The Duke Funding Alert newsletter, published every Monday, provides information on all new and updated grants and fellowships added to the database during the prior week. This listserv is restricted to members of the Duke community.
Cooperative Agreement for CESU-affiliated Partner with Piedmont-South Atlantic Coast Cooperative Ecosystem Studies Unit -- AI Models for Fish Recognition
The USGS is offering a funding opportunity to a CESU partner for research in developing deep convolutional neural networks for image-based individual fish recognition, develop baseline Artificial Intelligence (hereafter, AI) models for individual recognition performance, and determining the performance of AI models. Research Scientists at the EESC have a wealth of knowledge specific to ongoing studies that are using AI to identify fish in freshwater streams and develop early detection of diseased fish. This research will advance the understanding by linking developing methods in computer science with ecological science.
Deadline: Jan. 14, 2021
Areas of Interest
USGS is developing AI and Machine Learning (hereafter, AI_ML) projects that can benefit fisheries management in consultation with state, federal, and NGO partners and advance AI_ML to address fisheries management needs. Working with state fisheries managers, are working on three pilot projects:
1. Largemouth bass in the tidal Potomac River - abundance estimation, blotchy bass syndrome prevalence and pigmentation change over time
2. Brown trout in the Deerfield River, MA - abundance estimation, tracking of stocked fish
3. Brook trout in small streams - abundance estimation, effects of drought on movements/survival
The focus of this opportuntiy is on AI_ML individual recognition from photos because this application has the greatest potential to influence fisheries management. This application has the potential to save money and time by reducing reliance on resource-intensive tagging for population monitoring commonly conducted by state fisheries agencies. Information currently obtained from tagging studies, including abundance, survival, and movement estimates, could be derived from the images. Moreover, some aspects of fish health (e.g., blotchy bass syndrome and external tumors) could also be addressed using this technique.
This financial assistance opportunity is being issued under a Cooperative Ecosystem Studies Unit (CESU) Program. CESU’s are partnerships that provide research, technical assistance, and education. Eligible recipients must be a participating partner of the Piedmont-South Atlantic Coast Cooperative Ecosystem Studies Unit (CESU) Program.
It is anticipated that one award will be made with one base year and four renewal years. The total estimated funding for this project will not exceed $99,000. Funding in the amount of $42,000 is estimated to be available for FY 2022. Additional funding will be based upon satisfactory progress and the availability of funding.