BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Michigan Institute for Computational Discovery and Engineering - ECPv6.17.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://micde.umich.edu
X-WR-CALDESC:Events for Michigan Institute for Computational Discovery and Engineering
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20250711T120000
DTEND;TZID=America/Detroit:20250711T130000
DTSTAMP:20250808T204538Z
CREATED:20250708T154831Z
LAST-MODIFIED:20250808T204538Z
UID:10000826-1752235200-1752238800@micde.umich.edu
SUMMARY:Frontiers in Scientific Machine Learning Seminar 17: SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning
DESCRIPTION:Date: June 6\, 2025\, 12pm – 1pm\nThis is a hybrid event. To join via Zoom: Meeting ID: 978 2352 7756\, Passcode: Enter last year in format YYYY\nTo join in person: 2004 Lay Auto Lab. Refreshments will be available! \nAbstract: Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However\, real-world control systems–especially those requiring precise and reliable performance–often demand interpretability in the sense of a-priori assessments of agent behavior to identify safe or failure-prone interactions with environments. To address this limitation\, we propose SALSA-RL (Stability Analysis in the Latent Space of Actions)\, a novel RL framework that models control actions as dynamic\, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system\, our approach enables interpretability through local stability analysis\, where instantaneous growth in action-norms can be predicted before their execution. We demonstrate that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation\, SALSA-RL provides a powerful tool for advancing the design\, analysis\, and theoretical understanding of RL systems.\nBio: Romit Maulik is an Assistant Professor in the College of Information Sciences and Technology at Pennsylvania State University (Penn State). He is also a co-hire in the Institute for Computational and Data Sciences at Penn State and a Joint Appointment Faculty at Argonne National Laboratory. He obtained his PhD in Mechanical and Aerospace Engineering at Oklahoma State University (in 2019) and was the Margaret Butler Postdoctoral Fellow (from 2019-2021) before becoming an Assistant Computational Scientist at Argonne National Laboratory (from 2021-2023). His group studies high-performance multifidelity scientific machine learning algorithm development with applications to various multiphysical nonlinear dynamical systems such as those that arise in fluid dynamics\, geophysical modeling\, nuclear fusion\, and beyond. He is an Early Career Awardee of the Army Research Office.
URL:https://micde.umich.edu/event/workshop-seminarfrontiers-in-scientific-machine-learning-seminar-17-salsa-rl-stability-analysis-in-the-latent-space-of-actions-for-reinforcement-learning/
LOCATION:Walter E Lay Auto Lab – 2004
CATEGORIES:Deep Learning,FSML,Interdisciplinary,Machine Learning,North Campus,Scientific Computing,Sciml
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20250711T120000
DTEND;TZID=America/Detroit:20250711T130000
DTSTAMP:20250708T153951Z
CREATED:20250708T153951Z
LAST-MODIFIED:20250708T153951Z
UID:10000825-1752235200-1752238800@micde.umich.edu
SUMMARY:Frontiers in Scientific Machine Learning Seminar - Romit Maulik (Penn State University): SALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning
DESCRIPTION:Zoom link \nBio: Romit Maulik is an Assistant Professor in the College of Information Sciences and Technology at Pennsylvania State University (Penn State). He is also a co-hire in the Institute for Computational and Data Sciences at Penn State and a Joint Appointment Faculty at Argonne National Laboratory. He obtained his PhD in Mechanical and Aerospace Engineering at Oklahoma State University (in 2019) and was the Margaret Butler Postdoctoral Fellow (from 2019-2021) before becoming an Assistant Computational Scientist at Argonne National Laboratory (from 2021-2023). His group studies high-performance multifidelity scientific machine learning algorithm development with applications to various multiphysical nonlinear dynamical systems such as those that arise in fluid dynamics\, geophysical modeling\, nuclear fusion\, and beyond. He is an Early Career Awardee of the Army Research Office. \nSALSA-RL: Stability Analysis in the Latent Space of Actions for Reinforcement Learning\nAbstract: Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However\, real-world control systems–especially those requiring precise and reliable performance–often demand interpretability in the sense of a-priori assessments of agent behavior to identify safe or failure-prone interactions with environments. To address this limitation\, we propose SALSA-RL (Stability Analysis in the Latent Space of Actions)\, a novel RL framework that models control actions as dynamic\, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system\, our approach enables interpretability through local stability analysis\, where instantaneous growth in action-norms can be predicted before their execution. We demonstrate that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation\, SALSA-RL provides a powerful tool for advancing the design\, analysis\, and theoretical understanding of RL systems.
