Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Keyword
-
- Classification (2)
- Benthic habitat mapping (1)
- Chlorophyll-a (1)
- Coral (1)
- Coral detection (1)
-
- Coral reef change detection (1)
- Deep Learning (1)
- Deepwater Horizon (1)
- Dust (1)
- Eddy (1)
- Endangered species (1)
- Image analysis (1)
- Landsat (1)
- Landsat 8 (1)
- MODIS; OC-CCI (1)
- Machine learning (1)
- Marine (1)
- Nekton (1)
- Object Detection (1)
- Oil spill (1)
- Optical oceanography (1)
- Plant canopies (1)
- Red Sea (1)
- Remote Sensing (1)
- SVM (1)
- Satellite remote sensing (1)
- Seagrasses (1)
- Spawning (1)
- Spectral signature expansion (1)
- Publication
- Publication Type
Articles 1 - 8 of 8
Full-Text Articles in Marine Biology
Using Deep Learning And Uav Imagery To Detect Elkhorn Coral In St. Croix’S East End Marine Park, Samuel Wyatt
Using Deep Learning And Uav Imagery To Detect Elkhorn Coral In St. Croix’S East End Marine Park, Samuel Wyatt
Master's Theses
Elkhorn coral, or Acropora palmata, is an important reef building species that promotes species abundance and other ecological services to the communities in the US Virgin Islands. We captured high resolution imagery of a reef in St. Croix’s East End Marine Park using a Wingtra One UAV. We then used deep learning techniques to detect individual coral colonies. We compared two deep learning models, FasterRCNN and MaskRCNN, and found that the models achieved accuracy shores up to 0.78. These scores improved when examining only larger corals in shallow waters. The model was able to both detect Elkhorn coral and …
Coral Reef Change Detection In Remote Pacific Islands Using Support Vector Machine Classifiers, Justin J. Gapper, Hesham El-Askary, Erik Linstead, Thomas Piechota
Coral Reef Change Detection In Remote Pacific Islands Using Support Vector Machine Classifiers, Justin J. Gapper, Hesham El-Askary, Erik Linstead, Thomas Piechota
Mathematics, Physics, and Computer Science Faculty Articles and Research
Despite the abundance of research on coral reef change detection, few studies have been conducted to assess the spatial generalization principles of a live coral cover classifier trained using remote sensing data from multiple locations. The aim of this study is to develop a machine learning classifier for coral dominated benthic cover-type class (CDBCTC) based on ground truth observations and Landsat images, evaluate the performance of this classifier when tested against new data, then deploy the classifier to perform CDBCTC change analysis of multiple locations. The proposed framework includes image calibration, support vector machine (SVM) training and tuning, statistical assessment …
Evaluation Of Spatial Generalization Characteristics Of A Robust Classifier As Applied To Coral Reef Habitats In Remote Islands Of The Pacific Ocean, Justin J. Gapper, Hesham El-Askary, Erik J. Linstead, Thomas Piechota
Evaluation Of Spatial Generalization Characteristics Of A Robust Classifier As Applied To Coral Reef Habitats In Remote Islands Of The Pacific Ocean, Justin J. Gapper, Hesham El-Askary, Erik J. Linstead, Thomas Piechota
Mathematics, Physics, and Computer Science Faculty Articles and Research
This study was an evaluation of the spectral signature generalization properties of coral across four remote Pacific Ocean reefs. The sites under consideration have not been the subject of previous studies for coral classification using remote sensing data. Previous research regarding using remote sensing to identify reefs has been limited to in-situ assessment, with some researchers also performing temporal analysis of a selected area of interest. This study expanded the previous in-situ analyses by evaluating the ability of a basic predictor, Linear Discriminant Analysis (LDA), trained on Depth Invariant Indices calculated from the spectral signature of coral in one location …
Synergistic Use Of Remote Sensing And Modeling To Assess An Anomalously High Chlorophyll-A Event During Summer 2015 In The South Central Red Sea, Wenzhao Li, Hesham El-Askary, K. P. Manikandan, Mohamed A. Qurban, Michael J. Garay, Olga V. Kalishnikova
Synergistic Use Of Remote Sensing And Modeling To Assess An Anomalously High Chlorophyll-A Event During Summer 2015 In The South Central Red Sea, Wenzhao Li, Hesham El-Askary, K. P. Manikandan, Mohamed A. Qurban, Michael J. Garay, Olga V. Kalishnikova
Mathematics, Physics, and Computer Science Faculty Articles and Research
An anomalously high chlorophyll-a (Chl-a) event (>2 mg/m3) during June 2015 in the South Central Red Sea (17.5° to 22°N, 37° to 42°E) was observed using Moderate Resolution Imaging Spectroradiometer (MODIS) data from the Terra and Aqua satellite platforms. This differs from the low Chl-a values (<0.5 mg/m3) usually encountered over the same region during summertime. To assess this anomaly and possible causes, we used a wide range of oceanographical and meteorological datasets, including Chl-a concentrations, sea surface temperature (SST), sea surface height (SSH), mixed layer depth (MLD), ocean current velocity and aerosol optical depth (AOD) obtained from different sensors and models. Findings confirmed this anomalous behavior in the spatial domain using Hovmöller data analysis techniques, while a time series analysis addressed monthly and daily variability. Our analysis suggests that a combination of factors controlling nutrient supply contributed to the anomalous phytoplankton growth. These factors include horizontal transfer of upwelling water through eddy circulation and possible mineral fertilization from atmospheric dust deposition. Coral reefs might have provided extra nutrient supply, yet this is out of the scope of our analysis. We thought that dust deposition from a coastal dust jet event in late June, coinciding with the phytoplankton blooms in the area under investigation, might have also contributed as shown by our AOD findings. However, a lag cross correlation showed a two- month lag between strong dust outbreak and the high Chl-a anomaly. The high Chl-a concentration at the edge of the eddy emphasizes the importance of horizontal advection in fertilizing oligotrophic (nutrient poor) Red Sea waters.
