Use of Artificial Intelligence (AI) to Monitor Steller Sea Lion Populations

Article and Figures Provided By: Katie Sweeney, Marine Mammal Laboratory, Alaska Fisheries Science Center, NOAA Fisheries

Kenneth Vierra 0 866 Article rating: No rating
Every year, Alaska Fisheries Science Center’s Marine Mammal Laboratory of NOAA Fisheries uses crewed and uncrewed systems to conduct aerial surveys of known Steller sea lion sites across Alaska. These surveys are essential to monitoring the endangered western population of Steller sea lions in Alaska. While the population as a whole has begun to show signs of recovery, one region in the westernmost part of the population range has declined 94% in the last 40 years (showing no signs of recovery), and rookeries - sites where sea lions mate, give birth, and rest - have begun to disappear. In the Gulf of Alaska, anomalous warm water events beginning in 2014 are becoming more commonplace and are likely causing the observed declines in the area - an area which was previously showing signs of sea lion population recovery and began to increase in 2002.

Fusion of LiDAR and Hyperspectral Imagery to Monitor Wetland Restoration Benefiting Salmon


Kenneth Vierra 0 3599 Article rating: No rating

Effective restoration of wetlands from anthropogenic stress is a critical research priority worldwide, and in the Pacific Northwest of the US there is a heightened relevance for supporting recovery of listed and endangered salmon. Wetland vegetation communities are especially important for shelter and as a source of invertebrate prey preferred by juvenile salmon during migration to the ocean. While many new restoration projects have commenced in recent years, often lacking is the means for evaluation of the restoration effectiveness. This evaluation includes quantification of the trajectory of physical systems and vegetation communities from initial states towards those more beneficial to desired outcomes (e.g. fish survival). Typical wetland/estuarine vegetation and topographic surveys are expensive, time-consuming, and restricted in spatial and temporal cover, difficulties that until now have limited evaluation of restoration trajectories toward recovery.

This project is supported by funding from the UAS Program Office, and includes a partnership between NOAA Fisheries, Pacific Northwest National Laboratories, RykaUAS, and the National Park Service, has developed a UAS for remote sensing of vegetation types using a 110-band imaging spectrometer (BaySpec OCI) flown on a DJI Matrice 600 hexacopter. We established a library of ground-truthed “spectral signatures” from wetland plant species and analytical routines allowing for output of categorized maps and statistical metrics. The next phase of the project entails integrating a LiDAR (RIEGL miniVUX-1UAV) instrument for determining topography-vegetation species relationships and to track landform changes as restoration projects evolve over time. Fusing the vegetation and topographic data offers a means for the rapid and comprehensive assessment of habitat metrics with minimal additional ground truthing, and provides methods to evaluate the effectiveness of management actions.