你当前正在访问 Microsoft Azure Global Edition 技术文档网站。 如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站,请访问 https://docs.azure.cn。
此库提供现成的配置示例,用于可视化Microsoft行星计算机专业版中的常见地理空间数据类型。 每个示例都包含马赛克、呈现选项、图块设置和 SpatioTemporal 资产目录(STAC)集合元数据的综合 JSON 配置,你可以根据自己的数据集调整这些配置。
目录
Prerequisites
在使用这些示例之前,应具备:
如何使用这些示例
此画廊中的每个示例包括:
- 说明和上下文 - 有关数据源和可视化方法的信息
- 视觉示例 - 资源管理器中呈现数据的屏幕截图
- 完成按选项卡组织的配置设置:
- 马赛克 - 如何筛选和选择要显示的项
- 呈现选项 - 如何设置数据样式和可视化效果
- 图块设置 - 如何优化显示参数
- STAC 集合 - 基础集合元数据结构
若要将这些示例应用于你自己的数据,
Sentinel-2-l2a 集合配置
Sentinel-2 是欧洲航天局(ESA)作为科伯尼库计划一部分的高分辨率多光谱成像任务。
Sentinel-2 配置详细信息
马赛克配置
此拼接配置指示查看器显示集合中最新的 Sentinel-2 图像,但仅限于云覆盖率小于或等于 40%的图像。 公共查询语言 (CQL) 筛选器可确保仅包含相对清晰的图像,从而使可视化效果对大多数应用程序更有用。 每个马赛克条目可以定义用于选择和组合图像的不同条件,此马赛克示例使用一个“默认”马赛克,这些马赛克侧重于最近的低云图像。
[
{
"id": "default",
"name": "Most recent available",
"description": "Most recent available imagery in this Sentinel-2 collection",
"cql": [
{
"op": "<=",
"args": [
{
"property": "eo:cloud_cover"
},
40
]
}
]
}
]
渲染选项配置
此呈现配置定义了在资源管理器中可视化 Sentinel-2 卫星图像的几种方法。 每个条目描述不同的风格或科学产品,如 自然颜色 (你看到的眼睛), 彩色红外 (以突出显示植被),或 规范化差异植被指数(NDVI)( 植被健康指数)。
该 options 字符串指定如何可视化数据:
assets=B04&assets=B03&assets=B02:
此资产参数告知系统要用于图像的带段(卫星数据层)。 例如,B04 为红色,B03 为绿色,B02 为蓝色,它们共同制作真色图像。nodata=0:
任何值为 0 的像素都被视为缺失或透明。color_formula=Gamma RGB 3.2 Saturation 0.8 Sigmoidal RGB 25 0.35:
此伽玛调整应用颜色更正,使图像看起来更自然或更具视觉吸引力。- Gamma 调整亮度
- 饱和 度更改颜色强度
- Sigmoidal 调整对比度
expression=(B08-B04)/(B08+B04):
对于 NDVI 和 NDWI,此表达式参数通过使用波段计算数学公式,以创建能突出显示植被或水分的新图像。rescale=-1,1:
此重新缩放参数拉伸计算值以适应色阶,因此结果易于解释。colormap_name=rdylgn:
此配色图参数将调色板(红色-黄色-绿色)应用于结果,以便更轻松地查看差异。
[
{
"id": "natural-color",
"name": "Natural color",
"description": "True color composite of visible bands (B04, B03, B02)",
"type": "raster-tile",
"options": "assets=B04&assets=B03&assets=B02&nodata=0&color_formula=Gamma RGB 3.2 Saturation 0.8 Sigmoidal RGB 25 0.35",
"minZoom": 9
},
{
"id": "natural-color-pre-feb-2022",
"name": "Natural color (pre Feb, 2022)",
"description": "Pre-Feb 2022 true color composite of visible bands (B04, B03, B02)",
"type": "raster-tile",
"options": "assets=B04&assets=B03&assets=B02&nodata=0&color_formula=Gamma RGB 3.7 Saturation 1.5 Sigmoidal RGB 15 0.35",
"minZoom": 9
},
{
"id": "color-infrared",
"name": "Color infrared",
"description": "Highlights healthy (red) and unhealthy (blue/gray) vegetation (B08, B04, B03).",
"type": "raster-tile",
"options": "assets=B08&assets=B04&assets=B03&nodata=0&color_formula=Gamma RGB 3.7 Saturation 1.5 Sigmoidal RGB 15 0.35",
"minZoom": 9
},
{
"id": "short-wave-infrared",
"name": "Short wave infrared",
"description": "Darker shades of green indicate denser vegetation. Brown is indicative of bare soil and built-up areas (B12, B8A, B04).",
"type": "raster-tile",
"options": "assets=B12&assets=B8A&assets=B04&nodata=0&color_formula=Gamma RGB 3.7 Saturation 1.5 Sigmoidal RGB 15 0.35",
"minZoom": 9
},
{
"id": "agriculture",
"name": "Agriculture",
"description": "Darker shades of green indicate denser vegetation (B11, B08, B02).",
"type": "raster-tile",
"options": "assets=B11&assets=B08&assets=B02&nodata=0&color_formula=Gamma RGB 3.7 Saturation 1.5 Sigmoidal RGB 15 0.35",
"minZoom": 9
},
{
"id": "normalized-difference-veg-inde",
"name": "Normalized Difference Veg. Index (NDVI)",
"description": "Normalized Difference Vegetation Index (B08-B04)/(B08+B04), darker green indicates healthier vegetation.",
"type": "raster-tile",
"options": "nodata=0&expression=(B08-B04)/(B08+B04)&rescale=-1,1&colormap_name=rdylgn&asset_as_band=true",
"minZoom": 9
},
{
"id": "moisture-index-ndwi",
"name": "Moisture Index (NDWI)",
"description": "Index indicating water stress in plants (B8A-B11)/(B8A+B11)",
"type": "raster-tile",
"options": "nodata=0&expression=(B8A-B11)/(B8A+B11)&rescale=-1,1&colormap_name=rdbu&asset_as_band=true",
"minZoom": 9
},
{
"id": "atmospheric-penetration",
"name": "Atmospheric penetration",
"description": "False color rendering with non-visible bands to reduce effects of atmospheric particles (B12, B11, B8A).",
"type": "raster-tile",
"options": "nodata=0&assets=B12&assets=B11&assets=B8A&color_formula=Gamma RGB 3.7 Saturation 1.5 Sigmoidal RGB 15 0.35",
"minZoom": 9
}
]
图块设置配置
磁贴设置的配置控制 Explorer 中 Sentinel-2 图像的显示模式和性能表现。
关键参数:
minZoom: 8:设置 Sentinel-2 图像可见的最小缩放级别。 这种中等缩放级别设置适用于 Sentinel-2 的分辨率(大多数带为 10 米,某些带为 20 米,大气带为 60 米),使图像可用于从缩放级别 8-12 开始的区域到局部缩放分析。maxItemsPerTile: 35:控制每个图块中可以组合多少个单独的 Sentinel-2 场景。 此组合设置平衡性能与临时覆盖完整性,确保可以组合多个场景以获得更好的覆盖,同时保持呈现性能。defaultLocation: null:未指定默认位置,允许用户全局导航到任何感兴趣的区域。
此磁贴设置配置优化 Sentinel-2 中等分辨率图像的数据可见性和性能之间的平衡,使其适用于各种应用程序,从区域监视到详细的本地分析。
{
"minZoom": 8,
"maxItemsPerTile": 35,
"defaultLocation": null
}
STAC 收集配置
STAC 集合配置定义此 Sentinel-2 集合的核心元数据。
item_assets STAC 集合 JSON 中的部分充当集合中所有可用数据资产的关键目录。 它定义每个光谱带(B01-B12、B8A 等)及其属性,包括:
- 渲染配置引用的资产键值(如“B04”、“B03”)