A Case Study In The Effectiveness Of Marine Protected Areas (Mpas): The Islands Of Bonaire And Curacao, Dutch Caribbean, Noelle J. Relles
A Case Study In The Effectiveness Of Marine Protected Areas (Mpas): The Islands Of Bonaire And Curacao, Dutch Caribbean, Noelle J. Relles
Dissertations, Theses, and Masters Projects
The islands of Bonaire and Curacao, Dutch Caribbean, were both mapped along their leeward coasts for dominant coral community and other benthic cover in the early 1980s. This mapping effort offers a unique baseline for comparing changes in the benthic community of the two islands since that time, particularly given the marked differences between the two islands. Bonaire is well-protected and completely surrounded by a marine protected area (MPA), which includes two no-diving marine reserves; additionally, Bonaire's population is only around 15,000. In contrast, the island of Curacao is home to 140,000 inhabitants and marine protection is limited, with a …
Potential Impacts Of The Deepwater Horizon Oil Spill On Large Pelagic Fishes, Sarah Frias-Torres, Charles R. Bostater
Potential Impacts Of The Deepwater Horizon Oil Spill On Large Pelagic Fishes, Sarah Frias-Torres, Charles R. Bostater
Ocean Engineering and Marine Sciences Faculty Publications
Biogeographical analyses provide insights on how the Deepwater Horizon oil spill impacted large pelagic fishes. We georeferenced historical ichthyoplankton surveys and published literature to map the spawning and larval areas of bluefin tuna, swordfish, blue marlin and whale shark sightings in the Gulf of Mexico with daily satellite-derived images detecting surface oil. The oil spill covered critical areas used by large pelagic fishes. Surface oil was detected in 100% of the northernmost whale shark sightings, in 32.8 % of the bluefin tuna spawning area and 38 % of the blue marlin larval area. No surface oil was detected in the …
A Bio-Optical Model For Syringodium Filiforme Canopies, Margaret A. Stoughton
A Bio-Optical Model For Syringodium Filiforme Canopies, Margaret A. Stoughton
OES Theses and Dissertations
Seagrasses are significant ecological and biogeochemical agents in shallow water ecosystems throughout the world. In many regions, seagrass meadows occupy a sufficient fraction of the coastal zone, and generate optical signatures that can be observed from space. Bio-optical models of light absorption and scattering by submerged plant canopies for certain species such as Thalassia testudinum and Zostera marina have successfully modeled the plane irradiance distribution and photosynthesis within the submerged canopies. Syringodium filiforme differs &om T. testudinttm and Z marina, in leaf morphology and canopy architecture. The objective of this study was to develop a radiative transfer model that …
Movements And Behavior Of Wild And Head-Started Sea Turtles, John A. Keinath
Movements And Behavior Of Wild And Head-Started Sea Turtles, John A. Keinath
Dissertations, Theses, and Masters Projects
Flipper-tagging, aerial surveys, and satellite telemetry was used to investigate the occurrence, migratory routes, distances traveled, swimming speeds, diving behavior, and the relation of water temperature to movements and timing of migration of wild loggerhead (Caretta caretta) and Kemp's ridley (Lepidochelys kempii) sea turtles. The behavior and movements of head-started loggerhead turtles was investigated with satellite telemetry and compared to wild turtles. Flipper-tagged loggerhead and Kemp's ridley turtles inhabit Chesapeake Bay during the warm months and many return in subsequent seasons. Aerial surveys showed that loggerhead turtles migrate from south of Cape Hatteras to northern waters during May and June, …