Skip to main content
U.S. flag

An official website of the United States government

Scott Hamshaw, Ph.D., P.E.

Scott Hamshaw, Ph.D., P.E. is a Machine Learning Specialist in the Analysis & Prediction Branch of the USGS Water Resources Mission Area. 

Scott Hamshaw received his Ph.D. in Civil & Environmental Engineering from the University of Vermont where he undertook mapping of watershed erosion and data-driven modeling of sediment transport in the Lake Champlain Basin. After completing his Ph.D., he was a postdoctoral associate and research assistant professor at the University of Vermont applying machine learning to water resource problems as well as teaching land surveying and mapping. Prior to his Ph.D., Scott worked as a consulting engineer in Burlington, VT practicing stormwater management, water system design, and site engineering. Scott joined the Analysis & Prediction Branch of the Water Resources Mission Area in 2021 and is based in Bristol, VT.   

Scott’s interests are in the broad area of applied machine learning and water resource engineering with emphasis on using data-driven approaches to understand dynamics in streamflow and river water quality. Scott is active in national-scale research on applying deep learning methods to the prediction of water quantity and quality in rivers across the U.S.   

Professional Experience

  • Machine Learning Specialist, U.S. Geological Survey, Water Mission Area - 2021 to present

  • Research Assistant Professor, Civil & Environmental Engineering, University of Vermont - 2019 to 2021

  • Post-Doctoral Associate, Vermont EPSCoR, University of Vermont - 2017 to 2019

  • Research Assistant, Civil & Environmental Engineering, University of Vermont - 2011 to 2017

  • Staff Engineer, Engineered Solutions, Inc., Burlington, VT - 2007 to 2010

Education and Certifications

  • Ph.D. Civil & Environmental Engineering, University of Vermont, 2018

  • P.E., State of Vermont, License No. 100919, 2015

  • M.S. Civil & Environmental Engineering, University of Vermont, 2014

  • B.A. Engineering, St. Michael's College, 2006

  • B.S. Civil Engineering, University of Vermont, 2006

Science and Products

Preliminary streamflow percentile predictions for ungaged areas of the Colorado River Basin, 1981-2020

This dataset consists of daily streamflow percentiles for 1981-10-01 to 2020-03-31 relevant to streamflow drought defined using two approaches: Percentiles accounting for flow seasonality (variable threshold percentiles) and those based on the full record of data for each site regardless of season (fixed threshold percentiles). Because of the size of this dataset (99,530,836 rows), it could not be
By
Maryland-Delaware-D.C. Water Science Center

Data-Driven Drought Prediction Project Model Outputs for Select Spatial Units within the Conterminous United States

This metadata record describes model outputs and supporting model code for the Data-Driven Drought Prediction project of the Water Resources Mission Area Drought Program. The data listed here include outputs of multiple machine learning model types for predicting hydrological drought at select locations within the conterminous United States. The child items referenced below correspond to different
By
Water Resources Mission Area

Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations

Deep learning (DL) models are increasingly used to forecast water quality variables for use in decision making. Ingesting recent observations of the forecasted variable has been shown to greatly increase model performance at monitored locations; however, observations are not collected at all locations, and methods are not yet well developed for DL models for optimally ingesting recent observations
Authors
Jacob Aaron Zwart, Jeremy Alejandro Diaz, Scott Douglas Hamshaw, Samantha K. Oliver, Jesse Cleveland Ross, Margaux Jeanne Sleckman, Alison P. Appling, Hayley Corson-Dosch, Xiaowei Jia, Jordan S Read, Jeffrey M Sadler, Theodore Paul Thompson, David Watkins, Elaheh (Ellie) White
By
Science Synthesis, Analysis and Research Program, Advanced Research Computing (ARC)

Regional streamflow drought forecasting in the Colorado River Basin using Deep Neural Network models

Process-based, large-scale (e.g., conterminous United States [CONUS]) hydrologic models have struggled to achieve reliable streamflow drought performance in arid regions and for low-flow periods. Deep learning has recently seen broad implementation in streamflow prediction and forecasting research projects throughout the world with performance often equaling or exceeding that of process-based mode
Authors
Scott Douglas Hamshaw, Phillip J. Goodling, Konrad Hafen, John C. Hammond, Ryan R. McShane, Roy Sando, Apoorva Ramesh Shastry, Caelan E. Simeone, David Watkins, Elaheh (Ellie) White, Michael Wieczorek
By
Ecosystems Mission Area, Water Resources Mission Area, Climate Research and Development Program, Idaho Water Science Center, Oregon Water Science Center, Wyoming-Montana Water Science Center