URL:https://micde.umich.edu/event/frontiers-in-scientific-machine-learning-seminar-romit-maulik-penn-state-university/
LOCATION:2004 Lay Auto Lab
CATEGORIES:Ai In Science And Engineering,Computational Modeling,Engineering,FSML,Graduate School,Interdisciplinary,North Campus,Research,Sciml,Statistics
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2025/07/Romit-Maulik-PennState-University.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20250620T120000
DTEND;TZID=America/Detroit:20250620T130000
DTSTAMP:20250620T145718Z
CREATED:20250619T132221Z
LAST-MODIFIED:20250620T145718Z
UID:10000823-1750420800-1750424400@micde.umich.edu
SUMMARY:Frontiers in Scientific Machine Learning Seminar - Pan Du (University of Notre Dame): Conditional neural field latent diffusion model for generating spatiotemporal turbulence
DESCRIPTION:Zoom link \nBio: Pan Du received his bachelor’s degree in Thermal Engineering from Tsinghua University and completed his master’s in Mechanical Engineering at Washington University in St. Louis. He is currently a Ph.D. candidate in Aerospace and Mechanical Engineering at the University of Notre Dame under the guidance of Prof. Jian-Xun Wang. Pan’s research spans multiple disciplines\, including scientific machine learning\, Bayesian inference\, uncertainty quantification\, geometric deep learning\, and computational fluid mechanics. \nConditional neural field latent diffusion model for generating spatiotemporal turbulence\nAbstract: Pan Du will present the CoNFiLD model\, a novel generative framework for simulating complex turbulent flows in 3D irregular domains. While traditional eddy-resolved simulations are accurate\, their high computational cost limits usability. CoNFiLD addresses this by integrating neural field encoding with latent diffusion\, enabling efficient\, probabilistic modeling of spatiotemporal dynamics. It supports a wide range of tasks—such as flow super-resolution\, sparse reconstruction\, and data restoration—via Bayesian conditional sampling\, all without retraining. Results across diverse turbulent scenarios highlight its potential for advancing data-driven turbulence modeling.
URL:https://micde.umich.edu/event/frontiers-in-scientific-machine-learning-seminar-pan-du-university-of-notre-dame/
LOCATION:GG Brown Laboratory – 1642
CATEGORIES:Ai In Science And Engineering,Computational Modeling,Engineering,FSML,Graduate School,Interdisciplinary,North Campus,Research,Sciml,Statistics
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2025/06/Pan-Du-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20250606T120000
DTEND;TZID=America/Detroit:20250606T130000
DTSTAMP:20250604T181957Z
CREATED:20250602T103951Z
LAST-MODIFIED:20250604T181957Z
UID:10000822-1749211200-1749214800@micde.umich.edu
SUMMARY:Frontiers in Scientific Machine Learning Seminar - Ashwin Renganathan (Penn State): Sample-efficient and Principled Decision-making  with Expensive Stochastic Oracles
DESCRIPTION:Zoom link \nBio: Ashwin Renganathan is an assistant professor of aerospace engineering at Penn State and holds a joint appointment with the Penn State Institute of Computational and Data Sciences (ICDS). He directs the Computational complex engineered Systems Design Laboratory (CSDL) at Penn State. He is broadly interested in developing novel and scalable computational techniques for surrogate modeling\, uncertainty quantification\, and numerical optimization\, with a focus on aerospace applications. He earned his Ph.D. in aerospace engineering from Georgia Tech and previously completed a postdoctoral appointment in applied mathematics at the Argonne National Laboratory. \nSample-efficient and Principled Decision-making with Expensive Stochastic Oracles\nAbstract: Modern day engineering decision-making involves one or more computer simulation oracles of an engineered system which can be queried on-demand to learn the system response to control input. Querying simulation oracles\, also called “computer experiments”\, incur a non-trivial computational cost\, which increases with the level of fidelity in the underlying models. For instance\, a realistic computational aerodynamic simulation of an aircraft can cost several thousands of CPU hours to compute—anything more than a few dozens of such simulations is prohibitive. Therefore\, a central goal of engineering decision-making is to optimally design computer experiments\, to maximize the value of information extracted at minimal computational effort.\nIn this talk\, we will address problems anchored in\, what we coin\, the “decision-making triad” which includes: surrogate modeling\, uncertainty quantification (UQ)\, and numerical optimization/control. Specifically\, using variants of a probabilistic surrogate model and a Bayesian decision theoretic framework\, we will show that problems in the decision-making triad can be solved in a principled\, theoretically sound and\, yet (computational) cost-effective manner. We will show demonstrations on applications in computational aerodynamics.
