Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter, bathymety derivatives, and bathymetry derived from multispectral World View-2 satellite imageryof Ni'ihau Island, Hawaii, USA . The dataset was derived using Reson 8101 backscatter data, bathymetric variance and bathymetric rugosity. The sonar frequency is 240 kHz for the Reson 8101 backscatter data, which were resampled to a 5 m grid cell size prior to the classification. Limited seafloor photographs for groundtruthing are available for Ni'ihau Island and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map.

Preliminary hard and soft seafloor substrate map derived from a supervised classification from multispectral World View-2 satellite imagery of Ni'ihau Island, Territory of Main Hawaiian Islands, USA. The dataset was derived using multipectral World View-2 satellite data. Limited groundtruthing data are available for Ni'ihau Island and therefore we are unable to evaluate the accuracy of the supervised classification seafloor substrate map.

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymety derivatives at Ofu and Olosega Islands, Territory of American Samoa, USA . The dataset was derived using Reson 8101 backscatter data, bathymetric variance and bathymetric rugosity. The sonar frequency is 240 kHz for the Reson 8101 backscatter data, which were resampled to a 5 m grid cell size prior to the classification. Limited seafloor photographs for groundtruthing are available for Ofu and Olosega Islands and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments.

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymety derivatives at Ta'u Island, Territory of American Samoa, USA . The dataset was derived using Reson 8101 backscatter data, bathymetric variance and bathymetric rugosity. The sonar frequency is 240 kHz for the Reson 8101 backscatter data, which were resampled to a 5 m grid cell size prior to the classification. Limited seafloor photographs for groundtruthing are available for Ta'u and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments.

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymetry derivatives at Swains Island, Territory of American Samoa, USA. The dataset was created from gridded (40 m cell size) multibeam bathymetry derivatives collected aboard R/V AHI, and NOAA ship Hi'ialakai; 2 scales of bathymetric variance and bathymetric rugosity. Backscatter data were from a 300 kHz Simrad EM300 and a 240 kHz Reson 8101 sonar, gridded at 5 m. Very limited seafloor photographs for groundtruthing are available for Swains Island and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments. Since groundtruthing was not used to validate the unsupervised classification at Swains Island extreme caution should be used when examining these data to locate habitat of biological significance. The map should be used in conjunction with bathymetric derivatives such as rugosity, slope, and Bathymetric Position Index (BPI).

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymetry derivatives at Rose Atoll, Territory of American Samoa, USA. The dataset was created from gridded (40 m cell size) multibeam bathymetry derivatives collected aboard R/V AHI; 2 scales of bathymetric variance and bathymetric rugosity, and from multibeam backscatter. Backscatter data were from a 30 kHz Simrad EM300 sonar, gridded at 5 m. Very limited seafloor photographs for groundtruthing are available for Rose Atoll and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments. Since groundtruthing was not used to validate the unsupervised classification at Rose Atoll extreme caution should be used when examining these data to locate habitat of biological significance. The map should be used in conjunction with bathymetric derivatives such as rugosity, slope, and Bathymetric Position Index (BPI).

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymetry derivatives at Rose Atoll Lagoon, Territory of American Samoa, USA. The dataset was created from gridded (5 m cell size) multibeam bathymetry derivatives collected aboard R/V AHI; 2 scales of bathymetric variance and bathymetric rugosity, and from multibeam backscatter. Backscatter data were from a 240 kHz Reson 8101 sonar, gridded at 5 m. Very limited seafloor photographs for groundtruthing are available for Rose Atoll and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments. Since groundtruthing was not used to validate the unsupervised classification at Rose Atoll Lagoon extreme caution should be used when examining these data to locate habitat of biological significance. The map should be used in conjunction with bathymetric derivatives such as rugosity, slope, and Bathymetric Position Index (BPI).

Preliminary hard and soft seafloor substrate map derived from an unsupervised classification of multibeam backscatter and bathymety derivatives at the U.S. Territory of Guam. The dataset was derived using Reson 8101 backscatter data, bathymetric variance and bathymetric rugosity. The sonar frequency is 240 kHz for the Reson 8101 backscatter data, which were resampled to a 5 m grid cell size prior to the classification. Limited seafloor photographs for groundtruthing are available for Guam and therefore no supervised classification was performed and we are unable to visually or empirically evaluate the accuracy of the unsupervised classification seafloor substrate map. However, in locations such French Frigate Shoals, NWHI and Tutuila, American Samoa, where ground truth data are available, the unsupervised classification method is a robust predictor of substrate type in similar depth ranges and seafloor environments.