- 有关每个带的元数据(分辨率、数据类型、角色)
- 用于解释每个波段所代表的波段描述(B04 是“红色”,B08 是“近红外”)
- 适用于科学应用的波形信息
呈现配置直接引用这些资产键来创建不同的可视化效果。 例如,当渲染配置指定 assets=B04&assets=B03&assets=B02时,它会从项目资源中抽取红色、绿色和蓝色带,以创建自然色彩图像。
{
"id": "sentinel-2-l2a_Grindavik",
"type": "Collection",
"links": [
{
"rel": "items",
"type": "application/geo+json",
"href": "https://{geocatalog_id}/stac/collections/sentinel-2-l2a_Grindavik/items"
},
{
"rel": "parent",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "root",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "self",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/collections/sentinel-2-l2a_Grindavik"
},
{
"rel": "license",
"href": "https://scihub.copernicus.eu/twiki/pub/SciHubWebPortal/TermsConditions/Sentinel_Data_Terms_and_Conditions.pdf",
"title": "Copernicus Sentinel data terms"
},
{
"rel": "describedby",
"href": "https://planetarycomputer.microsoft.com/dataset/sentinel-2-l2a",
"type": "text/html",
"title": "Human readable dataset overview and reference"
}
],
"title": "Sentinel-2-l2a",
"assets": {
"thumbnail": {
"href": "https://{storage_account}.blob.core.windows.net/{blob_container}/collection-assets/thumbnail/blob",
"type": "image/png",
"roles": [
"thumbnail"
],
"title": "sentinel-2-l2a_Grindavik thumbnail"
}
},
"extent": {
"spatial": {
"bbox": [
[
-180,
-90,
180,
90
]
]
},
"temporal": {
"interval": [
[
"2015-06-27T10:25:31Z",
null
]
]
}
},
"license": "proprietary",
"keywords": [
"Sentinel",
"Copernicus",
"ESA",
"Satellite",
"Global",
"Imagery",
"Reflectance"
],
"providers": [
{
"url": "https://sentinel.esa.int/web/sentinel/missions/sentinel-2",
"name": "ESA",
"roles": [
"producer",
"licensor"
]
},
{
"url": "https://www.esri.com/",
"name": "Esri",
"roles": [
"processor"
]
},
{
"url": "https://planetarycomputer.microsoft.com",
"name": "Microsoft",
"roles": [
"host",
"processor"
]
}
],
"summaries": {
"gsd": [
10,
20,
60
],
"eo:bands": [
{
"name": "AOT",
"description": "aerosol optical thickness"
},
{
"gsd": 60,
"name": "B01",
"common_name": "coastal",
"description": "coastal aerosol",
"center_wavelength": 0.443,
"full_width_half_max": 0.027
},
{
"gsd": 10,
"name": "B02",
"common_name": "blue",
"description": "visible blue",
"center_wavelength": 0.49,
"full_width_half_max": 0.098
},
{
"gsd": 10,
"name": "B03",
"common_name": "green",
"description": "visible green",
"center_wavelength": 0.56,
"full_width_half_max": 0.045
},
{
"gsd": 10,
"name": "B04",
"common_name": "red",
"description": "visible red",
"center_wavelength": 0.665,
"full_width_half_max": 0.038
},
{
"gsd": 20,
"name": "B05",
"common_name": "rededge",
"description": "vegetation classification red edge",
"center_wavelength": 0.704,
"full_width_half_max": 0.019
},
{
"gsd": 20,
"name": "B06",
"common_name": "rededge",
"description": "vegetation classification red edge",
"center_wavelength": 0.74,
"full_width_half_max": 0.018
},
{
"gsd": 20,
"name": "B07",
"common_name": "rededge",
"description": "vegetation classification red edge",
"center_wavelength": 0.783,
"full_width_half_max": 0.028
},
{
"gsd": 10,
"name": "B08",
"common_name": "nir",
"description": "near infrared",
"center_wavelength": 0.842,
"full_width_half_max": 0.145
},
{
"gsd": 20,
"name": "B8A",
"common_name": "rededge",
"description": "vegetation classification red edge",
"center_wavelength": 0.865,
"full_width_half_max": 0.033
},
{
"gsd": 60,
"name": "B09",
"description": "water vapor",
"center_wavelength": 0.945,
"full_width_half_max": 0.026
},
{
"gsd": 20,
"name": "B11",
"common_name": "swir16",
"description": "short-wave infrared, snow/ice/cloud classification",
"center_wavelength": 1.61,
"full_width_half_max": 0.143
},
{
"gsd": 20,
"name": "B12",
"common_name": "swir22",
"description": "short-wave infrared, snow/ice/cloud classification",
"center_wavelength": 2.19,
"full_width_half_max": 0.242
}
],
"platform": [
"Sentinel-2A",
"Sentinel-2B"
],
"instruments": [
"msi"
],
"constellation": [
"sentinel-2"
],
"view:off_nadir": [
0
]
},
"description": "The [Sentinel-2](https://sentinel.esa.int/web/sentinel/missions/sentinel-2) program provides global imagery in thirteen spectral bands at 10m-60m resolution and a revisit time of approximately five days. This dataset represents the global Sentinel-2 archive, from 2016 to the present, processed to L2A (bottom-of-atmosphere) using [Sen2Cor](https://step.esa.int/main/snap-supported-plugins/sen2cor/) and converted to [cloud-optimized GeoTIFF](https://www.cogeo.org/) format.",
"item_assets": {
"AOT": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Aerosol optical thickness (AOT)"
},
"B01": {
"gsd": 60,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 1 - Coastal aerosol - 60m",
"eo:bands": [
{
"name": "B01",
"common_name": "coastal",
"description": "Band 1 - Coastal aerosol",