URL:https://micde.umich.edu/event/workshop-seminarfrontiers-in-scientific-machine-learning-seminar-15-ashwin-renganathan/
LOCATION:GG Brown Laboratory – 1642
CATEGORIES:Ai In Science And Engineering,Computational Modeling,Engineering,FSML,Graduate School,Interdisciplinary,North Campus,Research,Sciml,Statistics
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2025/06/MICDE-Seminar-Series-Speaker-Portraits-4.png
END:VEVENT
BEGIN:VEVENT
DTSTART;VALUE=DATE:20241018
DTEND;VALUE=DATE:20241019
DTSTAMP:20241008T155431Z
CREATED:20241003T220654Z
LAST-MODIFIED:20241008T155431Z
UID:10000775-1729209600-1729295999@micde.umich.edu
SUMMARY:SciML Lecture Series- Christopher Wentland: Domain decomposition and coupling data-driven models of fluid flows
DESCRIPTION:More details will be provided soon!
URL:https://micde.umich.edu/event/lecture-discussionsciml-lecture-series-2/
LOCATION:Venue TBA\, MI\, 48109\, United States
CATEGORIES:Micde,Sciml
GEO:42.3053253;-83.6694169
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20241004T120000
DTEND;TZID=America/Detroit:20241004T130000
DTSTAMP:20241104T140255Z
CREATED:20241002T220654Z
LAST-MODIFIED:20241104T140255Z
UID:10000774-1728043200-1728046800@micde.umich.edu
SUMMARY:FSML Lecture Series: Tokenization for Chemistry by Alex Wadell\, University of Michigan
DESCRIPTION:Alex Wadell is a PhD candidate at the University of Michigan Department of Mechanical Engineering. \nTokenization for Chemistry\nMolecular Foundation Models are emerging as a powerful tool for molecular design\, material science\, and cheminformatics. By leveraging the transformer architecture\, these models attempt to learn the language of chemistry and discover robust molecular embeddings. However\, current models are constrained by tokenizers that fail to capture the full breadth of chemical space or even the periodic table of elements. In his talk\, Alex will introduce smirk\, a new tokenizer for molecular foundation models that can represent the entirety of the OpenSMILES specification. We’ll also discuss performance metrics for tokenizers and the results of Alex’s systematic evaluation of thirteen chemistry-specific tokenizers using N-gram language models as a low-cost proxy for transformer models. \nIf you are unable to attend in person but are interested\, please feel free to join virtually. \nJoin Zoom Meeting\nhttps://umich.zoom.us/j/97823527756?pwd=H01BbvtuG5q02Wzb8LJvhUnvijlAIe.1\nMeeting ID: 978 2352 7756\nPasscode: 2024
URL:https://micde.umich.edu/event/lecture-discussionsciml-lecture-series/
LOCATION:Walter E Lay Auto Lab – 2052
CATEGORIES:FSML,Micde,Sciml
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2024/10/SciML-Lectures-e1727980667262.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20240708T090000
DTEND;TZID=America/Detroit:20240726T160000
DTSTAMP:20240611T125750Z
CREATED:20240611T033416Z
LAST-MODIFIED:20240611T125750Z
UID:10000684-1720429200-1722009600@micde.umich.edu
SUMMARY:SciFM24 Summer School
DESCRIPTION:The SciFM Summer School runs from July 8 to July 26. The first instance is going to be run in parallel at the University of Michigan (UM) and at Argonne National Laboratory (ANL). The focus will be on developing technical plans for specific instances for SciFMs\, a hackathon to jumpstart the construction of SciFMs\, as an incubator for ideas\, a training ground for researchers and students\, and further a vision for a national SciFM ecosystem.
