DAN LU, PH.D.
Dr. Dan Lu is a Senior Staff Scientist in Computational Earth Sciences Group at Oak Ridge National Laboratory (ORNL). She earned her Ph.D. in Computational Hydrology at Florida State University in 2012, and joined ORNL in 2013 after one-year postdoctoral appointment at the U. S. Geological Survey. Her research interest includes machine learning, uncertainty quantification, surrogate modeling, inverse modeling, sensitivity analysis; experimental design, and numerical simulations in earth, climate, and environment sciences. She is leading several ML related projects funded by different programs across U.S. Department of Energy. She is currently serving as an Associate Editor of the journal Artificial Intelligence for the Earth Systems, an Associate Editor of the journal Frontiers in Water, and a Topic Editor of the journal Geoscientific Model Development. Dan authored more than 70 publications and co-developed two softwares. She won the Department of Energy Early Career Award in 2023.
Email: lud1@ornl.gov, ORNL webpage: Staff information
Recent News
[2023/11] Dan gave a presentation on AI foundation model for climate at Supercomputing Conference.
[2023/10] Dan's project on UQ for ML won the Most Exciting Future Direction Award.
[2023/09] Dan gave an invited talk at ORNL-Vanderbilt University Collaborative Workshop.
[2023/08] Dan received Department of Energy Early Career Award with $2.5M for 5 years.
[2023/07] Our paper titled Uncertainty quantification of machine learning-based permeability estimation from rock images is published in Geoenergy Science and Engineering.
[2023/05] Dan gave a seminar at technical meeting with Air Force on Machine learning to advance Earth system predictability.
[2023/04] Our paper titled Uncertainty Quantification of Machine Learning Models to Improve Streamflow Prediction in Changing Climate and Environmental Conditions is published in Frontiers in Water.
[2023/02] Dan gave a seminar at Florida State University on Machine Learning in Earth System Modeling.
[2023/01] Our paper titled A deep learning-based direct forecasting of CO2 plume migration is published in Geoenergy Science and Engineering.
[2022/12] Our paper titled A Spatiotemporal-Aware Climate Model Ensembling Method for Improving Precipitation Predictability is published in Journal of Machine Learning in Modeling and Simulation.
[2022/11] Our research team has two papers accpeted in IEEE International Conference in Data Mining DMESS workshop.
[2022/09] Our proposal titled An Uncertainty-Aware, Machine Learning-Enabled Hydropower Seasonal Forecast Model, has beed funded by Water Power Technologies Office in Department of Energy (DOE).
[2022/09] Our proposal titled Uncertainty Quantification Methods for Machine Learning Models, has beed funded by ORNL LDRD program.
[2022/08] Our paper titled Exploiting the local parabolic landscapes of adversarial losses to accelerate black-box adversarial attack, has been accepted by European Conference on Computer Vision (ECCV), 2022.
[2022/04] Our paper titled PI3NN: Out-of-distribution-aware prediction intervals from three neural networks, has been accepted by International Conference on Learning Representations (ICLR), 2022.
[2022/03] We successfully delivered our SMARTA Phase I project and moved to Phase II with $550K/year for FY22-FY27 funded by Office of Fossil Energy and Carbon Management in DOE.
[2022/03] Our paper titled Invertible neural networks for E3SM land model calibration and simulation, has been accepted by ICLR AI for Earth and Space Sciences, 2022.
[2022/03] Our paper titled An interpretable machine learning model for advancing terrestrial ecosystem predictions, has been accepted by ICLR AI for Earth and Space Sciences, 2022.
[2022/03] Our paper titled Multimodel ensemble predictions of precipitation using Bayesian neural networks, has been accepted by ICLR AI for Earth and Space Sciences, 2022.
[2021/12] Our paper titled Machine learning-enabled model-data integration for predicting subsurface water storage, has been accepted by NeurIPS Tackling Climate Change with Machine Learning, 2021.
[2021/12] Our paper titled Accurate and timely forecasts of geologic carbon storage using machine learning methods, has been accepted by NeurIPS Tackling Climate Change with Machine Learning, 2021.
[2021/12] Dr. Ming Fan joined our research team as a postdoc.
[2021/01] Dr. Siyan Liu joined our research team as a postdoc.
Research Overview
Machine Learning (ML) and Uncertainty Quantification (UQ) for Earth System Modeling