"center_wavelength": 0.443,
"full_width_half_max": 0.027
}
]
},
"B02": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 2 - Blue - 10m",
"eo:bands": [
{
"name": "B02",
"common_name": "blue",
"description": "Band 2 - Blue",
"center_wavelength": 0.49,
"full_width_half_max": 0.098
}
]
},
"B03": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 3 - Green - 10m",
"eo:bands": [
{
"name": "B03",
"common_name": "green",
"description": "Band 3 - Green",
"center_wavelength": 0.56,
"full_width_half_max": 0.045
}
]
},
"B04": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 4 - Red - 10m",
"eo:bands": [
{
"name": "B04",
"common_name": "red",
"description": "Band 4 - Red",
"center_wavelength": 0.665,
"full_width_half_max": 0.038
}
]
},
"B05": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 5 - Vegetation red edge 1 - 20m",
"eo:bands": [
{
"name": "B05",
"common_name": "rededge",
"description": "Band 5 - Vegetation red edge 1",
"center_wavelength": 0.704,
"full_width_half_max": 0.019
}
]
},
"B06": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 6 - Vegetation red edge 2 - 20m",
"eo:bands": [
{
"name": "B06",
"common_name": "rededge",
"description": "Band 6 - Vegetation red edge 2",
"center_wavelength": 0.74,
"full_width_half_max": 0.018
}
]
},
"B07": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 7 - Vegetation red edge 3 - 20m",
"eo:bands": [
{
"name": "B07",
"common_name": "rededge",
"description": "Band 7 - Vegetation red edge 3",
"center_wavelength": 0.783,
"full_width_half_max": 0.028
}
]
},
"B08": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 8 - NIR - 10m",
"eo:bands": [
{
"name": "B08",
"common_name": "nir",
"description": "Band 8 - NIR",
"center_wavelength": 0.842,
"full_width_half_max": 0.145
}
]
},
"B09": {
"gsd": 60,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 9 - Water vapor - 60m",
"eo:bands": [
{
"name": "B09",
"description": "Band 9 - Water vapor",
"center_wavelength": 0.945,
"full_width_half_max": 0.026
}
]
},
"B11": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 11 - SWIR (1.6) - 20m",
"eo:bands": [
{
"name": "B11",
"common_name": "swir16",
"description": "Band 11 - SWIR (1.6)",
"center_wavelength": 1.61,
"full_width_half_max": 0.143
}
]
},
"B12": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 12 - SWIR (2.2) - 20m",
"eo:bands": [
{
"name": "B12",
"common_name": "swir22",
"description": "Band 12 - SWIR (2.2)",
"center_wavelength": 2.19,
"full_width_half_max": 0.242
}
]
},
"B8A": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Band 8A - Vegetation red edge 4 - 20m",
"eo:bands": [
{
"name": "B8A",
"common_name": "rededge",
"description": "Band 8A - Vegetation red edge 4",
"center_wavelength": 0.865,
"full_width_half_max": 0.033
}
]
},
"SCL": {
"gsd": 20,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Scene classification map (SCL)"
},
"WVP": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Water vapour (WVP)"
},
"visual": {
"gsd": 10,
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "True color image",
"eo:bands": [
{
"name": "B04",
"common_name": "red",
"description": "Band 4 - Red",
"center_wavelength": 0.665,
"full_width_half_max": 0.038
},
{
"name": "B03",
"common_name": "green",
"description": "Band 3 - Green",
"center_wavelength": 0.56,
"full_width_half_max": 0.045
},
{
"name": "B02",
"common_name": "blue",
"description": "Band 2 - Blue",
"center_wavelength": 0.49,
"full_width_half_max": 0.098
}
]
},
"preview": {
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"thumbnail"
],
"title": "Thumbnail"
},
"safe-manifest": {
"type": "application/xml",
"roles": [
"metadata"
],
"title": "SAFE manifest"
},
"granule-metadata": {
"type": "application/xml",
"roles": [
"metadata"
],
"title": "Granule metadata"
},
"inspire-metadata": {
"type": "application/xml",
"roles": [
"metadata"
],
"title": "INSPIRE metadata"
},
"product-metadata": {
"type": "application/xml",
"roles": [
"metadata"
],
"title": "Product metadata"
},
"datastrip-metadata": {
"type": "application/xml",
"roles": [
"metadata"
],
"title": "Datastrip metadata"
}
},
"msft:region": "westeurope",
"stac_version": "1.0.0",
"msft:_created": "2024-04-05T19:04:14.168175Z",
"msft:_updated": "2024-08-26T18:24:05.194898Z",
"msft:container": "sentinel2-l2",
"stac_extensions": [
"https://stac-extensions.github.io/item-assets/v1.0.0/schema.json",
"https://stac-extensions.github.io/table/v1.2.0/schema.json"
],
"msft:storage_account": "sentinel2l2a01",
"msft:short_description": "The Sentinel-2 program provides global imagery in thirteen spectral bands at 10m-60m resolution and a revisit time of approximately five days. This dataset contains the global Sentinel-2 archive, from 2016 to the present, processed to L2A (bottom-of-atmosphere)."
