Skip to main content
U.S. flag

An official website of the United States government

Jared Smith

Jared D. Smith, Ph.D., is a Machine Learning Specialist in the USGS Water Resources Mission Area. He is based in Reston, VA.

Jared has a background in environmental systems engineering, spatial data analysis, and statistics. His previous research has coupled physical and mathematical models with statistical analyses to inform planning and management decisions for environmental, earth-energy, and water resources systems. Jared joined the USGS in 2021 after completing a postdoc at The University of Virginia, where he developed green infrastructure portfolio optimizations that were designed to be robust to Bayesian-estimated parametric uncertainty of a watershed model. Jared completed his Ph.D. at Cornell University, where his research addressed Appalachian Basin geothermal resource assessment and subsequent uncertainty assessments for deep geothermal district heating projects at the Cornell and West Virginia University campuses. Previous work has also addressed ice jam flood frequency analysis under climate change, applied to the Peace-Athabasca Delta in Canada.

Education and Certifications

  • ​Ph.D. Environmental and Water Resources Systems Engineering, Cornell University, 2019

  • M.S. Environmental and Water Resources Systems Engineering, Cornell University, 2016

  • B.S. Environmental Engineering, Clarkson University, 2013

Abstracts and Presentations

  • ​Cluster Analysis and Prediction of Flood Flow Metrics for Minimally Altered Catchments in the Conterminous United States, HydroML Symposium 2022 

  • Discovering Flood Regions and Predicting Flood Flow Metrics to Inform Bridge Scour Studies in the Conterminous United States, National Hydraulic Engineering Conference, 2022 

Science and Products

link
highway

Transportation-Related Water Projects

The USGS has a long history of cooperative investigations with the Federal Highway Administration (FHWA) and state highway agencies to provide data and information to address various issues related to water resources and the Nation’s transportation infrastructure. These issues cover a wide spectrum and include items such as regional flow statistics, flood documentation, regional stream...
By
Water Resources Mission Area
link

Transportation-Related Water Projects

The USGS has a long history of cooperative investigations with the Federal Highway Administration (FHWA) and state highway agencies to provide data and information to address various issues related to water resources and the Nation’s transportation infrastructure. These issues cover a wide spectrum and include items such as regional flow statistics, flood documentation, regional stream...
Learn More

Delaware River Basin Stream Salinity Machine Learning Models and Data

This model archive contains the input data, model code, and model outputs for machine learning models that predict daily non-tidal stream salinity (specific conductance) for a network of 459 modeled stream segments across the Delaware River Basin (DRB) from 1984-09-30 to 2021-12-31. There are a total of twelve models from combinations of two machine learning models (Random Forest and Recurrent Gra
By
Water Resources Mission Area

A deep learning model and associated data to support understanding and simulation of salinity dynamics in Delaware Bay

Salinity dynamics in the Delaware Bay estuary are a critical water quality concern as elevated salinity can damage infrastructure and threaten drinking water supplies. Current state-of-the-art modeling approaches use hydrodynamic models, which can produce accurate results but are limited by significant computational costs. We developed a machine learning (ML) model to predict the 250 mg/L Cl- isoc
By
Water Resources Mission Area

Predictive understanding of stream salinization in a developed watershed using machine learning

Stream salinization is a global issue, yet few models can provide reliable salinity estimates for unmonitored locations at the time scales required for ecological exposure assessments. Machine learning approaches are presented that use spatially limited high-frequency monitoring and spatially distributed discrete samples to estimate the daily stream-specific conductance across a watershed. We comp
Authors
Jared David Smith, Lauren Elizabeth Koenig, Margaux Jeanne Sleckman, Alison P. Appling, Jeffrey M Sadler, Vincent T. DePaul, Zoltan Szabo
By
Water Resources Mission Area, New Jersey Water Science Center, Oklahoma-Texas Water Science Center

Deep learning of estuary salinity dynamics is physically accurate at a fraction of hydrodynamic model computational cost

Salinity dynamics in the Delaware Bay estuary are a critical water quality concern as elevated salinity can damage infrastructure and threaten drinking water supplies. Current state-of-the-art modeling approaches use hydrodynamic models, which can produce accurate results but are limited by significant computational costs. We developed a machine learning (ML) model to predict the 250 mg L−1 Cl− is
Authors
Galen Agnew Gorski, Salme Ellen Cook, Amelia Marie Snyder, Alison P. Appling, Theodore Paul Thompson, Jared David Smith, John C. Warner, Simon Nemer Topp
By
Water Resources Mission Area

New diagnostic assessment of MCMC algorithm effectiveness, efficiency, reliability, and controllability

Markov Chain Monte Carlo (MCMC) is a robust statistical approach for estimating posterior distributions. However, the significant computational cost associated with MCMC presents a considerable challenge, complicating the selection of an appropriate algorithm tailored to the specific problem at hand. This study introduces a novel and comprehensive framework for evaluating the performance of MCMC a
Authors
Hossein KavianiHamedani, Julianne D. Quinn, Jared David Smith
By
Water Resources Mission Area