URL:https://micde.umich.edu/event/workshop-seminarscifm24-summer-school/
CATEGORIES:Aerospace Engineering,College Of Engineering,Computational Science,Engineering,Micde,Scientific Computing,Sciml,Workshops
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2024/06/Untitled-design-1.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20240419T110000
DTEND;TZID=America/Detroit:20240419T120000
DTSTAMP:20240412T140752Z
CREATED:20240412T011911Z
LAST-MODIFIED:20240412T140752Z
UID:10000680-1713524400-1713528000@micde.umich.edu
SUMMARY:MICDE Fellowships Information Session
DESCRIPTION:Applications for the $4\,500 2024-2025 MICDE Graduate Fellowships will open May 1\, 2024. Please join this Zoom session to learn more about the fellowships and how to submit a great application! \nThese fellowships are sponsored by the Michigan Institute for Computational Discovery & Engineering. For more information\, see https://live-umor-micde.pantheonsite.io/academic-programs/fellowships/.
URL:https://micde.umich.edu/event/livestream-virtualmicde-fellowships-information-session/
LOCATION:Zoom Event
CATEGORIES:Aerospace Engineering,Ai In Science And Engineering,Astronomy,big data,Biomedical Engineering,Biosciences,Biostatistics,Chemical Engineering,Chemistry,Civil and Environmental Engineering,Climate and Space Sciences and Engineering,College Of Engineering,Complex Systems,Computation,Computational Modeling,Computational Science,Computational Social Science,computer science,Data Science,Earth And Environmental Sciences,Ecology,Ecology And Evolutionary Biology,Economics,Education,Electrical And Computer Engineering,Electrical Engineering and Computer Science,Engineering,Engineering Academic Calendar,Epidemiology,Evolutionary Biology,Fellowship,Free,Funding,Generative Ai,Graduate,Graduate and Professional Students,Graduate School,Graduate Students,Health Data,High Performance Computing,Industrial and Operations Engineering,Interdisciplinary,Kinesiology,Life Science,Lsaresearch,Machine Learning,Materials Science,Mathematics,Mechanical Engineering,Medicine,Micde,Natural Language Processing,Natural Sciences,Naval Architecture and Marine Engineering,Neuroscience,Nuclear Engineering and Radiological Sciences,parallel computing,Pharmacy,Physics,Politics,Prospective Graduate Students,Psychology,Public Health,Public Policy,Rackham,Research,Robotics,Scholarship,Science,Scientific Computing,Sciml,Sociology,Statistics,Virtual,Webcast,Workshops
ATTACH;FMTTYPE=image/png:https://micde.umich.edu/wp-content/uploads/2024/04/Fellowships-2024-info-session.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20231109T110000
DTEND;TZID=America/Detroit:20231109T130000
DTSTAMP:20231115T151403Z
CREATED:20231102T175811Z
LAST-MODIFIED:20231115T151403Z
UID:10000661-1699527600-1699534800@micde.umich.edu
SUMMARY:SciML Webinar: Lenz Fiedler - Efficient calculations of electronic structures with machine-learning models
