This data set comprises a 10m resolution GeoTIFF raster stack containing multiple topographical variables for the Hawaiian Islands (elevation, aspect, slope, geomorphon landform classification, and hillshade). 10-meter resolution 5 band GeoTIFF includes the following topographical layers: • Elevation (m) • Slope (degrees) • Aspect (degrees) • Geomorphon (integer values) landform classification (1-flat, 2-peak, 3-ridge, 4-shoulder, 5-spur, 6-slope, 7-hollow, 8-footslope, 9-valley, 10-pit) • Hillshade (integer values)

This data set comprises a 30 m resolution GeoTIFF raster stack containing multiple ecological/climatic variables that describe natural habitats across the Hawaiian Islands (vegetation height, habitat quality, and mean annual temperature and rainfall). This 30 meter resolution 4-band GeoTIFF includes the following topographical layers: • Habitat Status: Vegetation status, or degree of disturbance, to plant communities on the main Hawaiian Islands. • Forest Height (in meters) • Mean Annual Temperature (MAT) and • Mean Annual Precipication (MAP) based on monthly rasters aggregated to mean annual values for the last 10 years (2015-2024).

This data release comprises a collection of high-resolution environmental raster data for the Hawaiian Islands, developed to support conservation planning and ecological research. The collection includes both 30-meter and 10-meter resolution GeoTIFFs with topographical variables (elevation, aspect, slope, hillshade, and geomorphon landform classification), as well as complementary ecological variables (vegetation height, habitat quality, and mean annual temperature and rainfall). All rasters have been processed to share consistent resolution, extent, and projection (WGS84), making them readily integrated into spatial analyses and tool development. The primary source data for the topographical variables was the USGS National Map. The dataset provides standardized environmental layers that can be used to identify suitable microhabitats for species conservation, restoration site selection, and ecological modeling across the Hawaiian archipelago. This data release is divided into 3 files: -a 10m resolution GeoTIFF raster stack containing multiple topographical variables for the Hawaiian Islands (elevation, aspect, slope, hillshade, and geomorphon landform classification). -a 30m resolution GeoTIFF raster stack containing multiple topographical variables for the Hawaiian Islands (elevation, aspect, slope, hillshade, and geomorphon landform classification). -a 30m resolution GeoTIFF raster stack containing multiple ecological/climatic variables that describe natural habitats across the Hawaiian Islands (vegetation height, habitat quality, mean annual temperature and rainfall).

This dataset provides high-resolution, species-specific land cover maps for the Hawaiian island of Lāna'i based on 2020 WorldView-2 satellite imagery. Machine learning models were trained on extensive ground control polygons and points. The land cover maps capture the distribution and diversity of vegetation with high accuracy to support conservation planning and monitoring. This data release consists of two child items, one containing the field and expert collected ground control data used to train our models, and another consisting of resulting land cover maps for the island of Lāna‘i. The research effort that generated these input data, and products are carefully described in the associated manuscript Berio Fortini et al. 2024. Full citation is listed in the larger work section of this XML file. Inputs included in this page include: Ground control polygons used for model training and evaluation (ground_control_polygons.gpkg): This dataset consists of refined vegetation polygons digitized across the island of Lāna‘i representing the 15 land cover classes of interest. High-resolution aerial imagery and extensive field experience were used to iteratively collect and improve the polygons through expert review and interpretation. The polygons were divided into a 250m grid overlaying the island to balance sample size and spatial resolution while reducing spatial autocorrelation, resulting in 1,754 smaller polygons. These polygon data served as the primary dataset used to train, validate, and evaluate the classification models through cross-validation. An iterative collection process aimed to achieve satisfactory model accuracy across all classes prior to final model selection and island-wide mapping. Ground control points used for independent pixel-level model validation (ground_control_points.gpkg): This dataset consists of 313 points distributed across the 15 vegetation classes on the island of Lāna‘i. The points were randomly generated from the final species-specific land cover classification map and stratified by class to ensure representation across all classes. The dataset provides species-specific land cover labels for the 313 points, with the spatial location corresponding to the pixel coordinate location on the 2m resolution land cover map. Comparing modeled class assignments to these expert-validated classes enables an independent accuracy assessment supplemental to the polygon-based cross-validation accuracy evaluation.

This data set consists of ground control polygons used for model training and evaluation (ground_control_polygons.gpkg): This dataset consists of refined vegetation polygons digitized across the island of Lāna‘i representing the 15 land cover classes of interest. High-resolution aerial imagery and extensive field experience were used to iteratively collect and improve the polygons through expert review and interpretation. The polygons were divided into a 250m grid overlaying the island to balance sample size and spatial resolution while reducing spatial autocorrelation, resulting in 1,754 smaller polygons. These polygon data served as the primary dataset used to train, validate, and evaluate the classification models through cross-validation. An iterative collection process aimed to achieve satisfactory model accuracy across all classes prior to final model selection and island-wide mapping.

Digital elevation model (DEM) data are arrays of regularly spaced elevation values referenced horizontally either to a Universal Transverse Mercator (UTM) projection or to a geographic coordinate system. The grid cells are spaced at regular intervals along south to north profiles that are ordered from west to east. The U.S. Geological Survey (USGS) produces five primary types of elevation data: 7.5-minute DEM, 30-minute DEM, 1-degree DEM. These datasets were derived from USGS 7.5' DEM Quads for the main 8 Hawaiian Islands. Individual DEM quads were converted to a common datum, and vertical unit, and subsequently mosaicked in ArcGIS 9.x. The DEM for Hawaii (Big Island) has a coordinate system of NAD83 UTM5N. The DEM for the remaining 7 islands (Maui, Kahoolawe, Lanai, Molokai, Oahu, Kauai and Niihau) have a coordinate system of NAD83 UTM4N. All rasters have a spatial resolution of 10 meters and are in the ESRI grid format. On this metadata sheet, the bounding coordinates and row and column counts are for a hypothetical 10m grid that would contain the 8 main Hawaiian Islands. For bounding coordinates and the number of rows and columns for each actual, individual DEM, users should consult their respective layer properties.

