I am Minglang Yin. I am a Postdoc Fellow in the Department of Biomedical Engineering, Johns Hopkins University. I am working with Prof.Natalia Traynova on developing machine learning model for cardiovascular diseases. I finished my Ph.D. degree with Prof. George Em Karniadakis and the title of my thesis is Hybrid Computational-Machine Learning Models with Uncertainty Quantification for Aortic Dissection.
My research interests are on developing mechanistic models and scientific machine learning for diagnosis and prognosis of diverse cardiovascular diseases. I am also interested in cardiovascular biomechanics, computational mechanics, and uncertainty quantification.
- (Aug. 2022) I start my new position as a postdoc in the department of biomedical engineering, Johns Hopkins University.
- (Jul. 2022) I have my thesis defense in late July, 2022.
- (Jun. 2022) Glad to present our works at USNC/TAM 2022 in Austin!
- (Mar. 2022) Check out our new CMAME paper of interfacing finite elements with neural operators! Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
- (Mar. 2022) Check out our CMAME paper, A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
- (Feb. 2022) A new neural operator for simulating aortic dissection, Simulating progressive intramural damage leading to aortic dissection using DeepONet: an operator–regression neural network
- (Jan. 2022) Invited talk, Department of Biomedical Engineering, Johns Hopkins University, Multiscale Modeling and Machine Learning for Biomedicine
- (Jan. 2022) Finalist of the Distinguished Fellows Position, Department of Biomedical Engineering, Johns Hopkins University
- (Jan. 2022) Our new paper of PINNs for fluid mechanics, Physics-informed neural networks (PINNs) for fluid mechanics: A review
- (Oct. 2021) Conference Presentation: 2021 IACM Computational Fluids Conference, Imaging-Driven Inference of Biomaterial Properties with Physics-Informed Neural Networks
- (Aug. 2021) Invited talk: Northwestern Polytechnical University, Physics-Informed Machine Learning and its Application in Multiscale Modeling
- (Aug. 2021) Invited talk: Parallel-in-Time (PinT) Workshop Time parallel in PDEs using machine learning tools
- (Jan. 2021) New paper Multiscale Parareal Algorithm for Long-Time Mesoscopic Simulations of Microvascular Blood Flow in Zebrafish
- (Oct. 2020) New paper Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
- (May. 2020) New paper Non-invasive Inference of Thrombus Material Properties with Physics-informed Neural Networks