HydroLearn-CIROH May/June 2026 Workshop and Hackathon
May 27 - 8, 2026
Application Deadline 1.31.2026
The HydroLearn team is pleased to invite faculty, postdoctoral scholars, and graduate students with expertise in hydrology to participate in the 2026 HydroLearn-CIROH Workshop & Hackathon, to be held in May/June 2026.
Deadline to apply: January 31, 2026
Apply Here!
Event Dates: In-person workshop May 27 - 29, 2026, and virtual hackathon June 2 - 5 and June 8 - 11, 2026
Selected participants will receive travel support to attend the CIROH Developers Conference in Salt Lake City, UT (May 27 - 29, 2026) to collaborate with researchers and practitioners advancing river forecasting models and complete the in-person portion of our training. Then, participants will then work in pairs to create a high-quality learning module through our guided 8-day virtual hackathon (June 2 - 5 and June 8 - 11, 2026) with hydrology and education experts. Upon completion and peer review, modules will be hosted on the HydroLearn platform.
About HydroLearn
Originally supported by the National Science Foundation in 2008, HydroLearn is a platform and pedagogical model that integrates best practices in course design into workshops and hackathons to train hydrology educators and produce high-quality open online resources. The platform already contains over 60 peer-reviewed modules co-created by past HydroLearn fellows on a wide range of topics.
Eligibility
Participants in the 2026 HydroLearn-CIROH workshop and hackathon must:
Apply and be accepted to the program.
Commit to attending the in-person workshop in Salt Lake City, UT, May 27 - 29, 2026
Review assigned module-specific technical materials and resources in advance of the workshop and hackathon.
Fully attend and participate in the 8-day virtual hackathon, June 2 - 5, and June 8 - 11, 2026, from 11 AM - 6 PM Eastern.
Complete the module following the hackathon if it is not completed by the end of the hackathon, although the hackathon is designed so that modules can be completed within 8 days.
Integrate feedback from the content and education guides during the peer review process.
Commit to the HydroLearn pedagogical approach of assessment-driven, active learning content design.
Participants must reside in the U.S. and have a current affiliation with a U.S.-based university or non-profit in order to receive $2,500 stipend.
Participant Support
Participants eligible to do so will receive travel reimbursement for eligible travel expenses to and from the in-person workshop in Salt Lake City, UT, May 27 - 29, 2026
Upon full participation in the program including peer review and publication of the module, participants eligible to do so will receive a $2500 stipend.
Selection
Participants must apply and be accepted to participate in this program.
The successful candidate will:
Demonstrate their intention to participate fully as outlined in the above eligibility requirements
Demonstrate their content knowledge and experience, relevant to their selected module topic (described below).
Demonstrate an interest in developing as a hydrology educator.
Demonstrate an interest in, and any experience working on collaborative teams to co-create a high-quality educational product.
Module Topics
Module topics have been pre-determined for the 2026 workshop and hackathon. This ensures alignment with CIROH’s research themes, guarantees the availability of subject-matter expertise, and speeds the module development process. You will be asked to select which module(s) you would like to work on and demonstrate that you have relevant knowledge and/or experience with the topic area.Module topics are listed and described below, including the name of the technical lead who will provide resources and guidance on content during the workshop and hackathon event.
Identifying and Applying Error Metrics for River Forecasting
Summary: In this module, learners will be introduced to a wide variety of error metrics (i.e. NSE, KGE, Bias, etc) that are used to evaluate a model's accuracy for predicting streamflow. Using real data, students will apply these different error metrics and explore their relevance for various end-user applications. Learners will also be introduced to the concept of ensemble forecasting and learn how it increases error analysis complexity.
