ameya D. Jagtap, and S. Mishra, Error estimates for physics informed neural networks approximating the Navier-Stokes equations, IMA Journal of Numerical Analysis, Oxford Academic, 2023. https://doi.org/10.1093/imanum/drac085 [Journal] [arXiv]

(First Nonlinear Theory for PINNs and XPINNs: This is the first comprehensive theoretical analysis of PINNs (and XPINNs) for a prototypical nonlinear PDE, the Navier-Stokes equations.)

Z. Hu, Ameya D. Jagtap, G. E. Karniadakis, K. Kawaguchi, When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?, SIAM Journal on Scientific Computing, Vol. 44, No. 5, pp. A3158–A3182. [Journal] [arXiv]
Ameya D. Jagtap, Z. Mao, N. Adams, G.E. Karniadakis, Physics-informed neural networks for inverse problems in supersonic flows, Journal of Computational Physics, 466 (2022) 111402. [Journal] [arXiv]
Ameya D. Jagtap, D. Mitsotakis, G. E. Karniadakis, Deep learning of inverse water waves problems using multi-fidelity data: Application to Serre-Green-Naghdi equations, Ocean Engineering, 248 (2022) 110775. [Journal] [arXiv]
Ameya D. Jagtap, Y. Shin, K. Kawaguchi, G. E. Karniadakis, Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions, Neurocomputing, Vol. 468, (2022), 165-180. [Journal] [arXiv]

Recent Preprints

J. Abbasi, Ameya D. Jagtap, B. Moseley, A. Hiorth, and P. Ø. Andersen, Challenges and Advancements in Modeling Shock Fronts with Physics-Informed Neural Networks: A Review and Benchmarking Study, arxiv preprint, arXiv:2503.17379, 2025. [Arxiv]

One of the Most Cited Articles since 2020

Adaptive activation functions accelerate convergence in deep and physics-informed neural networks, Journal of Computational Physics, Vol. 404, 109136, 2020.
Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems, Computer Methods in Applied Mechanics and Engineering, 365 (2020) 113028.
Physics-informed neural networks for high-speed flows, Computer Methods in Applied Mechanics and Engineering, Vol.360, 112789, 2020.
Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations, Communications in Computational Physics, Vol. 28, No.5, pp. 2002-2041, 2020.
Locally adaptive activation functions with slope recovery for deep and physics-informed neural networks, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 476: 20200334, 2020. [Journal] [arXiv]
Parallel Physics-Informed Neural Networks via Domain Decomposition, Journal of Computational Physics, 447 (2021) 110683. [Journal] [arXiv]

Most Downloaded Papers in the Last 90 Days

Adaptive activation functions accelerate convergence in deep and physics-informed neural networks, Journal of Computational Physics, Vol. 404, 109136, 2020.
Physics-informed neural networks for inverse problems in supersonic flows, Journal of Computational Physics, 466 (2022) 111402. [Journal] [arXiv]
Conservative physics-informed neural networks on discrete domains for conservation laws: Applications to forward and inverse problems, Computer Methods in Applied Mechanics and Engineering, 365 (2020) 113028.
Physics-informed neural networks for high-speed flows, Computer Methods in Applied Mechanics and Engineering, Vol.360, 112789, 2020.

Highlighted papers on DeepAI : The Front Page of A.I.

Ameya D. Jagtap, Y. Shin, K. Kawaguchi, G. E. Karniadakis, Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions, Neurocomputing, Vol. 468, (2022), 165-180. [Journal] [arXiv]
Z. Hu, Ameya D. Jagtap, G. E. Karniadakis, K. Kawaguchi, When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?, arXiv preprint, arXiv:2109.09444, 2021. [arXiv]

Featured Article on Communications in Computational Physics (CiCP) Journal

A. D. Jagtap, G E Karniadakis, Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations, Communications in Computational Physics, Vol. 28, No.5, pp. 2002-2041, 2020.

