News & Events

• Graduate students at Qizhi's home, 11/23/2024

Updates in ASME's International Mechanical Engineering Congress & Exposition (IMECE) 2024 in Portland, OR.

Presentations
Our group was involved in two presentations on advancing differentiable mechanics: 
- "A Neural Network-Enhanced Differentiable Meshfree Method for Computational Mechanics" Contributors: Honghui Du, Binyao Guo
- "Neural Topology Optimization Based on Differential Programming with Principled Constrained Optimization" Contributors: Ryan Devera (Computer Science & Engineering) and Binyao Guo

Committees
Dr. He served on the ASME AI/Deep Learning Best Paper Honors Committee, and joined the IMECE Fracture and Fatigue Mechanics Technical Committee (FFMTC)

Awards
Honghui received the ASME Applied Mechanics Division's Robert M. and Mary Haythornthwaite Foundation Student Travel Award for the work on "Neural-Integrated Meshfree Method for computational mechanics". Congratulations!

I was pleased to share our recent research on Differentiable Solid Mechanics and Geophysics with students and colleagues during my visit to Singapore in September. The talk was titled "Neural-Integrated and Data-Driven Approaches for Computational Modeling in Solid Mechanics and Geophysics." I am grateful for the warm invitations from NUS, NTU and A*STAR.

• ME Department Seminar, National University of Singapore (NUS)
• iHPC Seminar, Agency for Science, Technology and Research (A*STAR)
• CEE Department Seminar, Nanyang Technological University (NTU)

Talk (12/2023): Our group, InCOME, will be contributing 4 presentations at AGU Annual Meeting 2023, 11-15 December. If you are interested in our work, please check out our talks and posters (focusing on hybrid scientific machine learning, geophysics and geomechanics, subsurface transport, carbon sequestration, and ice-sheet modeling). 

H13L-1610: Poster - Generating the digital twin of discontinuous reservoirs with monitoring data in real time (Qiao et al.;  2:10pm - 6:30pm PST, Mon, Dec 11, Board 1610‚ Poster Hall A-C - South - MC)

MR13B-0052: Poster - Measuring the mechanical property of planetary rocks at grain- and macro-scale using miro-RME and AGBM (Zhang et al.;  2:10pm - 6:30pm PST, Mon, Dec 11, Board 0052‚ Poster Hall A-C - South - MC)

H31H-08: Oral (Virtual) - Physics-informed hybrid learning for subsurface transport and its application to geological sequestration (Honghui Du, Zihan Lin, QiZhi He;  9:40am - 9:50am, Wed, Dec 13, MC - 3005 - West)

C41A-05: Invited Oral - Machine Learning modeling for accelerated uncertainty quantification in projections of ice sheets' mass change (Perego, He, et al.; 9:10am - 9:20am, Thu, Dec 14, MC - 2005 - West)

Paper (04/2023): Congratulations to Honghui for publishing a paper titled "Modeling density-driven flow in porous media by physics-informed neural networks for CO2 sequestration" in Computers and Geotechnics. In collaboration with the UIUC's team, this study aims at exploring the application of deep learning approach in predicting the flow and transport behavior during CO2 injection, with providing a detailed comparison to the classic FEM numerical solver. More details can be found in: https://authors.elsevier.com/a/1gsEh,63b-0Miq.

Our paper "Physics-informed neural networks of the Saint-Venant equations for downscaling a large-scale river model" by Dongyu Feng (PNNL), Zeli Tan (PNNL) & QiZhi He (UMN) is accepted for publication in Water Resources Research.

Talk (December, 2022) Dr. He gave a seminar talk about Reduced Order Modeling and Physics-Constrained Deep Surrogate Model at University of Illinois Urbana-Champaign.

Conference (December 12-15, 2022) We have two collaborative studies presented in AGU Fall Meeting 2022, Chicago. 

• Physics-Informed Neural Network Method for Parabolic Differential Equations with Sharply Perturbed Initial Conditions
• Solving River Dynamics at the River-ocean Interface using a Physics-informed Deep Learning Based Data Assimilation Approach

Event: We are organizing a symposiums titled "Data-Driven Approaches and Digital Twins for Solid and Geological Mechanics" in Engineering Mechanics Institute Conference (EMI) 2023. You are invited to submit abstracts to the mini-symposium MS704 at https://emi-conference.org/call-abstracts/list-mini-symposia

Talk (November, 2022) Honghui presented his recent studies on "efficient meshfree method and CO₂ density-driven flow modeling by using physics-informed neural networks" in the Structures Seminar at the Department of Civil, Environmental, ang Geo- Engineering.

In the same week, Dr. He gave a talk titled "Data-Assisted Computational Mechanics: From Reduced Order Modeling to Physics-Constrained Deep Surrogate Model" in Solid Mechanics Research Seminar at the Department of Aerospace Engineering and Mechanics.

Event (November, 2022) We are organizing two symposiums on Data-Driven Computational Solid Mechanics and Data-Driven Additive Manufacturing in the 17^th U.S. National Congress on Computational Mechanics (USNCCM) at Albuquerque, New Mexico, July 23-27, 2023 (https://17.usnccm.org/). Welcome to submit abstracts to the following two MS before Jan 15^th, 2023. 

MS 413 Data-Driven Computational Solid and Geological Mechanics
Qizhi He (UMN), WaiChing Sun (Columbia), Jiun-Shyan Chen (UCSD), Xiaolong He (ANSYS)

MS 605 Physics-Based and Data-Driven Solutions for Additive Manufacturing 
Lin Cheng (WPI), Jinhui Yan (UIUC),  Miguel Bessa (Brown),  Qizhi He (UMN)

News (August, 2022) Dr. He was appointed as the CTS Faulty Scholar of the Center for Transportation Studies. He also recently joined the organizer team for the "CSE DSI Machine Learning Seminar Series sponsored by the College of Science and Engineering.