Solar forecasting by physical modeling integrated with machine learning
Hybridization of solar, wind and geothermal
Cost effective large-scale energy storage
Extracting food, energy and clean water from the Earth’s limited resources and land area while mitigating climate change and reducing pollution is essential but challenging. In REALab, we are dedicated to explore the science and develop technologies to utilize renewable energy efficiently. To improve solar power integration, we develop high fidelity solar power forecasting models by integrating spectral atmospheric radiative transfer, physics-based estimation of cloud optical properties from cutting-edge remote sensing data (e.g., GOES satellite imaging) and machine learning techniques. To improve the grid penetration of renewable power, we research novel large-scale thermal and chemical energy storage, hybridization of different renewable sources for power production and solar-driven passive cooling and desalination.
Please forward all inquiries to Dr. Li at firstname.lastname@example.org.
Energy Meteorology, Solar Resourcing and Forecasting, Renewable Power Systems with Passive Cooling and Desalination, Thermal Storage
Multienergy complementation system, Solar thermal power system design and optimization, Load forcasting, Comprehensive energy system optimization
Machine Learning and Deep Learning, Convolutional and Recurrent Neural Network, Image classification and segmenation, Feature Engineering
Photovoltaics solar cells, Solar energy materials and their characterizations, Semiconductor device physics, Electrical characterization
Heat and Mass transfer, CFD, CO2 capture, PV/CSP hybrid block transients
Renewable Energy Systems, Solar Resourcing and Forecasting, Life Cycle Analysis in Energy Systems, Machine Learning
Robotics and Controls, Solar Resourcing, Advanced Material and Structural Design, Metal Material
Renewable Energy Systems, Thermal Energy Storage, Heat Transfer, Computational Fluid Dynamics