Dr. Kristen Schell

Dr. Schell's research develops mathematical models that inform the energy transition. She works at both the generation level, improving wind energy resource assessment and forecasting, and at the systems level, designing adaptable microgrids that can respond to future climate events. Methodologically, she has contributed to advancing spatio-temporal statistical forecasting models, deep learning architectures and energy system network optimization. These models are informed by large, empirical data from wind power producers, electric utilities, independent system operators and numerical weather prediction models. Her doctoral degrees are from the Engineering and Public Policy programs at Carnegie Mellon University and the Faculty of Engineering of the University of Porto, Portugal. She holds a Master's of Science in Environmental Engineering from Johns Hopkins University, and a Bachelor of Science degree in Chemical Engineering from Carnegie Mellon University, with an additional major in Engineering and Public Policy.

['Yang, H., Schell, K.R. ATTnet: An Explainable Gated Recurrent Unit Neural Network for High Frequency Electricity Price Forecasting. International Journal of Electrical Power and Energy Systems. July 2024. https://www.sciencedirect.com/science/article/pii/S0142061524001960', 'Arrieta-Prieto, M. and Schell, K.R. Spatially transferable machine learning wind power prediction models: logit random forests. Renewable Energy. March 2024. https://doi.org/10.1016/j.renene.2024.120066', 'Arwa, E. and Schell, K.R. Batteries or Silos: Optimizing Storage Capacity in Direct Air Capture Plants to Maximize Renewable Energy Use. Applied Energy. February 2024. https://www.sciencedirect.com/science/article/pii/S0306261923017099', 'Owusu-Obeng, P.Y. and Schell, K.R. Bi-level goal programming model for simult