Humboldt State University

SACNAS

The Society for Advancement of Hispanics/Chicanos and Native Americans in Science (SACNAS) is an inclusive organization dedicated to fostering the success of Hispanic/Chicano and Native American scientists—from college students to professionals—to attain advanced degrees, careers, and positions of leadership in STEM.

2024 SACNAS National Conference:
The National Diversity in STEM Conference
October 31 - November 2, 2024
Phoenix, Arizona

                      

 

student presents poster

 Conference Presentation

2023 SACNAS poster presentation awards (INRSEP students)

Analyzing the influence of aquaculture-related habitat modification on elasmobranch abundance and predation intensity using AI software

Alexis Hernandez - California Polytechnic State University, Humboldt

Nievita Bueno Watts - Cal Poly Humboldt

Paul Bourdeau - Cal Poly Humboldt

Recent breakthroughs in artificial intelligence (AI) and the breadth of its application, motivated us to use AI for marine species identification and analysis. Using an open-source ‘do-it-yourself’ AI software platform developed by NOAA called VIAME (Video and Image Analytics for Marine Environments), we will assess the effectiveness of using AI and machine learning to identify marine species from video surveys in Humboldt Bay, California. Humboldt Bay produces ~70% of California's oysters, and is home to many ecologically and commercially important marine species. With the growth of oyster aquaculture in the bay, the resultant habitat modification may provide an additional source of shelter for benthic fish and invertebrates, and may influence species’ habitat use. Using BRUVS (Baited Underwater Video Systems) to collect video footage of marine species present in and out of aquaculture-modified habitat in Humboldt Bay, we will compare how efficient VIAME is compared to human observers in identifying species in our video surveys. This will allow us to determine whether VIAME is a useful tool that can save time and resources in analyzing BRUVS footage, a common underwater survey method.