DESCRIPTION:https://umich.zoom.us/j/95111677727?pwd=V1Q5MkUwT2NpOFVhd0ZRVGR1YTM3Zz09 \n\nSpeaker: Lenz Fiedler (Helmholtz-Zentrum Dresden-Rossendorf)\nSession Chair: Michael Herbst (EPFL) \nAbstract: Quantum mechanical calculations of the electronic structure of matter enable accessing interesting thermodynamical properties without the need for prior experimental measurements. Therefore\, electronic structure calculations are of great interest in fields such as materials discovery or drug design. At the forefront of such simulations lies density functional theory (DFT)\, due to its excellent balance between computational accuracy and efficiency. Yet\, as pressing environmental and social issues shift the research focus to increasingly complicated systems and conditions\, even the most efficient of DFT implementations are approaching their limitations in terms of computational feasibility. A possible route to enable more complex calculations lies with machine learning (ML)\, i.e.\, algorithms that are capable of capturing complicated relationships based on large amounts of data.\nIn this talk\, Lenz Fiedler will talk about current contributions of Center for Advanced Systems Understanding\, Helmholtz-Zentrum Dresden-Rossendorf (CASUS) w.r.t. building ML models that replace conventional DFT calculations. More precisely\, Lenz will talk about the current state of the Materials Learning Algorithms library (MALA)\, which allows easy training and inference for ML-DFT models that are developed by CASUS in cooperation with Sandia National Laboraties and Oak Ridge National Laboratory. In contrast to comparable frameworks\, MALA allows full access to the electronic structure of compounds\, including volumetric data as well as scalar quantities of interest\, such as energies. It will be shown how MALA models can operate efficiently across phase boundaries\, length scales and temperature ranges.
URL:https://micde.umich.edu/event/sciml-webinar-lenz-fiedler-efficient-calculations-of-electronic-structures-with-machine-learning-models/
CATEGORIES:Micde,Scientific Computing,Sciml,SciML Webinar Series,Webinar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20231026T110000
DTEND;TZID=America/Detroit:20231026T130000
DTSTAMP:20231107T231334Z
CREATED:20231017T170318Z
LAST-MODIFIED:20231107T231334Z
UID:10000658-1698318000-1698325200@micde.umich.edu
SUMMARY:SciML Webinar: Bowen Deng - CHGNet: pretrained universal interatomic potential to study electron coupled ionic systems.
DESCRIPTION:https://umich.zoom.us/j/95111677727?pwd=V1Q5MkUwT2NpOFVhd0ZRVGR1YTM3Zz09 \n\nSpeaker: Bowen Deng (UC Berkeley)\nSession Chair: Sakidja Ridwan (Missouri State University) \nAbstract: Large-scale simulations with complex electron interactions remain one of the greatest challenges for atomistic modeling. Although classical force fields often fail to describe the\ncoupling between electronic states and ionic rearrangements\, the more accurate ab-initio molecular dynamics suffers from computational complexity that prevents long-time and large-\nscale simulations\, which are essential to study technologically relevant phenomena. Our work presents the Crystal Hamiltonian Graph Neural Network (CHGNet)\, a graph-neural-\nnetwork-based machine-learning interatomic potential (MLIP) that models the universal potential energy surface. CHGNet is pretrained on the energies\, forces\, stresses\, and magnetic moments\nfrom the Materials Project Trajectory Dataset\, which consists of over 10 years of density functional theory calculations of ∼ 1.5 million inorganic structures. The explicit inclusion of\nmagnetic moments enables CHGNet to learn and accurately represent the orbital occupancy of electrons\, enhancing its capability to describe both atomic and electronic degrees of freedom.\nWe demonstrate several applications of CHGNet in solid-state materials and energy storage applications.
