Skip to Main Content U.S. Department of Energy
Physics-Informed Learning Machines

Announcements

PhILMs webinar speakers:


Invited presentations and keynotes:

  • Atzberger PJ. 2019. "Challenges and Opportunities using Machine Learning Approaches in the Sciences and Engineering", Sandia National Laboratories, March 2019, Albuquerque, New Mexico.
  • Atzberger PJ. 2019. "Incorporating Physics-Based Inductive Bias into Machine Learning Methods", Sandia National Laboratories, May 2019, Livermore, California.
  • D'Elia M. 2019. "nPINNs: Physics-Informed Neural Networks", Control and Optimization for nonlocal problem, RICAM, Linz, Austria, Oct 2019.
  • Daskalakis C. 2018. Theory of Computation Colloquium, MIT, September 2018, Cambridge, Massachusetts.
  • Daskalakis C. 2018. Applied Mathematics Seminar, MIT, October 2018, Cambridge, Massachusetts.
  • Daskalakis C. 2018. Workshop on Complexity of Total Search Problems, Foundations of Computer Science Conference, October 2018, Paris, France.
  • Daskalakis C. 2018. Algorithms Seminar, Boston University, November 2018, Boston, Massachusetts.
  • Daskalakis C. 2018. New York Colloquium on Algorithms and Complexity, November 2018, New York, New York.
  • Daskalakis C. 2018. ECE Seminar, UT Austin, November 2018, Austin, Texas.
  • Daskalakis C. 2018. NIPS 2018 Workshop on "Smooth Games Optimization and Machine Learning", December 2018, Montreal, Canada (Invited Talk).
  • Daskalakis C. 2018. Applied Economic Theory Seminar, University of Chicago, December 2018, Chicago, Illinois.
  • Daskalakis C. 2018. Greek Stochastics Kappa Workshop, December 2018, Athens, Greece.
  • Daskalakis C. 2019. Greek Ministry of Defense, January 2019, Athens, Greece.
  • Daskalakis C. 2019. National Technical University of Athens, January 2019, Athens, Greece.
  • Daskalakis C. 2019. Public Lecture at Fundraising Gala, Not for Profit Organization "Mazi gia to paidi," January 2019, Athens, Greece.
  • Daskalakis C. 2019. American College of Athens, January 2019, Athens, Greece (Outreach Lecture).
  • Daskalakis C. 2019. Varvakeio high school, January 2019, Athens, Greece (Outreach Lecture).
  • Daskalakis C. 2019. Columbia-Princeton Probability Day, March 2019, Princeton, New Jersey (Plenary Talk).
  • Daskalakis C. 2019. Technology Forum, April 2019, Thessaloniki, Greece (Plenary Talk).
  • Daskalakis C. 2019. Arsakeio High School, April 2019, Athens, Greece (Outreach Talk).
  • Daskalakis C. 2019. ML Track Keynote, Open Data Science Conference, April 2019, Boston, Massachusetts.
  • Daskalakis C. 2019. ACM Summer School on Data Science, July 2019, Athens, Greece (Keynote).
  • Daskalakis C. 2019. Emmanuel Drandakis Lecture, Conference on Research on Economic Theory and Econometrics, July 2019, Tinos, Greece.
  • Daskalakis C. 2019. Workshop on Algorithms for Learning and Economics, July 2019, Rhodes, Greece (Invited Talk).
  • Daskalakis C. 2019. AI Institute, Microsoft, August 2019, Redmond, Washington.
  • Daskalakis C. 2019. CS Colloquium, University of Wisconsin-Madison, September 2019, Madison, Wisconsin.
  • Daskalakis C. 2019. RANDOM-APPROX Conference, September 2019, Cambridge, Massachusetts (Keynote).
  • Daskalakis C. 2019. Applied Math Colloquium, Brown University, October 2019, Providence, Rhode Island.
  • Daskalakis C. 2019. Statistics Seminar, University of Pennsylvania, October 2019, Philadelphia, Pennsylvania.
  • Daskalakis C. 2019. Inference on Graphical Models Conference, Columbia University, October 2019, New York, New York (Invited Talk).
