R&D

Academic Research

Upstream Tech’s research & development efforts are dedicated to advancing the state of technology for watershed management and conservation.

We publish our research findings because we believe that openness, transparency, and collaboration are required to tackle our pressing climate challenges. We welcome continued discussion on these topics: if you would like to learn more about our research please contact us at team@hydroforecast.com.

Director of Research Dr. Grey Nearing leads our R&D team in incorporating new findings that drive innovation in HydroForecast™ and the field of machine learning-based hydrology at large.

Dr. Grey Nearing is Director of Research at Upstream Tech. He completed his Ph.D. in Hydrology in 2013 and has extensive experience with hydrological model evaluation, benchmarking, process-diagnostics, and uncertainty quantification. Grey has over forty peer-reviewed journal articles and book chapters in the field of hydrological modeling and uncertainty quantification, and has given over a dozen invited talks at universities and major international society meetings (EGU, AGU, AMS, SSSA, and others). Grey also holds an appointment as an Assistant Professor at the University of Alabama in the Geological Sciences Department where his research focuses on large-scale hydrological modeling, model/data fusion, and the use of remote sensing and other types of hydrologic observations to improve hydrology models.

Published Papers

View on AGU Publications

Toward Improved Predictions in Ungauged Basins: Exploiting the Power of Machine Learning

Water Resources Research (2019)

Authors: Frederik Kratzert, Daniel Klotz, Mathew Herrnegger, Alden K. Sampson, Sepp Hochreiter, Grey S. Nearing

Preprints

View on EarthArXiv

A note on leveraging synergy in multiple meteorological datasets with deep learning for rainfall-runoff modeling

Under review (2020)

Authors: Frederik Kratzert, Daniel Klotz, Sepp Hochreiter, and Grey S. Nearing


View on EarthArXiv

What Role Does Hydrological Science Play in the Age of Machine Learning? Under review (2020)

Authors: Grey S. Nearing, Frederik Kratzert, Alden Keefe Sampson, Craig S. Pelissier, Daniel Klotz, Jonathan M. Frame, Cristina S. Prieto, Hoshin V. Gupta

Conference Proceedings

View on EGU 2020

Machine Learning is Central to the Future of Hydrological Modeling

Conference: European Geosciences Union (May 2020)

Authors: Grey Nearing, Frederik Kratzert, Craig Pelissier, Daniel Klotz, Jonathan Frame, Hoshin Gupta


View on EGU 2020

Forecasting Seasonal Streamflow Using a Stacked Recurrent Neural Network

Conference: European Geosciences Union (May 2020)

Authors: David Lambl, Dan Katz, Eliza Hale, and Alden Sampson


View on IGARSS 2020

Combining Parametric Land Surface Models with Machine Learning

Conference: International Geoscience and Remote Sensing Symposium (IGARSS) (February 2020)

Authors: Craig Pelissier, Jonathan Frame, Grey Nearing


View on AGU 2019

Industry and Academic Collaboration to Advance Adoption of Machine Learning Hydrology

Conference (Invited): American Geophysical Union (December 2019)

Authors: Alden Keefe Sampson, Grey Stephen Nearing, Frederik Kratzert, Marshall Moutenot


View on NeurIPS

Using LSTMs for climate change assessment studies on droughts and floods

Conference: 33rd Conference on Neural Information Processing Systems (NeurIPS): Workshop on Tackling Climate Change with Machine Learning (November 2019)

Authors: Frederik Kratzert, Daniel Klotz, Johannes Brandstetter, Pieter-Jan Hoedt, Grey Nearing, Sepp Hochreiter