}
国家农业图像计划收集配置
国家农业图像计划 (NAIP)在美国提供高分辨率的空中图像。 美国农业部农场服务局至少每三年捕获一次此 NAIP 图像。
NAIP 数据提供出色的细节,空间分辨率从 0.3 米到每像素 1 米不等。 图像以云优化的 GeoTIFF 格式存储,以便高效访问和处理。
每个 NAIP 图像都包含四个光谱带:
- Red
- Green
- Blue
- 近红外 (NIR)
所有四个波段作为单个多波段资产一起存储。 此带状结构支持多种类型的分析:
- 自然颜色可视化 使用 RGB 带(1-3)创建与人眼看到的相似图像
- 彩色红外分析 结合 NIR、红色和绿色波段来评估植被健康
- NDVI 计算方法使用公式 (NIR-Red)/(NIR+Red) 来测量植被的密度和健康状况。
NAIP 配置详细信息
马赛克配置
马赛克配置定义在资源管理器中显示的图像组合方式,此 NAIP 集合使用默认设置。
[
{
"id": "default",
"name": "Default",
"description": "",
"cql": []
}
]
渲染选项配置
此呈现配置定义了在资源管理器中可视化 NAIP 空中图像的三种不同的方法。 每个条目都描述了不同的可视化技术,如 自然色 (用眼睛看到的)、 彩色红外 (以突出显示植被)或 规范化差异植被指数(NDVI)( 测量植被健康)。
NAIP 图像包含四个光谱带存储在名为“image”的单个多带资产中:
- 波段 1:红色
- 波段 2:绿色
- 波段 3:蓝色
- 带 4:近红外(NIR)
该 options 字符串指定如何可视化数据:
assets=image:
此资产参数用于指定从 STAC 项目中选择哪个资产。 对于 NAIP,所有带都存储在单个“图像”资产中。asset_bidx=image|1,2,3:
此 bidx 参数从多带图像中选择要使用的带段,以及如何将它们映射到颜色通道。 例如,1,2,3分别将 1、2 和 3 映射到红色、绿色和蓝色通道。color_formula=Sigmoidal RGB 15 0.35:
此 gamma 参数应用颜色更正以提高视觉外观和对比度。expression=(image_b4 - image_b1)/(image_b4 + image_b1):
对于 NDVI 计算,此表达式公式使用波段来创建一个突出植物健康的植被指数。rescale=-1,1:
此重新缩放参数拉伸计算的 NDVI 值,以适应标准色阶,以便更轻松地解释。colormap_name=rdylgn:
此色图参数将红色-黄色-绿色调色板应用于 NDVI 结果,使植被模式易于识别。
自然色(真色)
-
配置:
"options": "assets=image&asset_bidx=image|1,2,3" -
工作原理:此自然颜色选项将 NAIP 图像的前三个带映射到相应的红色、绿色和蓝色通道以供显示。
- 红色通道:波段 1 (红)
- 绿色通道:波段 2(绿色)
- 蓝色频道:乐队 3 (蓝色)
- 结果:这种自然颜色映射生成一个“真实颜色”图像,该图像近似于人眼看到的内容。
彩色红外
-
配置:
"options": "assets=image&asset_bidx=image|4,1,2&color_formula=Sigmoidal RGB 15 0.35" -
工作原理:此彩色红外选项是一种“假颜色”复合,可用于植被分析。 它按如下方式映射频带:
- 红色通道:带 4 (近红外)
- 绿色通道:频段1(红色)
- 蓝色频道:乐队 2 (绿色)
-
结果:健康植被在近红外光谱中强烈反映,因此在生成的图像中显示为鲜红色。 城市区域或裸土显示为蓝色或灰色。
color_formula用于增加图像的对比度和视觉吸引力。
规范化差异植被指数 (NDVI)
-
配置:
"options": "expression=(image_b4 - image_b1)/(image_b4 + image_b1)&rescale=-1,1&colormap_name=rdylgn" -
工作原理:此 NDVI 选项不直接显示源图像。 相反,它使用数学公式计算每个像素的 NDVI:
(NIR - Red) / (NIR + Red)。 在这种情况下,该计算对应于(Band 4 - Band 1) / (Band 4 + Band 1)。 -
结果:NDVI 计算的结果是 -1 和 1 之间的值,这是植被健康和密度的度量值。 该
rescale=-1,1参数将输出颜色缩放到此 NDVI 范围,参数colormap_name=rdylgn应用“红色-黄色-绿色”颜色映射。 茂密、健康植被的地区显示为绿色,而几乎没有或没有植被的地区出现红色或黄色。
[
{
"id": "natural-color",
"name": "Natural color",
"description": "RGB from visual assets",
"type": "raster-tile",
"options": "assets=image&asset_bidx=image|1,2,3",
"minZoom": 11
},
{
"id": "color-infrared",
"name": "Color infrared",
"description": "Highlights healthy (red) and unhealthy (blue/gray) vegetation.",
"type": "raster-tile",
"options": "assets=image&asset_bidx=image|4,1,2&color_formula=Sigmoidal RGB 15 0.35",
"minZoom": 12
},
{
"id": "ndvi",
"name": "Normalized Difference Veg. Index (NDVI)",
"description": "Normalized Difference Vegetation Index (NIR-Red)/(NIR+Red), darker green indicates healthier vegetation.",
"type": "raster-tile",
"options": "expression=(image_b4 - image_b1)/(image_b4 + image_b1)&rescale=-1,1&colormap_name=rdylgn",
"minZoom": 12
}
]
图块设置配置
图块设置配置控制 Explorer 中 NAIP 航空影像的显示行为和性能特征。
关键参数:
minZoom: 4:设置 NAIP 数据可见的最小缩放级别。 虽然这种低缩放设置允许广泛缩放级别的可见性,但 NAIP(0.3-1 米地面样本距离)等高分辨率图像在缩放级别 12-18 中最为有效,其中各个特征清晰可区分。maxItemsPerTile: 35:限制可以在单个地图图块中组合在一起的 NAIP 图像图块的数量。 此限制设置在性能与覆盖完整性之间寻找平衡,确保多个重叠图像可以被组合,而不会使呈现过程不堪重负。defaultLocation: null:未指定默认位置,允许用户导航到提供 NAIP 覆盖范围的美国任何感兴趣的区域。
此磁贴设置配置优化了广泛可访问性和详细可视化之间的平衡,使用户可以在低缩放级别发现NAIP数据,同时在放大到适当比例时提供最大详细信息,以便进行高分辨率分析。
{
"minZoom": 4,
"maxItemsPerTile": 35,
"defaultLocation": null
}
STAC 收集配置
STAC 集合配置定义此 NAIP 集合的核心元数据。
{
"id": "naip-airports",
"type": "Collection",
"links": [
{
"rel": "items",
"type": "application/geo+json",
"href": "https://{geocatalog_id}/stac/collections/naip-airports/items"
},
{