Technical Leads: Dr. Katie VanWerkhoven, Dr. Shaun Carney, RTI
Water quality forecasts using the National Water Model
Summary: This module will introduce participants to water quality forecasting and nowcasting with the National Water Model (NWM). Water quality forecasts are challenging to make due to the complex processes and feedback that govern water quality dynamics. Here, we will use machine learning (ML) models trained on observational data to account for these complexities and build skillful models that ingest NWM streamflow forecasts to make water quality forecasts for a variety of constituents. Participants will work with open-source streamflow, precipitation, and water quality data gathered by the USGS, EPA, and NOAA as well as several different ML models (random forest, gradient-boosted decision trees) to develop a workflow to train ML water quality models. Once trained, learners will then use NWM medium-term and analysis and assimilation data to build water quality “nowcasts” and “forecasts” for sites and constituents of interest. Upon completion, module participants will gain hands-on experience with tools for producing water quality forecasts and gain a holistic understanding of the forecasting process, from model training to near-real-time forecasting.
Technical Lead: Dr. John Kemper, Utah State University
Using Hydrofabric for Integrated and Adaptive Hydrologic Modeling
Summary: Hydrofabric is a geospatial framework that organizes hydrologic features such as catchments, flowpaths, waterbodies, and nexuses into a connected, standardized network that underpins the Next Generation (NextGen) hydrologic modeling system. It is a community-driven data source and a workflow that enables the integration of different models and can be easily adapted as needs evolve. In this module, learners will use the R scripts within Hydrofabric to access data and build an integrated model that meets a specific end-user need. Learners will subsequently adapt the model to use different datasets, demonstrating its flexibility and adaptability.
Technical Lead: Dr. David Tarboton
Embedding Community Engagement into Decision Support Tool Design
Summary: This learning module introduces the basics of community engagement and highlights why it is essential for the water science community when developing and deploying decision support tools. Drawing on lessons from a study that leveraged co-development to enhance the accessibility of a water-prediction model for decision making, the module emphasizes how early, inclusive engagement helps researchers understand diverse stakeholder needs, build trust, improve communication, and ensure tools are relevant and usable beyond technical audiences. Through brief activities such as stakeholder identification, discussion of common engagement methods, and reflection on co-development case examples, learners gain insight into how meaningful collaboration can strengthen both scientific products and improve real-world decision making.
Technical Lead: Dr. Kristin Raub, Northeastern University
Best Practices in High Performance Computing (HPC) for Hydrologic Modeling
This module introduces learners to the computational foundations needed to build and run large-scale hydrologic models. Many modern hydrologic applications, such as continental-scale prediction, ensemble modeling, and parameter estimation, demand substantial computing power, particularly in operational forecasting environments. Learners will gain a practical introduction to high-performance computing (HPC), including how distributed systems, parallel execution, and workflow design support advanced hydrologic modeling used by both researchers and operational agencies. The module will also touch briefly on newer approaches, such as the actor model of concurrent computing and actor-based execution, that offer flexible and resilient alternatives to traditional HPC methods. By the end of the module, learners will understand why hydrologic forecasting requires sophisticated computational strategies, how classical HPC concepts map onto modeling challenges in both research and operations, and how well-designed workflows enable efficient, reproducible model configuration and execution. They will gain hands-on experience running test cases using modern open-source hydrologic modeling tools and learn how computational choices influence model performance, scalability, and forecast reliability.
Technical Lead: Dr. Ray Spiteri, University of Saskatoon
About CIROH
CIROH, a partnership between NOAA and The University of Alabama, is a national consortium committed to advancing water prediction and building community resilience to water-related challenges. CIROH scientists work to improve our understanding of hydrologic processes, create new operational hydrologic forecasting techniques and workflows, support community water modeling, translate forecasts into actionable products, and improve how water predictions are used in decision-making.
This HydroLearn workshop is supported by the Cooperative Institute for Research to Operations in Hydrology (CIROH) with funding under award NA22NWS4320003 from the NOAA Cooperative Institute Program. The statements, findings, conclusions, and recommendations are those of the author(s) and do not necessarily reflect the opinions of NOAA.
Additional Information:
We encourage you to check with your employer regarding your eligibility to receive a stipend.