Recently Invited Talks

Mathematical Sciences Departmental Colloquium, WPI, USA. (April 12, 2024).
Physics-Informed Neural networks and Neural Operator Networks: Methods and Applications, Oak Ridge National Laboratory, USA. (February 8, 2024) (Flyer)
Phi-ML meets Engineering, The Alan Turing Institute, UK. (February 1, 2024) (Flyer)
A physics-informed neural network-based solution to inverse problems in high-speed fluid flows, International Symposium on Recent Trends in Numerical Methods, IIT Kanpur, India. (January 21, 2024)
Physics-Informed Deep Learning: Methods and Applications in Scientific Computing, Worcester Polytechnic Institute, USA. (January 10, 2024)
Physics-Driven Deep Learning Methods for Scientific Computing, 5th International Conference on Mathematical Techniques and Applications (ICMTA-2024), SRM, India. (January 3, 2024)
Physics-Informed Deep learning: Merging Data with Physics, Shell .ai, Aryabhata Series, Shell Technology Center Bangalore, India, Oct. 20, 2023 (Flyer)
Short Course on Physics-Informed Deep Learning at TIFR-CAM, Bengaluru, India (18 Oct. 2023) [Link]
Scientific Machine Learning through the Lens of Physics-Informed Neural Networks, Lawrence Livermore National Laboratory, April 14, 2023.
Scientific Machine Learning through the Lens of Physics-Informed Neural Networks, SankhyaSutra Labs, India, Feb. 24, 2023. (Flyer)
Physics-Informed Neural Networks for Inverse Problems in Supersonic Flows, Theoretical Division, Los Alamos National Laboratory, USA Oct. 24, 2022
Artificial Neural Networks for scientific computations: Embedding physics and data, The University of Texas at El Paso (UTEP), USA, Oct. 21, 2022.
Physics-Informed Neural Networks for Scientific Computations: Algorithms and Applications, BIMSA-Tsinghua seminar on Machine Learning and Differential Equations, Yanqi Lake Beijing Institute of Mathematical Sciences and Applications, and Tsinghua University, China, Oct. 12, 2022. (Flyer)
Physics-Informed Machine Learning: Merging Data and Physics, High-Performance Computing, and AI Predictive Tools in Fluids and Thermal, NIT Rourkela, India, July 26, 2022.
Physics-Informed Machine Learning for scientific computations: Recent Advances and Applications, Theoretical Division, Los Alamos National Laboratory, USA, May 20, 2022.
Physics-Informed Neural Networks: A new paradigm for learning physical laws, Conference on PDE and Numerical Analysis, Tata Institute of Fundamental Research - Center for Applicable Mathematics, Bengaluru, India, April 30, 2022. (Link)
Physics-Informed Machine Learning for scientific computations: Recent Advances and Applications, LANS Seminar, Argonne National Laboratory, USA, February 23, 2022. (Flyer)
Physics-Informed Machine Learning for scientific computations, ECE Colloquium Series, University of Connecticut, USA, November 19, 2021.
Scientific Machine Learning: From PINNs to eXtended PINNs (XPINNs), SRM University, India, September 11, 2021. (Flyer)
A Generalized Space-Time Domain Decomposition based Extended Physics-Informed Neural Networks for partial differential equations: Method and Implementation, Carnegie Mellon University, USA, June 17, 2021.
Parallel Physics-Informed Neural Networks via Domain Decomposition, Seminars of the Interdisciplinary Area of Computational Engineering and Science, COPPE/Federal University of Rio de Janeiro, Brazil, June 10, 2021. (Poster)
Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations, AI Chair OceaniX Webinars 2021, IMT Atlantique, Brest, France, March 24, 2021.
Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations, AAAI 2021 Spring Symposium on Combining Artificial Intelligence and Machine Learning in Physics Sciences, Stanford University, Palo Alto, California, USA, March 22, 2021.

Outstanding Reviewer Certificate 2020

I am honored and delighted to receive the certificate for the outstanding reviewer of the year 2020 from Pramana - Journal of Physics, Springer (Indian Academy of Sciences)

My Recent Publications

PINNs for Supersonic Flow Problems

Ameya D. Jagtap, Z. Mao, N. Adams, G.E. Karniadakis, Physics-informed neural networks for inverse problems in supersonic flows, Journal of Computational Physics, 466 (2022) 111402. [Journal] [arXiv]

PINNs for Nonlinear Water Wave Problems

Ameya D. Jagtap, D. Mitsotakis, G. E. Karniadakis, Deep learning of inverse water waves problems using multi-fidelity data: Application to Serre-Green-Naghdi equations, Ocean Engineering, 248 (2022) 110775. [Journal] [arXiv]

XPINNs Generalization

Z. Hu, Ameya D. Jagtap, G. E. Karniadakis, K. Kawaguchi, When Do Extended Physics-Informed Neural Networks (XPINNs) Improve Generalization?, arXiv preprint, arXiv:2109.09444, 2021. [arXiv] (Accepted in SIAM Journal on Scientific Computing)

General Framework for Adaptive Activation functions and Rowdy Activation Functions

Ameya D. Jagtap, Y. Shin, K. Kawaguchi, G. E. Karniadakis, Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions, Neurocomputing, Vol. 468, (2022), 165-180. [Journal] [arXiv]

Scalable and Parallel PINNs using Domain Decomposition Strategy

K. Shukla, A. D. Jagtap, G E Karniadakis, Parallel Physics-Informed Neural Networks via Domain Decomposition, Journal of Computational Physics, 447 (2021) 110683. [Journal] [arXiv]

Quantification of Microstructure Properties of Nickel Material using Experimental Data

K. Shukla, A. D. Jagtap, James L. Blackshire, Daniel Sparkman, and G. E. Karniadakis, A physics-informed neural network for quantifying the microstructure properties of polycrystalline Nickel using ultrasound data, IEEE Signal Processing Magazine, vol. 39, no. 1, pp. 68-77, Jan. 2022. [Journal] [arXiv]

eXtended PINNs: Generalized Space-Time Domain Decomposition based PINNs

Ameya D. Jagtap, G. E. Karniadakis, Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition based Deep Learning Framework for Nonlinear Partial Differential Equations, Communications in Computational Physics, Vol. 28, No. 5, pp. 2002-2041, 2020. [Journal]

Page updated

Google Sites

Report abuse