Non-USGS Publications**

Burberry, C. M., Flatley, A., Gray, A., Guilinger, J., Hamshaw, S., Hill, K., et al. (2022). Earth and Planetary Surface Processes Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science. Earth and Space Science, 9(8).
Hamshaw, S. D., Dewoolkar, M. M., Schroth, A. W., Wemple, B. C., & Rizzo, D. M. (2018). A New Machine‐Learning Approach for Classifying Hysteresis in Suspended‐Sediment Discharge Relationships Using High‐Frequency Monitoring Data. Water Resources Research, 54(6), 4040–4058.
Javed, A., Hamshaw, S. D., Lee, B. S., & Rizzo, D. M. (2021). Multivariate event time series analysis using hydrological and suspended sediment data. Journal of Hydrology, 593, 125802.

**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.

Science and Products

Preliminary streamflow percentile predictions for ungaged areas of the Colorado River Basin, 1981-2020

This dataset consists of daily streamflow percentiles for 1981-10-01 to 2020-03-31 relevant to streamflow drought defined using two approaches: Percentiles accounting for flow seasonality (variable threshold percentiles) and those based on the full record of data for each site regardless of season (fixed threshold percentiles). Because of the size of this dataset (99,530,836 rows), it could not be
By
Maryland-Delaware-D.C. Water Science Center

Data-Driven Drought Prediction Project Model Outputs for Select Spatial Units within the Conterminous United States

This metadata record describes model outputs and supporting model code for the Data-Driven Drought Prediction project of the Water Resources Mission Area Drought Program. The data listed here include outputs of multiple machine learning model types for predicting hydrological drought at select locations within the conterminous United States. The child items referenced below correspond to different
By
Water Resources Mission Area

Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations

Deep learning (DL) models are increasingly used to forecast water quality variables for use in decision making. Ingesting recent observations of the forecasted variable has been shown to greatly increase model performance at monitored locations; however, observations are not collected at all locations, and methods are not yet well developed for DL models for optimally ingesting recent observations
Authors
Jacob Aaron Zwart, Jeremy Alejandro Diaz, Scott Douglas Hamshaw, Samantha K. Oliver, Jesse Cleveland Ross, Margaux Jeanne Sleckman, Alison P. Appling, Hayley Corson-Dosch, Xiaowei Jia, Jordan S Read, Jeffrey M Sadler, Theodore Paul Thompson, David Watkins, Elaheh (Ellie) White
By
Science Synthesis, Analysis and Research Program, Advanced Research Computing (ARC)

Regional streamflow drought forecasting in the Colorado River Basin using Deep Neural Network models

Process-based, large-scale (e.g., conterminous United States [CONUS]) hydrologic models have struggled to achieve reliable streamflow drought performance in arid regions and for low-flow periods. Deep learning has recently seen broad implementation in streamflow prediction and forecasting research projects throughout the world with performance often equaling or exceeding that of process-based mode
Authors
Scott Douglas Hamshaw, Phillip J. Goodling, Konrad Hafen, John C. Hammond, Ryan R. McShane, Roy Sando, Apoorva Ramesh Shastry, Caelan E. Simeone, David Watkins, Elaheh (Ellie) White, Michael Wieczorek
By
Ecosystems Mission Area, Water Resources Mission Area, Climate Research and Development Program, Idaho Water Science Center, Oregon Water Science Center, Wyoming-Montana Water Science Center

Non-USGS Publications**

Burberry, C. M., Flatley, A., Gray, A., Guilinger, J., Hamshaw, S., Hill, K., et al. (2022). Earth and Planetary Surface Processes Perspectives on Integrated, Coordinated, Open, Networked (ICON) Science. Earth and Space Science, 9(8).
Hamshaw, S. D., Dewoolkar, M. M., Schroth, A. W., Wemple, B. C., & Rizzo, D. M. (2018). A New Machine‐Learning Approach for Classifying Hysteresis in Suspended‐Sediment Discharge Relationships Using High‐Frequency Monitoring Data. Water Resources Research, 54(6), 4040–4058.
Javed, A., Hamshaw, S. D., Lee, B. S., & Rizzo, D. M. (2021). Multivariate event time series analysis using hydrological and suspended sediment data. Journal of Hydrology, 593, 125802.

**Disclaimer: The views expressed in Non-USGS publications are those of the author and do not represent the views of the USGS, Department of the Interior, or the U.S. Government.