"rel": "parent",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "root",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "self",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/collections/naip-airports"
},
{
"rel": "license",
"href": "https://www.fsa.usda.gov/help/policies-and-links/",
"title": "Public Domain"
},
{
"rel": "describedby",
"href": "https://planetarycomputer.microsoft.com/dataset/naip",
"type": "text/html",
"title": "Human readable dataset overview and reference"
}
],
"title": "naip-airports",
"assets": {
"thumbnail": {
"href": "https://{storage_account}.blob.core.windows.net/{blob_container}/collection-assets/thumbnail/blob",
"type": "image/png",
"roles": [
"thumbnail"
],
"title": "naip-airports thumbnail"
}
},
"extent": {
"spatial": {
"bbox": [
[
-124.784,
24.744,
-66.951,
49.346
],
[
-156.003,
19.059,
-154.809,
20.127
],
[
-67.316,
17.871,
-65.596,
18.565
],
[
-64.94,
17.622,
-64.56,
17.814
]
]
},
"temporal": {
"interval": [
[
"2010-01-01T00:00:00Z",
"2022-12-31T00:00:00Z"
]
]
}
},
"license": "proprietary",
"keywords": [
"NAIP",
"Aerial",
"Imagery",
"USDA",
"AFPO",
"Agriculture",
"United States"
],
"providers": [
{
"url": "https://www.fsa.usda.gov/programs-and-services/aerial-photography/imagery-programs/naip-imagery/",
"name": "USDA Farm Service Agency",
"roles": [
"producer",
"licensor"
]
},
{
"url": "https://www.esri.com/",
"name": "Esri",
"roles": [
"processor"
]
},
{
"url": "https://planetarycomputer.microsoft.com",
"name": "Microsoft",
"roles": [
"host",
"processor"
]
}
],
"summaries": {
"gsd": [
0.3,
0.6,
1
],
"eo:bands": [
{
"name": "Red",
"common_name": "red",
"description": "visible red"
},
{
"name": "Green",
"common_name": "green",
"description": "visible green"
},
{
"name": "Blue",
"common_name": "blue",
"description": "visible blue"
},
{
"name": "NIR",
"common_name": "nir",
"description": "near-infrared"
}
]
},
"description": "The [National Agriculture Imagery Program](https://www.fsa.usda.gov/programs-and-services/aerial-photography/imagery-programs/naip-imagery/) (NAIP) \nprovides U.S.-wide, high-resolution aerial imagery, with four spectral bands (R, G, B, IR). \nNAIP is administered by the [Aerial Field Photography Office](https://www.fsa.usda.gov/programs-and-services/aerial-photography/) (AFPO) \nwithin the [US Department of Agriculture](https://www.usda.gov/) (USDA). \nData are captured at least once every three years for each state. \nThis dataset represents NAIP data from 2010-present, in [cloud-optimized GeoTIFF](https://www.cogeo.org/) format.\nYou can visualize the coverage of current and past collections [here](https://naip-usdaonline.hub.arcgis.com/). \n",
"item_assets": {
"image": {
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "RGBIR COG tile",
"eo:bands": [
{
"name": "Red",
"common_name": "red"
},
{
"name": "Green",
"common_name": "green"
},
{
"name": "Blue",
"common_name": "blue"
},
{
"name": "NIR",
"common_name": "nir",
"description": "near-infrared"
}
]
},
"metadata": {
"type": "text/plain",
"roles": [
"metadata"
],
"title": "FGDC Metadata"
},
"thumbnail": {
"type": "image/jpeg",
"roles": [
"thumbnail"
],
"title": "Thumbnail"
}
},
"msft:region": "westeurope",
"stac_version": "1.0.0",
"msft:_created": "2024-08-02T13:19:22.446214Z",
"msft:_updated": "2024-08-21T17:21:13.132140Z",
"stac_extensions": [
"https://stac-extensions.github.io/item-assets/v1.0.0/schema.json",
"https://stac-extensions.github.io/table/v1.2.0/schema.json"
],
"msft:short_description": "NAIP provides US-wide, high-resolution aerial imagery. This dataset includes NAIP images from 2010 to the present."
