Skip to main content
U.S. flag

An official website of the United States government

Using Artificial Intelligence to Help Protect Trout and Drinking Water Supplies

By Year of Open Science September 15, 2023

Reproducible workflows and stakeholder engagement enable open forecasts that are valuable for decision makers. 

Decisions depend on our ability to predict the future with imperfect information. Forecasts that offer both predictions and uncertainty information are valuable tools for decision makers. Transparent decision making is essential to gain public trust.  

One decision-making scenario that USGS work supports involves drinking water for the people of New York City (NYC). Managers need to sensibly release some reservoir water to cool stream temperatures in the Delaware River Basin. This water release is crucial for protecting trout and other important species in the basin. However, managers also need to ensure that they reserve enough water supply for NYC. They have created a "thermal bank," a set volume of water available for release, to use when river site temperatures are expected to exceed 75°F. Predicting these temperature spikes can be challenging, and that is one area where USGS can help.  

Scientists at USGS have developed forecasts of stream water temperature with associated uncertainties in the Delaware River Basin. We use public datasets to teach deep learning models how to accurately predict stream temperature dynamics.  Each day, our model makes public forecasts of stream temperature. These forecasts help reservoir managers anticipate warm periods and release the appropriate amount of water. The forecasts are also useful for ecotourists and other scientists in the basin.   

We engaged NYC reservoir managers at many stages in the development process. Their feedback was instrumental for creating an effective open science product. They provided input on the model setup, forecast visualization, and data delivery. This input enabled us to produce a tool that is useful for water management decision making.  

We provide all our code, datasets, and methods in open access repositories. This transparency allows others to build upon and learn from our experiences. 

Website: https://labs.waterdata.usgs.gov/water-temperature-forecasts/DRB/2023/index.html

Preprint: https://doi.org/10.31223/X55K7G

Journal Article 1: https://doi.org/10.1111/1752-1688.13093

Journal Article 2: https://doi.org/10.3389/frwa.2023.1184992

Data Release 1: https://doi.org/10.5066/P9NVEA4V

Data Release 2: https://doi.org/10.5066/P9GD8I7A 

Data Release 3: https://doi.org/10.5066/P96R34A7

Code Release: https://doi.org/10.5281/zenodo.7382575

 

Related Content

Data to support near-term forecasts of stream temperature using process-guided deep learning and data assimilation

This data release contains the forcings and outputs of 7-day ahead maximum water temperature forecasting models that made real-time predictions in the Delaware River Basin during 2021. The model is driven by weather forecasts and observed reservoir releases and produces maximum water temperature forecasts for the issue day (day 0) and 7 days into the future (days 1-7) at five sites. This data rele
By
Water Resources Mission Area

Predicting water temperature in the Delaware River Basin

Daily temperature predictions in the Delaware River Basin (DRB) can inform decision makers who can use cold-water reservoir releases to maintain thermal habitat for sensitive fish and mussel species. This data release supports a variety of flow and water temperature modeling efforts and provides the inputs and outputs of both machine learning and process-based modeling methods across 456 river rea
By
Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center

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)

Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions

Deep learning (DL) models are increasingly used to make accurate hindcasts of management-relevant variables, but they are less commonly used in forecasting applications. Data assimilation (DA) can be used for forecasts to leverage real-time observations, where the difference between model predictions and observations today is used to adjust the model to make better predictions tomorrow. In this us
Authors
Jacob Aaron Zwart, Samantha K. Oliver, William Watkins, Jeffrey Michael Sadler, Alison P. Appling, Hayley Corson-Dosch, Xiaowei Jia, Vipin Kumar, Jordan Read

Related Content

Data to support near-term forecasts of stream temperature using process-guided deep learning and data assimilation

This data release contains the forcings and outputs of 7-day ahead maximum water temperature forecasting models that made real-time predictions in the Delaware River Basin during 2021. The model is driven by weather forecasts and observed reservoir releases and produces maximum water temperature forecasts for the issue day (day 0) and 7 days into the future (days 1-7) at five sites. This data rele
By
Water Resources Mission Area

Predicting water temperature in the Delaware River Basin

Daily temperature predictions in the Delaware River Basin (DRB) can inform decision makers who can use cold-water reservoir releases to maintain thermal habitat for sensitive fish and mussel species. This data release supports a variety of flow and water temperature modeling efforts and provides the inputs and outputs of both machine learning and process-based modeling methods across 456 river rea
By
Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center

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)

Near-term forecasts of stream temperature using deep learning and data assimilation in support of management decisions

Deep learning (DL) models are increasingly used to make accurate hindcasts of management-relevant variables, but they are less commonly used in forecasting applications. Data assimilation (DA) can be used for forecasts to leverage real-time observations, where the difference between model predictions and observations today is used to adjust the model to make better predictions tomorrow. In this us
Authors
Jacob Aaron Zwart, Samantha K. Oliver, William Watkins, Jeffrey Michael Sadler, Alison P. Appling, Hayley Corson-Dosch, Xiaowei Jia, Vipin Kumar, Jordan Read

Get Our News

These items are in the RSS feed format (Really Simple Syndication) based on categories such as topics, locations, and more. You can install and RSS reader browser extension, software, or use a third-party service to receive immediate news updates depending on the feed that you have added. If you click the feed links below, they may look strange because they are simply XML code. An RSS reader can easily read this code and push out a notification to you when something new is posted to our site.

Advanced Research Computing (ARC) News

Ecosystems News

Water News

Year of Open Science News