This dataset provides high-resolution, species-specific land cover maps for the Hawaiian island of Lāna'i based on 2020 WorldView-2 satellite imagery. Machine learning models were trained on extensive ground control polygons and points. The land cover maps capture the distribution and diversity of vegetation with high accuracy to support conservation planning and monitoring. This data release consists of two child items, one containing the field and expert collected ground control data used to train our models, and another consisting of resulting land cover maps for the island of Lāna‘i. The research effort that generated these input data, and products are carefully described in the associated manuscript Berio Fortini et al. 2024. Full citation is listed in the larger work section of this XML file. Inputs: Ground control polygons used for model training and evaluation Ground control points used for independent pixel-level model validation Outputs: Raster 1. Species-specific land cover map for the island of Lāna‘i, based on expert-adjusted class posterior probabilities. Raster 2. Community-specific land cover map for the island of Lāna‘i, based on land cover classification including expert-adjusted class posterior probabilities. Raster 3. Mixed hierarchical land cover map for the island of Lāna‘i, based on land cover classification including expert-adjusted class posterior probabilities. Raster 4 (stack) Individual cover class membership probability maps.

This dataset provides high-resolution, species-specific land cover maps for the Hawaiian island of Lāna'i based on 2020 WorldView-2 satellite imagery. Machine learning models were trained on extensive ground control polygons and points. The land cover maps capture the distribution and diversity of vegetation with high accuracy to support conservation planning and monitoring. This data release consists of two child items, one containing the field and expert collected ground control data used to train our models, and another consisting of resulting land cover maps for the island of Lāna‘i. The research effort that generated these input data, and products are carefully described in the associated manuscript Berio Fortini et al. 2024. Full citation is listed in the larger work section of this XML file. Outputs included in this page include: Map 1 - Species-specific land cover map: This raster depicts the distribution of 15 species-specific vegetation classes across the island of Lāna‘i at 2m resolution. It represents the final selected neural network model predictions with expert-adjusted posterior probabilities. Each pixel is assigned to the most likely species-specific class based on the model. Overall and class-specific accuracy assessments indicate this map has generally over 95% accuracy. It provides detailed species-level vegetation mapping to support conservation planning and monitoring. Map 2 - Community-specific land cover map: This raster depicts the distribution of broader community-level vegetation classes across Lāna‘i. To generate this map, the species-specific class probabilities were summed to get total probability of membership in each defined community class. Each pixel was then assigned to the community class with the highest probability. This generalized map allows for an assessment of vegetation patterns at a coarser categorical level across the island. Map 3 - Mixed hierarchical land cover map: This raster integrates the species-specific and community classifications using a hierarchical approach based on classification certainty. A 0.66 probability threshold was applied, with pixels assigned the finest species-specific class as long as the probability exceeded the threshold. Pixels below the threshold were assigned to the broader community class meeting the threshold. This approach displays the most detailed class possible given a minimum confidence, providing a map that balances specificity and certainty. Map 4 - Class membership probability maps: This raster stack contains 15 probability layers representing the pixel-level predicted probability of membership in each species-specific vegetation class from 0 to 1. These probability layers can be used to generate class membership uncertainty maps or probabilistic class cover maps from the model outputs. They provide additional information beyond the discrete categorial land cover assignments. Please note that to reduce the inherent 'salt and pepper' noise in the final land cover classification maps above, we applied a 3x3 pixel moving window majority filter to the final classification results.

This dataset provides high-resolution, species-specific land cover maps for the Hawaiian island of Lāna'i based on 2020 WorldView-2 satellite imagery. Machine learning models were trained on extensive ground control polygons and points. The land cover maps capture the distribution and diversity of vegetation with high accuracy to support conservation planning and monitoring. This data release consists of two child items, one containing the field and expert collected ground control data used to train our models, and another consisting of resulting land cover maps for the island of Lāna‘i. The research effort that generated these input data, and products are carefully described in the associated manuscript Berio Fortini et al. 2024. Full citation is listed in the larger work section of this XML file. Inputs: Ground control polygons used for model training and evaluation Ground control points used for independent pixel-level model validation Outputs: Raster 1. Species-specific land cover map for the island of Lāna‘i, based on expert-adjusted class posterior probabilities. Raster 2. Community-specific land cover map for the island of Lāna‘i, based on land cover classification including expert-adjusted class posterior probabilities. Raster 3. Mixed hierarchical land cover map for the island of Lāna‘i, based on land cover classification including expert-adjusted class posterior probabilities. Raster 4 (stack) Individual cover class membership probability maps.

This data set consists of ground control points used for independent pixel-level model validation (ground_control_points.gpkg): This dataset consists of 295 points distributed across the 15 vegetation classes on the island of Lāna‘i. The points were randomly generated from the final species-specific land cover classification map and stratified by class to ensure representation across all classes. The dataset provides species-specific land cover labels for the points, with the spatial location corresponding to the pixel coordinate location on the 2m resolution land cover map. Comparing modeled class assignments to these expert-validated classes enables an independent accuracy assessment supplemental to the polygon-based cross-validation accuracy evaluation.