Non-USGS Publications**

Smith, J.D., L. Lin, J.D. Quinn, and L.E. Band, 2022, Guidance on evaluating parametric model uncertainty at decision-relevant scales. HESS, 26(9): 2519-2022. https://doi.org/10.5194/hess-26-2519-2022
Lamontage, J.R., M. Jasek, and J.D. Smith, 2021, Coupling physical understanding and statistical modeling to estimate ice jam flood frequency in the northern Peace-Athabasca Delta under climate change. Cold Reg. Sci. Technol., 192: 103383. https://doi.org/10.1016/j.coldregions.2021.103383
Whealton, C.A., J.R. Stedinger, J.D. Smith, T.E. Jordan, F.G. Horowitz, and M.C. Richards, 2020, Multi-criteria spatial screening and uncertainty analysis applied to direct-use geothermal projects. Int. J. Geogr. Inf. Sci., 34(10): 2053-2076. https://doi.org/10.1080/13658816.2020.1765247

**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

link
highway

Transportation-Related Water Projects

The USGS has a long history of cooperative investigations with the Federal Highway Administration (FHWA) and state highway agencies to provide data and information to address various issues related to water resources and the Nation’s transportation infrastructure. These issues cover a wide spectrum and include items such as regional flow statistics, flood documentation, regional stream...
By
Water Resources Mission Area
link

Transportation-Related Water Projects

The USGS has a long history of cooperative investigations with the Federal Highway Administration (FHWA) and state highway agencies to provide data and information to address various issues related to water resources and the Nation’s transportation infrastructure. These issues cover a wide spectrum and include items such as regional flow statistics, flood documentation, regional stream...
Learn More

Delaware River Basin Stream Salinity Machine Learning Models and Data

This model archive contains the input data, model code, and model outputs for machine learning models that predict daily non-tidal stream salinity (specific conductance) for a network of 459 modeled stream segments across the Delaware River Basin (DRB) from 1984-09-30 to 2021-12-31. There are a total of twelve models from combinations of two machine learning models (Random Forest and Recurrent Gra
By
Water Resources Mission Area

A deep learning model and associated data to support understanding and simulation of salinity dynamics in Delaware Bay

Salinity dynamics in the Delaware Bay estuary are a critical water quality concern as elevated salinity can damage infrastructure and threaten drinking water supplies. Current state-of-the-art modeling approaches use hydrodynamic models, which can produce accurate results but are limited by significant computational costs. We developed a machine learning (ML) model to predict the 250 mg/L Cl- isoc
By
Water Resources Mission Area

Predictive understanding of stream salinization in a developed watershed using machine learning

Stream salinization is a global issue, yet few models can provide reliable salinity estimates for unmonitored locations at the time scales required for ecological exposure assessments. Machine learning approaches are presented that use spatially limited high-frequency monitoring and spatially distributed discrete samples to estimate the daily stream-specific conductance across a watershed. We comp
Authors
Jared David Smith, Lauren Elizabeth Koenig, Margaux Jeanne Sleckman, Alison P. Appling, Jeffrey M Sadler, Vincent T. DePaul, Zoltan Szabo
By
Water Resources Mission Area, New Jersey Water Science Center, Oklahoma-Texas Water Science Center

Deep learning of estuary salinity dynamics is physically accurate at a fraction of hydrodynamic model computational cost

Salinity dynamics in the Delaware Bay estuary are a critical water quality concern as elevated salinity can damage infrastructure and threaten drinking water supplies. Current state-of-the-art modeling approaches use hydrodynamic models, which can produce accurate results but are limited by significant computational costs. We developed a machine learning (ML) model to predict the 250 mg L−1 Cl− is
Authors
Galen Agnew Gorski, Salme Ellen Cook, Amelia Marie Snyder, Alison P. Appling, Theodore Paul Thompson, Jared David Smith, John C. Warner, Simon Nemer Topp
By
Water Resources Mission Area

New diagnostic assessment of MCMC algorithm effectiveness, efficiency, reliability, and controllability

Markov Chain Monte Carlo (MCMC) is a robust statistical approach for estimating posterior distributions. However, the significant computational cost associated with MCMC presents a considerable challenge, complicating the selection of an appropriate algorithm tailored to the specific problem at hand. This study introduces a novel and comprehensive framework for evaluating the performance of MCMC a
Authors
Hossein KavianiHamedani, Julianne D. Quinn, Jared David Smith
By
Water Resources Mission Area

Non-USGS Publications**

Smith, J.D., L. Lin, J.D. Quinn, and L.E. Band, 2022, Guidance on evaluating parametric model uncertainty at decision-relevant scales. HESS, 26(9): 2519-2022. https://doi.org/10.5194/hess-26-2519-2022
Lamontage, J.R., M. Jasek, and J.D. Smith, 2021, Coupling physical understanding and statistical modeling to estimate ice jam flood frequency in the northern Peace-Athabasca Delta under climate change. Cold Reg. Sci. Technol., 192: 103383. https://doi.org/10.1016/j.coldregions.2021.103383
Whealton, C.A., J.R. Stedinger, J.D. Smith, T.E. Jordan, F.G. Horowitz, and M.C. Richards, 2020, Multi-criteria spatial screening and uncertainty analysis applied to direct-use geothermal projects. Int. J. Geogr. Inf. Sci., 34(10): 2053-2076. https://doi.org/10.1080/13658816.2020.1765247

**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.

Was this page helpful?