URL:https://micde.umich.edu/event/sciml-webinar-bowen-deng/
CATEGORIES:Micde,Scientific Computing,Sciml,SciML Webinar Series,Webinar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20231019T110000
DTEND;TZID=America/Detroit:20231019T130000
DTSTAMP:20231025T194805Z
CREATED:20230915T150343Z
LAST-MODIFIED:20231025T194805Z
UID:10000646-1697713200-1697720400@micde.umich.edu
SUMMARY:SciML Webinar Ji Qi: DImensionality-Reduced Encoded Clusters with sTratified (DIRECT) sampling for Robust Training of Machine Learning Interatomic Potentials
DESCRIPTION:https://umich.zoom.us/j/95111677727?pwd=V1Q5MkUwT2NpOFVhd0ZRVGR1YTM3Zz09 \n\nSpeaker: Ji Qi (UC San Diego and LLNL)\nSession Chair: Daniel Schwalbe-Koda (UC Los Angeles) \nAbstract: Machine learning interatomic potentials (MLIPs) enable accurate simulations of materials at scales beyond conventional first-principles approaches\, and they have played increasingly important roles in understanding and design of materials. However\, MLIPs are only as accurate and robust as the data they are trained on. In this seminar\, I will present DImensionality-Reduced Encoded Clusters with sTratified (DIRECT) sampling as an approach to select a robust training set of structures from a large and complex configuration space. By applying DIRECT sampling on the Materials Project relaxation trajectories dataset with over one million structures and 89 elements\, we develop an improved materials 3-body graph network (M3GNet) universal potential that extrapolate more reliably to unseen structures. We further show that molecular dynamics (MD) simulations with universal potentials such as M3GNet can be used in place of expensive ab initio MD to rapidly create a large configuration space for target materials systems. For demonstration\, we combined this scheme with DIRECT sampling to develop a reliable moment tensor potential for titanium hydrides without the need for iterative augmentation of training structures. \nIn this seminar\, I will walk through two Jupiter notebooks to showcase DIRECT sampling with the two example cases demonstrated in our manuscript\, so that audience can expect to reproduce our major results with no trouble. Hopefully\, DIRECT sampling will serve as a straightforward\, efficient\, useful plug-in for the robust training of MLIPs across any compositional complexity.
URL:https://micde.umich.edu/event/workshop-seminarsciml-webinar-ji-qi-2/
CATEGORIES:Micde,Scientific Computing,Sciml,SciML Webinar Series,Webinar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20231012T110000
DTEND;TZID=America/Detroit:20231012T130000
DTSTAMP:20231018T173554Z
CREATED:20230915T150330Z
LAST-MODIFIED:20231018T173554Z
UID:10000644-1697108400-1697115600@micde.umich.edu
SUMMARY:SciML Webinar Justin Beroz: A closed-form mathematical framework for modeling turbulent fluids
DESCRIPTION:Speaker: Justin Beroz (ReynKo Inc.) \n\nSession Chair: Varun Shankar (Physics Inverted Mataerials) \nAbstract: Despite significant advances over the past two centuries\, a complete general mathematical framework for turbulent fluid motion has yet to be put forth\, and remains the longest standing unsolved problem in classical physics. I will present such a framework\, which is based on constructing a spectral decomposition for the fluid’s kinetic energy from first principles. The approach departs from the usual Reynolds decomposition and yields a set of closed and solvable ordinary differential equations in matrix form. Within this prescription\, the linear terms in the Navier-Stokes equations correspond to a symmetric matrix operator\, and the nonlinear convective term enters as an anti-symmetric operator that provides coupling between eigenstates of turbulent fluctuation. Specifically\, I will present a derivation for the turbulent energy spectrum\, including the Kolmogorov energy cascade; elucidate instability mechanisms for the transition to turbulence;  and detail the analytical solution for turbulence in a box. Careful attention will be given to the physical picture and scaling\, in addition to the rigorous mathematical program. The talk will conclude with a forward look into current efforts implementing the model into a numerical simulation within my company\, ReynKo Inc.