  • Daskalakis C. 2019. H2O AI World New York, October 2019, New York, New York (Keynote).
  • Gulian M. 2019. "Machine Learning of Space-Fractional Differential Equations", Control and Optimization for nonlocal problem, RICAM, Linz, Austria, Oct 2019.
  • Gulian M. 2019. "Machine Learning of Linear Fractional Differential Equations", SIAM Computer Science and Engineering Conference, February 2019, Spokane, Washington.
  • Karniadakis GE. 2019. "Physics-Informed Neural Networks (PINNs)", Machine Learning in Heliophysics, Sept 16-20, 2019 Amsterdam, Netherlands (Keynote).
  • Karniadakis GE. 2019. "Physics-informed neural networks (PINNs) with uncertainty quantification", Front UQ19: Frontiers on Uncertainty Quantification on Fluid Mechanics, Sept 11-13, 2019 Pisa, Italy (Keynote).
  • Karniadakis GE. 2019. "Uncertainty Quantification for Physics Informed Neural Networks", UNCECOMP: International Conference on Uncertainty Quantification in Computational Sciences and Engineering, June 24-26, 2019, Crete, Greece (Keynote).
  • Karniadakis GE. 2019. "Physics-Informed Learning Machines for Physical Systems", CFD IMPACT Conference, Technion, July 1, 2019, Haifa, Israel (Keynote).
  • Karniadakis GE. 2019. 22nd Korean SIAM Conference, May 17-18, 2019, Seoul, Korea (Keynote).
  • Karniadakis GE. 2019. Department of Mechanics, Zhejiang University, May 13, 2019, Zhejiang, China.
  • Karniadakis GE. 2019. Department of Mechanical Engineering, Northwestern University, April 18, 2019, Evanston, Illinois.
  • Karniadakis GE. 2019. "Physics-Informed Neural Networks (PINNs) for solving stochastic and fractional PDEs" Machine Learning for Multiscale Model Reduction Workshop, Harvard University, March 27-29, 2019, Cambridge, Massachusetts (Keynote).
  • Karniadakis GE. 2019. Department of Mathematics, Technical University of Munich, January 9, 2019, Munich, Germany.
  • Karniadakis GE. 2019. Department of Mechanical Engineering, Stanford University, November 30, 2019, Stanford, California. Parks M. 2019. "On Neumann-type Boundary Conditions for Nonlocal Models", 9th International Congress on Industrial and Applied Mathematics, Valencia, Spain, July 2019.
  • Perego M. 2019. "Neural Network Surrogates of PDE-based Dynamical Systems, Application to Ice Sheet Dynamics", SIAM Computer Science and Engineering Conference, February 2019, Spokane, Washington.
  • Stinis P. 2019. "Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks", ICERM Workshop on Scientific Machine Learning, January, 2019, Providence, Rhode Island.
  • Tartakovsky AM. 2018."Physics-Informed Machine Learning methods for Parameter and Model Estimation and Uncertainty Reduction", CCMA Seminar at Pennsylvania State University, State College, Pennsylvania.
  • Tartakovsky AM. 2018. "Non-local mesoscale multiphase flow model", Seminar at Imperial College, London, United Kingdom.
  • Tartakovsky AM. 2019. "Learning Parameters and Constitutive Relationships with Physics- Informed Deep Neural Networks", INTERPORE 11th Annual Meeting, Valencia, Spain.
  • Tartakovsky AM. 2019. "Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Network", Computational Science and Engineering (CSE), Spokane, Washington.
  • Tartakovsky AM. 2019. "Physics-Informed Machine Learning", Seminar at the Portland State University, Portland, Oregon.
  • Xu K, Darve E, and Huang D. 2019. "Physics informed machine learning", 15th US National Congress of Computational Mechanics, July 28-Aug 1, 2019, Austin, TX (Keynote).


