Jacob Zwart, PhD
Dr. Jacob Zwart is a senior research data scientist and aquatic biogeochemist for the USGS Water Resources Mission Area.
Jacob is a senior research data scientist and aquatic biogeochemist focused on several interdisciplinary research objectives: 1) Improving our understanding of aquatic biogeochemical processes and their responses to future global changes. 2) Advancing artificial intelligence (AI) methods for environmental science, including knowledge-guided machine learning (KGML), equitable machine learning for water predictions, and responsible AI. 3) Innovating on deep learning forecasting methods including assimilating real-time observations into KGML models and characterizing deep learning forecast uncertainty.
He was awarded the Presidential Early Career Award for Scientists and Engineers (PECASE) in 2025 for his environmental forecast research, the highest honor bestowed by the U.S. government on outstanding scientists and engineers early in their careers. Jacob has received four outstanding publication awards including three as the lead author, an outstanding dissertation award from University of Notre Dame Biology Department, and he is an author of three book chapters in the fields of aquatic ecology, machine learning, and knowledge-guided machine learning.
Jacob also serves as a Peer Support Worker at USGS promoting awareness and education on topics and USGS policies for antiharassment, discrimination, biases, and scientific integrity, as well as providing peer-to-peer support for USGS employees.
Professional Experience
2025 – present: Senior Research Data Scientist, U.S. Geological Survey
2022 – 2025: Senior Data Scientist, U.S. Geological Survey
2021 – 2022: Data Scientist, U.S. Geological Survey
2019 – 2021: Mendenhall Postdoctoral Fellow, U.S. Geological Survey
2017 – 2019: National Science Foundation Earth Sciences Postdoctoral Fellow, U.S. Geological Survey
2014 – 2017: National Science Foundation Graduate Research Fellow, University of Notre Dame
2012 – 2014: Research and Teaching Assistant, University of Notre Dame
Education and Certifications
Ph.D., Biological Sciences, 2017, University of Notre Dame
- Hydrologic Regulation of Lake Carbon Cycling in Both Time and Space. Advisor: Dr. Stuart Jones
B.S., Biology, Calvin College, 2012
Honors and Awards
Presidential Early Career Award in Science and Engineering (PECASE), the highest honor bestowed by the U.S. government on outstanding scientists and engineers early in their careers, 2025
American Water Resources Association’s William R. "Randy" Boggess Award 2024 for best paper published in the Journal of the American Water Resources Association during the previous year.
Ecological Society of America Ecological Forecasting Outstanding Publication Award 2023 - annual award in recognition of an outstanding scholarly publication published within the last three years.
Best Applied Data Science Paper Award in the SIAM International Conference on Data Mining 2021 – awarded annually for outstanding publication in Society for Industrial and Applied Mathematics (SIAM)
U.S. Geological Survey Mendenhall Postdoctoral Fellowship, 2019 – 2021
National Science Foundation Earth Sciences Postdoctoral Fellowship, 2017 – 2019
Best dissertation award for the University of Notre Dame Biology Department, 2017
University of Notre Dame Linked Experimental Ecosystem Facility Research Grant, 2017
Exceptional Promise in Graduate Research Award, Ecological Society of America Aquatic Ecology Section – awarded to scientists in recognition of an outstanding paper resulting from research done as a g
National Science Foundation Graduate Research Fellowship, 2014 – 2017
University of Notre Dame Center for Aquatic Conservation Graduate Fellow, 2014
University of Notre Dame Environmental Research Center Graduate Research Fellowship, 2013 – 2015
University of Notre Dame Environmental Research Center Graduate Mentoring Fellowship, 2012
Science and Products
Near-term ecological forecasting for climate change action
The 2024 “Hacking Limnology” Workshop Series and Virtual Summit: Increasing inclusion, participation, and representation in the aquatic sciences
Human activities shape global patterns of decomposition rates in rivers
Evaluation of metrics and thresholds for use in national-scale river harmful algal bloom assessments
Fair graph learning using constraint-aware priority adjustment and graph masking in river networks
National-scale remotely sensed lake trophic state from 1984 through 2020
Response of lake metabolism to catchment inputs inferred using high-frequency lake and stream data from across the northern hemisphere
A synergistic future for AI and ecology
Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations
Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions
Physics-guided recurrent neural networks for predicting lake water temperature
Physics-guided graph meta learning for predicting water temperature and streamflow in stream networks
Non-USGS Publications**
**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.
Integrating stream gage records, water presence observations, and models to improve hydrologic prediction in stream networks
Data release: early warning indicators for harmful algal bloom assessments in the Illinois River, 2013 - 2020
Predictions and supporting data for network-wide 7-day ahead forecasts of water temperature in the Delaware River Basin
National-scale, remotely sensed lake trophic status 1984-2020
Harmonized discrete and continuous water quality data in support of modeling harmful algal blooms in the Illinois River Basin, 2005 - 2020
Model predictions for heterogeneous stream-reservoir graph networks with data assimilation
Data to support near-term forecasts of stream temperature using process-guided deep learning and data assimilation
Multi-task Deep Learning for Water Temperature and Streamflow Prediction (ver. 1.1, June 2022)
Data to support water quality modeling efforts in the Delaware River Basin
Lake Biogeochemical Model Output for One Retrospective and 12 Future Climate Runs in Northern Wisconsin & Michigan, USA
Predicting water temperature in the Delaware River Basin
Data release: Process-based predictions of lake water temperature in the Midwest US
Experimental Forecast for River Chlorophyll
Science and Products
Near-term ecological forecasting for climate change action
The 2024 “Hacking Limnology” Workshop Series and Virtual Summit: Increasing inclusion, participation, and representation in the aquatic sciences
Human activities shape global patterns of decomposition rates in rivers
Evaluation of metrics and thresholds for use in national-scale river harmful algal bloom assessments
Fair graph learning using constraint-aware priority adjustment and graph masking in river networks
National-scale remotely sensed lake trophic state from 1984 through 2020
Response of lake metabolism to catchment inputs inferred using high-frequency lake and stream data from across the northern hemisphere
A synergistic future for AI and ecology
Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations
Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions
Physics-guided recurrent neural networks for predicting lake water temperature
Physics-guided graph meta learning for predicting water temperature and streamflow in stream networks
Non-USGS Publications**
**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.