URL:https://micde.umich.edu/event/workshop-seminarsciml-webinar-justin-beroz/
CATEGORIES:Micde,Scientific Computing,Sciml,SciML Webinar Series,Webinar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20231005T110000
DTEND;TZID=America/Detroit:20231005T123000
DTSTAMP:20231018T165056Z
CREATED:20230918T024126Z
LAST-MODIFIED:20231018T165056Z
UID:10000649-1696503600-1696509000@micde.umich.edu
SUMMARY:SciML Webinar: Jianke Yang - Generative Adversarial Symmetry Discovery
DESCRIPTION:Speaker: Jianke Yang (UC San Diego) \n\n\nSession Chair: Bharath Ramsundar (Deep Forest Sciences) \nAbstract:Despite the success of equivariant neural networks in scientific applications\, they require knowing the symmetry group a priori. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivariance from data.  We propose a framework\, LieGAN\, to automatically discover equivariances from a dataset using a paradigm akin to generative adversarial training. Specifically\, a generator learns a group of transformations applied to the data\, which preserves the original distribution and fools the discriminator. LieGAN represents symmetry as an interpretable Lie algebra basis and can discover various symmetries such as the rotation group and the restricted Lorentz group in trajectory prediction and top-quark tagging tasks. More generally\, LieGAN can also be extended to discover the nonlinear symmetries in high-dimensional dynamics. The learned symmetry can be readily used in several existing equivariant neural networks to improve prediction accuracy and generalization. It can also improve the symbolic equation discovery and long-term forecasting for various dynamical systems. \n\n\n 
URL:https://micde.umich.edu/event/sciml-webinar-jianke-yang-generative-adversarial-symmetry-discovery/
CATEGORIES:Sciml,SciML Webinar Series
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Detroit:20230928T110000
DTEND;TZID=America/Detroit:20230928T123000
DTSTAMP:20231018T163755Z
CREATED:20230918T023335Z
LAST-MODIFIED:20231018T163755Z
UID:10000648-1695898800-1695904200@micde.umich.edu
SUMMARY:SciML Webinar: Bob Carpenter - Multiscale Generalized Hamiltonian Monte Carlo with Delayed Rejection
DESCRIPTION:Speaker: Bob Carpenter (Flatiron Institute) \n\n\nSession Chair: Sam Livingstone (University College London) \n\n\nAbstract: In this talk\, I will demonstrate how we can combine two ideas\, generalized Hamiltonian Monte Carlo and delayed rejection\, to derive a sampler that is as efficient as Hamiltonian Monte Carlo\, but is able to adapt its step size to deal with multiscale distributions\, much like a standard integrator for ordinary differential equations. A distribution is multiscale if its curvature has different scales in the posterior; a textbook example is Radford Neal’s funnel example derived from hierarchical priors\, which has a very flat mouth (corresponding to high population variance) and very highly curved neck (low population variance). No fixed step size allows exploration of its posterior. Generalized HMC allows us to take a single Hamiltonian step along the gradient at a time (which is equivalent to Metropolis-adjusted Langevin dynamics)\, but only refresh momentum partially (which makes it underdamped). The naive form of this algorithm does not work because momentum must be reversed to maintain detailed balance if the Metropolis step rejects. To maintain directed exploration\, we apply delayed rejection\, which allows a proposal rejected due to divergence of the Hamiltonian (from too large a step size in the first-order approximation of the dynamics) to be retried with a smaller step size (with a Hastings-style adjustment for the retry). We show that the combination of delayed rejection and GHMC allows sampling multiscale distributions which otherwise lead to biased samples in standard Hamiltonian Monte Carlo (including dynamic forms such as the no-U-turn sampler). In conclusion\, I will discuss some preliminary work on applying the the automatic tuning method using complementary parallel chains developed by Matt Hoffman and Pavel Sountsov for their sampler MEADS (which also uses generalized HMC\, but with an alternative approach to maintaining directed exploration based on work of Radford neal\, which will also describe). \n\nSlides: https://statmodeling.stat.columbia.edu/wp-content/uploads/2023/09/carpenter-sciml-webinar-2023.pdf
URL:https://micde.umich.edu/event/sciml-webinar-bob-carpenter-multiscale-generalized-hamiltonian-monte-carlo-with-delayed-rejection/
CATEGORIES:Sciml,SciML Webinar Series
END:VEVENT
END:VCALENDAR