Improved Harmful Algal Blooms Prediction with Hybrid Models | W81EWF 24 SOI 0041

Opportunity Information: Apply for W81EWF 24 SOI 0041

The Improved Harmful Algal Blooms Prediction with Hybrid Models opportunity is a U.S. Army Corps of Engineers (USACE) research and development effort aimed at closing a major gap in how harmful algal blooms (HABs) are assessed and forecast in lakes and reservoirs. The problem the agency is trying to solve is that, for most U.S. waterbodies, there is still no widely implemented way to quantify bloom vulnerability or to generate reliable forecasts at the kind of detail that reservoir managers and drinking-water stakeholders actually need. That gap has real operational consequences: it makes it harder to prevent expensive emergency responses, to design monitoring programs efficiently, to judge whether mitigation actions are working, and to maintain public confidence when blooms occur or when advisories are issued.

A key driver for this project is that many current HAB detection and prediction approaches are limited by sparse data and narrow scope. Satellite imagery can be valuable, but it is often infrequent, can be obstructed by clouds, and may not capture conditions below the surface. Water sampling provides strong ground truth, but it is usually collected at limited locations and on schedules that miss rapid bloom changes. As a result, predictions are often tied to specific sampling stations rather than providing full-reservoir coverage, and the models used tend to focus heavily on weather correlations without offering much insight into the underlying causes of blooms, such as nutrient loading, watershed runoff dynamics, reservoir operations, stratification, mixing, and other physical and biogeochemical drivers. USACE specifically frames its challenge as twofold: improving the spatial and temporal resolution of HAB predictions, and improving diagnostic capability so managers can understand why blooms happen in managed reservoirs and what levers might reduce risk.

The overarching goal of the funded work is to develop and test a hybrid modeling system that combines three complementary model types: watershed models, hydrodynamic models, and machine learning models. In practical terms, this points toward an integrated framework where watershed models can represent how nutrients and sediments move from the surrounding landscape into the reservoir, hydrodynamic models can represent how water movement, temperature structure, stratification, and mixing distribute those inputs and create conditions favorable for blooms, and machine learning can learn patterns from historical observations to improve predictive accuracy, fill gaps, and potentially provide probabilistic forecasts. The emphasis on “high spatial and temporal resolution” suggests outputs that are more like frequent, reservoir-wide maps or gridded predictions rather than occasional point forecasts, supporting day-to-day decision making and situational awareness.

The opportunity describes three main deliverables. First, the project is expected to produce a working hybrid HAB prediction system for USACE reservoirs that improves on the current state of the art in both spatial coverage (more complete representation across a reservoir rather than just at sampling sites) and temporal frequency (more frequent updates rather than intermittent snapshots). Second, the project must demonstrate that the hybrid approach is not only predictive but also explanatory, meaning it can help identify the drivers of HABs and estimate the likely efficacy of interventions. That second point is important for management, because interventions can be costly and politically sensitive; a tool that can evaluate “what if” scenarios (for example, changes in nutrient inputs, altered reservoir operations, or targeted watershed actions) is much more actionable than a tool that only predicts bloom occurrence. Third, the project must include documentation and training materials to support deployment at additional USACE reservoirs, indicating that the agency wants the work to be transferable and scalable beyond a single pilot site.

Administratively, this is a discretionary funding opportunity using a Cooperative Agreement, which typically means substantial involvement or collaboration by the federal agency during the project period rather than a hands-off grant. The issuing organization is the Engineer Research and Development Center (ERDC). The Funding Opportunity Number is W81EWF 24 SOI 0041, and it is listed under CFDA 12.630 within the Science and Technology / Research and Development activity category. The opportunity anticipates a single award with an expected award ceiling of $142,324. The original closing date is 2024-09-16, and the opportunity was created on 2024-07-18.

Eligibility is restricted: only non-federal partners of the Pacific Northwest Cooperative Ecosystems Studies Unit (CESU) may apply. That constraint effectively limits applicants to organizations already participating in that CESU network (often universities, nonprofits, tribes, and other qualified entities that are CESU partners), and it signals that the agency intends to place the work within an existing cooperative research framework. Overall, the funding is aimed at producing a deployable, decision-relevant forecasting and diagnostic system for HABs in USACE-managed reservoirs, with a strong emphasis on improving prediction detail, understanding causation, and enabling broader adoption through training and documentation.

• The Engineer Research and Development Center in the science and technology and other research and development sector is offering a public funding opportunity titled "Improved Harmful Algal Blooms Prediction with Hybrid Models" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 12.630.
• This funding opportunity was created on 2024-07-18.
• Applicants must submit their applications by 2024-09-16. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• Each selected applicant is eligible to receive up to $142,324.00 in funding.
• The number of recipients for this funding is limited to 1 candidate(s).
• Eligible applicants include: Others.

Apply for W81EWF 24 SOI 0041

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: