Scientist at Los Alamos National Laboratory

About Me

Wenting Li is a Scientist at Los Alamos National Laboratory (LANL). She was a postdoc research associate of Center for Nonlinear Study and Theory-5 Division at LANL from 2020 to 2023. She obtained the Ph.D. degree in Electrical Computer and System Engineering (ECSE) and Master degree in Applied Mathematics at the Rensselaer Polytechnics Institute (RPI) in Dec. 2019. Her supervisor is Prof. Meng Wang. Her doctoral thesis is about developing machine/deep learning based algorithms to enhancing power systems monitoring and protection. Before she came to RPI in 2015, she worked as a research assistant in the Wind Farm Research Center (WFRC) at Shanghai Jiao Tong University (SJTU) under the supervison of Prof. Xu Cai. In 2013, she received her B.S. degree in Elcetrical Engineering and Automation from Harbin Institute of Technology (HIT).

News

  • 04/05/2023: Talk on “Physics-Informed Machine Learning for Enhancing Robustness and Verification” at NASPI Workshop and Vendor Show
  • 03/22/2023: Give a talk on “Physics-Preserved Graph Learning for Robust Fault Location in Distribution Systems” at Huston University
  • 02/2022: Our paper of “Physics-Constrained Adversarial Training for Neural Networks in Stochastic Power Grids” is accepted by Transaction on Artificial Intelligence.
  • 02/13/2023: My co-worker Krishnamurthy (Dj) Dvijotham presented presents our research on “Physics-Constrained Interval Bound Propagation for Robustness Verifiable Neural Networks in Power Grids” at AI for Energy Innovation held in conjunction with 37th AAAI Conference on Artificial Intelligence.
  • 01/03/2022: My co-worker Deepjyodi Deka presents our paper “PPGN: Physics-Preserved Graph Networks for Real-Time Fault Location in Distribution Systems with Limited Observation and Labels” on Hawaii International Conference on System Sciences (HICSS) conference.
  • 7/1/2022: Organize the 4-week Physics-Informed Machine Learning Training at LANL
  • 03/11/2021: Talk on a latest paper on neural networks verification for the optimization machine learning (OPTML) reading group.
  • 02/24/2021: A lighting talk for the DisrupTech: Robust fault location through graph-based learning at low label rates
  • 08/03/2020: Big Data Analytics Sessions during the 2020 PES general meeting : Identifying Overlapping Successive Events Using a Shallow Convolutional Neural Network here
  • 07/14/2020: Los Alamos National Laboratory Postdoc Seminar: Physics-informed Neural Networks for High Impedance Fault Detection.
  • 11/01/2019: CURENT Power and Energy Seminar: Real-time and Agile Data-driven Approaches Enabling Power Grids to be Smart. here

Research interests

  • Physics-informed machine learning
  • Graph learning and graph neural networks
  • Robust optimization and verified neural networks
  • Feature extraction from high-dimensional data
  • Deep learning models Design (CNN, RNN, LSTM, Autoencoder)