UAS-multisensor input imagery and random forest classification products for mapping vegetation species at a tallgrass prairie in Urbana, IL
Fuente:
PANGAEA
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Dataset Open Access |
| Lingua: | en |
| Pubblicazione: |
PANGAEA
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1867170124228722688 |
|---|---|
| author | Hall, Emma Lara, Mark J |
| author_facet | Hall, Emma Lara, Mark J |
| collection | Datos científicos de ciencias marinas y ambientales |
| contents | Three mosaic raster files are provided depicting Uncrewed Aerial Systems (UAS) data collection from RGB, multispectral, and hyperspectral sensors, which were collected at Weaver Park in Urbana, IL. Along with spectral bands, all image products are fused with canopy height models (CHM), where RGB and multispectral products are fused with an SfM-derived (structure from motion) CHM and the hyperspectral product is fused with a LiDAR-derived (Light Detection and Ranging) CHM. A multispectral phenological time series product is also provided, where Normalized Difference Vegetation Index (NDVI) was calculated across six time periods in one growing season and where an additional 15 NDVI-derived metrics were calculated, resulting in a 21-band image product. Differential GPS (dGPS; 2cm resolution) data identifying vegetation species are also provided, which were used at the training and testing datasets for conducting random forest classifications on each image product. Random forest classification models were applied to each of the three UAS-sensor types both with and without CHM fusion, and to the multispectral phenology time series image, resulting in the 7 vegetation maps provided. |
| format | Dataset Open Access |
| id | pangaea_https___doi_org_10_1594_PANGAEA_967351 |
| institution | PANGAEA |
| language | en |
| publishDate | 2024 |
| publisher | PANGAEA |
| record_format | pangaea |
| spellingShingle | UAS-multisensor input imagery and random forest classification products for mapping vegetation species at a tallgrass prairie in Urbana, IL Hall, Emma Lara, Mark J Binary Object; Binary Object (File Size); File content; hyperspectral; Lidar; Multispectral; phenology; Random forest classification; Tallgrass Prairie; Time series; UAS; Uncrewed Aerial System; Urbana_IL_UAS; Vegetation Mapping Three mosaic raster files are provided depicting Uncrewed Aerial Systems (UAS) data collection from RGB, multispectral, and hyperspectral sensors, which were collected at Weaver Park in Urbana, IL. Along with spectral bands, all image products are fused with canopy height models (CHM), where RGB and multispectral products are fused with an SfM-derived (structure from motion) CHM and the hyperspectral product is fused with a LiDAR-derived (Light Detection and Ranging) CHM. A multispectral phenological time series product is also provided, where Normalized Difference Vegetation Index (NDVI) was calculated across six time periods in one growing season and where an additional 15 NDVI-derived metrics were calculated, resulting in a 21-band image product. Differential GPS (dGPS; 2cm resolution) data identifying vegetation species are also provided, which were used at the training and testing datasets for conducting random forest classifications on each image product. Random forest classification models were applied to each of the three UAS-sensor types both with and without CHM fusion, and to the multispectral phenology time series image, resulting in the 7 vegetation maps provided. |
| title | UAS-multisensor input imagery and random forest classification products for mapping vegetation species at a tallgrass prairie in Urbana, IL |
| topic | Binary Object; Binary Object (File Size); File content; hyperspectral; Lidar; Multispectral; phenology; Random forest classification; Tallgrass Prairie; Time series; UAS; Uncrewed Aerial System; Urbana_IL_UAS; Vegetation Mapping |
| url | https://doi.org/10.1594/PANGAEA.967351 |