Peer-reviewed Conference Papers:

  • Acharya J, Bhattacharyya A, Daskalakis C, and Kandasamy S. 2018. "Learning and Testing Causal Models with Interventions", Proceedings of the 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), December 2018, Montreal, Canada.
  • Anari N, Daskalakis C, Maass W, Papadimitriou C, Saberi A, and Vempala S. 2018. "Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons", Proceedings of the 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), December 2018, Montreal, Canada.
  • Dagan Y, Daskalakis C, Dikkala N, and Jayanti S. 2019. "Generalization and learning under Dobrushin's condition", Proceedings of the 32nd Annual Conference on Learning Theory (COLT), 2019, Phoenix, Arizona.
  • Daskalakis C, and Panageas, I. 2018. "The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization", Proceedings of the 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), December 2018, Montreal, Canada.
  • Daskalakis C, Dikkala N, and Jayanti S. 2018. "HOGWILD!-Gibbs can be PanAccurate", Proceedings of the 32nd Annual Conference on Neural Information Processing Systems (NeurIPS), December 2018, Montreal, Canada.
  • Daskalakis C, and Panageas I. 2019. "Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization", Proceedings of the 10th Innovations in Theoretical Computer Science (ITCS) Conference, January 2019, San Diego, California.
  • Daskalakis C, Dikkala N, and Panageas I. 2019. "Regression from Dependent Observations", Proceedings of the 51st Annual ACM Symposium on the Theory of Computing (STOC), 2019, Phoenix, Arizona. Daskalakis C, Gouleakis T, Tzamos C, and Zampetakis M. 2019. "Computationally and Statistically Efficient Truncated Regression", Proceedings of the 32nd Annual Conference on Learning Theory (COLT), 2019, Phoenix, Arizona.
  • Daskalakis C, Gouleakis T, Tzamos C, and Zampetakis M. 2018. "Efficient Statistics, in High Dimensions, from Truncated Samples", Proceedings of the 59th Annual IEEE Symposium on Foundations of Computer Science (FOCS), October 2018, Paris, France.
  • Trask N, Patel RG, Gross BJ, and Atzberger PJ. 2019. "GMLS-Nets: Scientific Machine Learning Methods for Unstructured Data", NeurIPs 2019: Workshop on Machine Learning and the Physical Sciences, December 2019, Vancouver, Canada (accepted).


Organized conferences and workshops:

  • Organized Minisymposium: Gross BJ and Atzberger PJ. "Machine Learning Approaches for the Sciences and Engineering: Recent Developments," SIAM Computer Science and Engineering Conference, February 2019, Spokane, Washington.
  • Organized Session: Tartakovsky, AM. "Big Data and Machine Learning in Hydrology and Subsurface Flow and Transport," AGU meeting, December 2018, Washington, District of Columbia.


Eric Darve presented a keynote lecture at USNCCM 15: "Physics informed machine learning"

Kailai Xu, Eric Darve, Daniel Huang, 15th US National Congress on Computational Mechanics, July 28-Aug 1, 2019, Austin, TX


Kailai Xu presented a poster: Adversarial Numerical Analysis at Xpo.

We introduce a novel approach -- adversarial numerical analysis (ANA) -- for solving inverse problems involving probabilistic computations. The approach allows us to solve a variety of inference problem by leveraging the striking power of neural networks for classification and adversarial training algorithms for intractable probabilistic computation. We demonstrate its effectiveness and generality by solving various problems, including UQ, probabilistic inversion, parameter inference in stochastic processes and volatility calibration for option pricing.


New software released for MachineLearning & PDE's - DeepXDE First Release, the most powerful machine learning tool to solve PDEs.


George Em Karniadakis's paper "Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness" was recently highlighted in the weekly online magazine DeepAI


PhILMs workshop on May 31, 2019 at Sandia National Lab focused on Machine Learning.


CRUNCH group research highlighted by LANGMUIR as cover article

Langmuir cover image
This photo was reprinted with permission from the authors. Copyright 2019 American Chemical Society.

Research from the CRUNCH group has been featured on the cover of the prestigious ACS journal LANGMUIR. The research was a collaborative effort by Kaixuan Zhang, Zhen Li, Martin Maxey and George Karniadakis in partnership with Shuo Chen from Tongji University (Shanghai, China). Shown on the cover are different phases of droplet coalescence dynamics on a hydrophobic surface with hierarchical roughness, in which the colors on the rough wall indicate the distribution of surface structure height, and the wavelets on the liquid droplets represent the thermal capillary waves. View the article.

