Filters: Tags: Hawai'i (X) > Date Range: {"choice":"month"} (X)
8 results (76ms)|
Filters
Date Types (for Date Range)
Types Contacts
Categories Tag Types Tag Schemes |
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...
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...
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. Please note that to reduce the inherent 'salt and pepper' noise in the final land cover classification map, we applied a 3x3 pixel moving window majority filter to the final classification results.
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. Please note that to reduce the inherent 'salt and pepper' noise in the final land cover classification map, we applied a 3x3 pixel moving window majority filter to the final classification results.
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.
Categories: Data;
Types: Downloadable,
GeoTIFF,
Map Service,
Raster;
Tags: Conservation,
Hawaiian Islands,
Hawai‘i,
Invasive species,
Land cover,
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...
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...
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. Please note that to reduce the inherent 'salt and pepper' noise in the final land cover classification map, we applied a 3x3 pixel moving window majority filter to the final classification results.
|
|