The study reports a novel self-cleaning mechanism of textured surfaces attributed to a spontaneous coalescence-induced wetting transition, which explains why droplets on rough surfaces are able to change from the highly adhesive Wenzel state to the low-adhesion Cassie-Baxter state and achieve self-cleaning. The study also reports that the spatial distribution of liquid components in the coalesced droplet can be controlled by properly designing the overall arrangement of multiple droplets. The findings offer new insights for designing effective biomimetic self-cleaning surfaces by enhancing spontaneous Wenzel-to-Cassie wetting transitions, and additionally, for developing new noncontact methods to manipulate liquids inside the small droplets via multiple-droplet coalescence.

CRUNCH group research highlighted by Soft Matter as cover article

softmatter cover image
Cover image reproduced with permission of the authors and the Royal Society of Chemistry".

Recent research from the CRUNCH group has been featured on the back cover of the prestigious RSC journal Soft Matter. This highlighted work was performed in the group of Prof. George Karniadakis from the Division of Applied Mathematics, Brown University, in collaboration with the group of Prof. Chao Yang from the Institute of Process Engineering, Chinese Academy of Sciences. Shown on the cover is a snapshot of multiscale simulation of a shear flow past an endothelial glycocalyx layer (EGL) in a microchannel, with the atomistic resolution locally (water molecules, heparan sulfate chains, lipid bilayer and transmembrane proteins) and the coarse-grained resolution in bulk domain. View the article.

The study reports the multiscale modeling of soft multi-functional surfaces. The endothelial glycocalyx layer is a soft multi-functional surface, coating the endothelial cells and lining the entire vascular system. Single brute-force atomistic simulation for this problem is prohibitively expensive and limited to small scales. This study shows that an efficient parallel multiscale method can bridge the atomistic and mesoscale regimes in modeling of soft mult-functional surfaces, from nanometer to micron and beyond.


Harnessing New Computing Tools to Solve Big Physics Problems

New $10 million collaborative grant to boost deep learning applications

philms

The Department of Energy's Pacific Northwest National Laboratory (PNNL) has been tapped to lead a $10 million, four-year effort to uncover hidden physics using new developments in deep learning, a computing technique that harnesses the power of machine learning and big data.

The Physics-Informed Learning Machines for Multiscale and Multiphysics Problems (PhILMs) Center, is a collaboration among PNNL and Sandia National Laboratories, with academic partners at Brown University, Massachusetts Institute of Technology, Stanford University, and the University of California, Santa Barbara.

The PhILMs collaborators are working together to adapt advanced computing techniques to help solve long-standing problems in science and engineering. 

"The most difficult problems in modern physics and engineering involve computing at vastly different scales and across large data sets," said George Karniadakis, the Center Director, who holds a joint appointment at PNNL and Brown University. "By combining the expertise of mathematicians, programmers, and specialists in machine learning techniques, and focusing that expertise on these physics problems, we are aiming to bring new tools to the global physics community."

The research team plans to create, test, and release new open-source computational tools developed through the collaboration and make them freely available through the team's PhILMs web site.

The initial research goals include developing computational frameworks based on deep learning algorithms for applications in combustion, subsurface, and earth systems, as well as machine learning tools for the design of functional materials with tunable properties. Ultimately, the researchers hope to establish scientific machine learning as a new meta-discipline at the intersection of computational mathematics, big data, and deep learning.

PhILMs leadership includes PNNL's Alexandre Tartakovsky, Center Co-Director; Michael L. Parks, Sandia National Laboratories; Mark Ainsworth, Brown University; Eric Darve, Stanford University; and Paul J. Atzberger, University of California, Santa Barbara.

The collaboration is supported by the Applied Mathematics Program within the U.S. Department of Energy, Office of Advanced Scientific Computing Research.


Paul Atzberger organized a mini-symposium, "Machine Learning Approaches for the Sciences and Engineering: Recent Developments", at the 2019 SIAM Computer Science and Engineering (CSE) Conference.


George Em Karniadakis kicked off the DOE ASC meeting on January 30th in Rockville.

PhILMs

Collaborations

Seminar Series

Computing Research at PNNL

Science at PNNL

Computing Research

View All Highlights

Contacts