}
Umbra SAR 图像收集配置
Umbra 的合成孔径雷达(SAR)图像 使用从卫星传输的雷达信号来创建地球表面的高分辨率图像,能够穿透云层、黑暗以及阻碍传统光学卫星的天气条件。 这种SAR技术在监测基础设施、检测城市区域的变化、跟踪船舶和车辆以及评估自然灾害后造成的损害方面具有价值,因为它可以在白天或夜间随时捕获详细的图像,与天气条件无关。
SAR 配置详细信息
马赛克配置
此 SAR 集合是默认马赛克配置。
[
{
"id": "default",
"name": "Default",
"description": "",
"cql": []
}
]
渲染选项配置
此呈现配置定义如何在资源管理器中可视化 Umbra SAR 图像。 SAR 图像使用雷达信号来检测表面特征和结构,显示为灰度强度数据,其中较亮的区域表示更强的雷达返回。
该配置侧重于 VV 极化 数据,该数据是指“垂直传输、垂直接收”雷达信号,这些信号可用于检测人工结构和表面粗糙度。
该 options 字符串指定如何可视化数据:
assets=GEC:
此资产参数从 STAC 项中选择了经过地理编码和椭圆体校正的 (GEC) 资产,该资产中包含已处理的 SAR 反向散射数据。rescale=0,255:
此重新缩放参数将雷达反散点值转换为 8 位范围(0-255),以便进行适当的可视化,将原始雷达数据转换为可显示的强度值。colormap_name=gray:
此色图参数应用适用于 SAR 强度数据的灰度调色板,其中较暗的区域表示较弱的雷达返回,较亮的区域表示更强的返回。
可视化效果可创建灰度图像,其中建筑物、崎岖地形和其他表面强烈反射雷达信号看起来明亮,而平滑表面(如水)则显得很暗。
[
{
"id": "vv-polarization",
"name": "VV polarization",
"description": "VV asset scaled to `0,.20`.",
"type": "raster-tile",
"options": "assets=GEC&rescale=0,255&colormap_name=gray",
"minZoom": 8,
"conditions": [
{
"property": "sar:polarizations",
"value": [
"VV"
]
}
]
}
]
图块设置配置
磁贴设置配置控制 Explorer 中 Umbra SAR 图像的显示行为和性能特性。
关键参数:
minZoom: 12:设置 SAR 图像可见的最小缩放级别。 这种相对较高的缩放比例设置适用于 Umbra 的亚米级分辨率数据(大约 0.48 米地面样本距离),确保用户在显示数据时可以看到有意义的细节。 在较低的缩放级别,高分辨率 SAR 数据将过于详细,无法有用,可能会影响性能。maxItemsPerTile: 35:限制可在单个地图图块中组合在一起的 SAR 图像数。 对于 SAR 数据,此限制设置确保多个重叠的数据采集不会使切片生成过程过载,并在需要时允许进行时间复合。defaultLocation: null:未指定默认位置,允许用户导航到 Umbra SAR 覆盖范围可用的任何感兴趣的区域。
此磁贴设置配置优化了数据可见性和性能之间的平衡,确保在用户放大各个建筑物、车辆和基础结构元素变得清晰可区分的相应比例时,能够有效地显示高分辨率 SAR 图像。
{
"minZoom": 12,
"maxItemsPerTile": 35,
"defaultLocation": null
}
STAC 收集配置
该 item_assets 部分是 STAC 集合 JSON 的关键组件,用于定义此 Umbra SAR 集合的每个项内可用的资产(数据文件)。 对于此 Umbra SAR 集合:
此 GEC 资产部分告诉我们:
资产密钥:
GEC是用于在呈现配置中引用此资产的密钥标识符(assets=GEC)数据格式:该资产是云优化的 GeoTIFF 格式,允许高效访问图像的部分内容。
雷达属性:
- 此 GEC 图像包含 VV 极化数据(垂直传输、垂直接收)
- 包含经过地形校正和辐射校正的伽马零值
技术规范:
-
nodata值-32768指示不带数据的像素 - 数据存储为 8 位无符号整数(
uint8) - 空间分辨率约为每个像素 0.48 米
-
在渲染配置中通过assets=GEC直接引用此 GEC 资产定义,渲染参数(rescale=0,255&colormap_name=gray)的设计目标是正确可视化此特定数据资产中的 SAR 反散射值。
{
"id": "umbra-sar",
"type": "Collection",
"links": [
{
"rel": "items",
"type": "application/geo+json",
"href": "https://{geocatalog_id}/stac/collections/umbra-sar/items"
},
{
"rel": "parent",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "root",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "self",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/collections/umbra-sar"
}
],
"title": "Umbra SAR Imagery",
"assets": {
"thumbnail": {
"href": "https://{storage_account}.blob.core.windows.net/{blob_container}/collection-assets/thumbnail/blob",
"type": "image/png",
"roles": [
"thumbnail"
],
"title": "umbra-sar thumbnail"
}
},
"extent": {
"spatial": {
"bbox": [
[
-180,
-90,
180,
90
]
]
},
"temporal": {
"interval": [
[
"2018-01-01T00:00:00Z",
null
]
]
}
},
"license": "CC-BY-4.0",
"keywords": [
"Umbra",
"X-Band",
"SAR",
"RTC"
],
"providers": [
{
"url": "https://umbra.space/",
"name": "Umbra",
"roles": [
"processor"
]
},
{
"url": "https://planetarycomputer.microsoft.com",
"name": "Microsoft",
"roles": [
"host"
]
}
],
"description": "Umbra satellites offer the highest commercially available SAR imagery, surpassing 25 cm resolution. Capable of capturing images day or night, through clouds, smoke, and rain, our technology enables all-weather monitoring.",
"item_assets": {
"GEC": {
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "VV: vertical transmit, vertical receive",
"description": "Terrain-corrected gamma naught values of signal transmitted with vertical polarization and received with vertical polarization with radiometric terrain correction applied.",
"raster:bands": [
{
"nodata": -32768,
"data_type": "uint8",
"spatial_resolution": 0.4770254115
}
]
}
},
"stac_version": "1.0.0",
"msft:_created": "2024-04-05T17:55:17.930092Z",
"msft:_updated": "2024-04-05T18:30:16.587869Z",
"stac_extensions": [
"https://{storage_account}.blob.core.windows.net/{blob_container}/json-schemas/json-schemas/msft/v0.1/schema.json"
],
"msft:short_description": "Umbra Synthetic Aperture Radar (SAR) Imagery"
}
影响观测站土地利用/土地覆盖9分类集合配置
影响观测站土地使用/土地覆盖9类数据集提供年度全球土地使用和土地覆盖地图(LULC)。 此数据集 是使用数十亿人标像素生成的,用于训练用于土地分类的深度学习模型,该模型以 10 米分辨率应用于 Sentinel-2 图像。
9 类系统包括:水、树木、淹没植被、作物、建筑区域、裸地、积雪/冰、云和牧场。 此更新的分类模型将以前独立的草地类和灌木类合并为一个牧场类,从而在时间序列中提供更一致的分类。
每个年度地图表示全年 LULC 预测的复合,评估的平均准确度超过 75%。 这些数据对于监测土地使用变化、跟踪森林砍伐、城市扩张和全球农业模式非常有用。
土地使用/土地覆盖配置详细信息
马赛克配置
此集合的马赛克配置提供临时筛选选项,允许用户查看特定年份的土地覆盖数据。 每个马赛克定义筛选数据,以仅使用公共查询语言(CQL)表达式显示特定年份中的项。 此时态筛选允许用户比较土地覆盖变化逐年变化,或专注于特定兴趣时间段
该配置包括六个单独的马赛克选项,涵盖 2017-2022:
-
时态筛选:每个马赛克都使用
anyinteracts运算符筛选属性与特定年份日期范围相交的项datetime -
日期范围:每年的筛选器范围从该特定年份的 1 月 1 日到 12 月 31 日(
2022-01-01T23:59:59Z到2022-12-31T23:59:59Z)
这种临时筛选方法对于土地覆盖分析非常有用,因为它使用户能够跟踪土地使用模式的变化,监测森林砍伐或造林,观察城市扩张,并评估自然灾害或人类活动随时间推移的影响。
[
{
"id": "2022",
"name": "2022",
"description": "2022 Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2022-01-01T23:59:59Z",
"2022-12-31T23:59:59Z"
]
}
]
}
]
},
{
"id": "2021",
"name": "2021",
"description": "2021 Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2021-01-01T23:59:59Z",
"2021-12-31T23:59:59Z"
]
}
]
}
]
},
{
"id": "2020",
"name": "2020",
"description": "2020 Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2020-01-01T23:59:59Z",
"2020-12-31T23:59:59Z"
]
}
]
}
]
},
{
"id": "2019",
"name": "2019",
"description": "2019 Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2019-01-01T23:59:59Z",
"2019-12-31T23:59:59Z"
]
}
]
}
]
},
{
"id": "2018",
"name": "2018",
"description": "2018 Land Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2018-01-01T23:59:59Z",
"2018-12-31T23:59:59Z"
]
}
]
}
]
},
{
"id": "2017",
"name": "2017",
"description": "2017 Land Use/Land Cover",
"cql": [
{
"op": "anyinteracts",
"args": [
{
"property": "datetime"
},
{
"interval": [
"2017-01-01T23:59:59Z",
"2017-12-31T23:59:59Z"
]
}
]
}
]
}
]
渲染选项配置
此呈现配置定义了三种不同的方法,用于在资源管理器中可视化影响观测站土地覆盖分类数据。 每个条目都描述了不同的可视化方法,例如 ESA CCI 分类 (使用标准科学色图)、 默认 IO 9 类 (使用自定义影响观察站颜色)或 ESA 颜色图替代 项(将 ESA 颜色与增强处理相结合)。 有关颜色映射的详细信息,请查看 支持的彩图指南。
土地覆盖数据包含表示九种不同土地覆盖类型的分类值,这些分类值存储在单个“数据”资产中,该资产要求颜色地图应用程序有效地可视化类别。
该 options 字符串指定如何可视化数据:
assets=data:
此资产参数从 STAC 项中选择分类数据资产,其中包含每个像素的分类土地覆盖值。colormap_name=esa-cci-lc或colormap_name=io-lulc-9-class:
此配色图参数应用预定义的调色板将数字分类值映射到颜色。 ESA 颜色图遵循科学标准,而 IO 颜色图则针对 9 类系统进行优化。exitwhenfull=False:
即使磁贴缓存已满,此展开参数也会继续处理磁贴,确保完全覆盖。skipcovered=False:
此参数skipcovered处理所有像素,包括已由其他磁贴覆盖的像素,确保可视化效果没有间隙。
可视化效果将创建一个彩色地图,其中九个土地覆盖类(水、树、作物、建筑区域等)以不同的颜色显示,以便进行识别和分析。
ESA CCI 土地覆盖分类
-
配置:
"options": "assets=data&colormap_name=esa-cci-lc" - 目的:使用标准欧空局 CCI (欧洲航天局气候变化倡议) 颜色地图进行陆地覆盖可视化
- 最佳用途:与其他欧空局土地覆盖产品和科学出版物保持一致
- 缩放级别:可从缩放级别 3 获取,适合全球和大陆缩放查看
默认值 (IO 9 类颜色图)
-
配置:
"options": "assets=data&exitwhenfull=False&skipcovered=False&colormap_name=io-lulc-9-class" - 目的:使用专为影响天文台 9 类系统设计的自定义颜色图
-
技术详细信息:
-
exitwhenfull=False:即使磁贴缓存已满,仍继续处理 -
skipcovered=False:处理所有像素,包括已经被其他磁贴覆盖的像素
-
- 适用于:对 9 类土地覆盖类别进行最佳可视化,并为该分类系统精心选择颜色
默认值 (ESA 颜色图替代项)
-
配置:
"options": "assets=data&exitwhenfull=False&skipcovered=False&colormap_name=esa-cci-lc" - 目的:将 ESA 颜色图与默认配置相同的处理选项组合在一起
- 最适合:首选 ESA 配色方案但想要增强的处理选项的用户
所有呈现选项都使用 data 包含分类土地覆盖值的资产,并应用不同的色图以不同的颜色可视化 9 个陆地覆盖类。
[
{
"id": "esa-cci-class",
"name": "Classification",
"description": "ESA CCI land cover classification",
"type": "raster-tile",
"options": "assets=data&colormap_name=esa-cci-lc",
"minZoom": 3
},
{
"id": "default",
"name": "Default",
"description": "Land cover classification using 9 class custom colormap",
"type": "raster-tile",
"options": "assets=data&exitwhenfull=False&skipcovered=False&colormap_name=io-lulc-9-class",
"minZoom": 4
},
{
"id": "default-esa-colormap",
"name": "Default",
"description": "Land cover classification using 9 class custom colormap",
"type": "raster-tile",
"options": "assets=data&exitwhenfull=False&skipcovered=False&colormap_name=esa-cci-lc",
"minZoom": 4
}
]
图块设置配置
图块设置配置控制资源管理器中土地覆盖数据的显示行为和性能特征。
关键参数:
minZoom: 3:设置陆地覆盖数据可见的最小缩放级别。maxItemsPerTile: 35:限制可以在单个地图图块中组合在一起的 STAC 项数。 对于年度土地覆盖数据,此限制设置可确保多个重叠项目(如果存在)不会使磁贴生成过程不堪重负。defaultLocation: null:未指定默认位置,允许用户全局导航到任何感兴趣的区域。
此配置优化了数据可见性和性能之间的平衡,确保在用户放大到适当的比例进行分析时有效显示 10 米分辨率的土地覆盖分类。
{
"minZoom": 3,
"maxItemsPerTile": 35,
"defaultLocation": null
}
STAC 收集配置
STAC 集合配置定义影响观测站土地使用/土地覆盖 9 类集合的核心元数据和结构。
关键组件:
项资产 - 数据资产: 此配置最重要的部分是 item_assets.data 该部分,用于定义土地覆盖分类数据的结构化方式:
- 资产类型:云优化的 GeoTIFF 格式,用于高效访问和处理
- 空间分辨率:每个像素 10 米,派生自 Sentinel-2 图像
-
分类值:该
file:values部分定义 9 个陆地覆盖类:- 0:无数据
- 1: 水 (海洋, 湖泊, 河流)
- 2:树木(森林,树林植被)
- 4:洪水淹没的植被(湿地、沼泽)
- 5:作物(农业区)
- 7:建筑面积(城市、建筑、基础设施)
- 8: 裸地 (土壤, 岩石, 沙子)
- 9:冰雪(永久和季节性积雪覆盖)
- 10:云(云覆盖)
- 11: 牧草地(草原,灌木丛地 - 结合以前的草地和灌木丛类)
时态覆盖范围:
- 范围:2017-2022 年全球覆盖范围
- 更新频率:年度地图,每一张地图表示全年预测的汇总
数据血缘:
- 来源:ESA Sentinel-2 图像
- Processing:基于数十亿个人工标注像素训练的深度学习模型
- 准确性:平均准确度超过 75%
- 制作人:与Esri和微软合作的Impact Observatory
此 STAC 配置使渲染配置能够引用 data 资源并应用适当的颜色图,从而能在 Explorer 中有效直观地展示分类的土地覆盖值。
{
"id": "io-9-class-collection",
"type": "Collection",
"links": [
{
"rel": "items",
"type": "application/geo+json",
"href": "https://{geocatalog_id}/stac/collections/IO-lulc-9-class-collection/items"
},
{
"rel": "parent",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "root",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/"
},
{
"rel": "self",
"type": "application/json",
"href": "https://{geocatalog_id}/stac/collections/IO-lulc-9-class-collection"
},
{
"rel": "related",
"href": "https://livingatlas.arcgis.com/landcover/"
},
{
"rel": "license",
"href": "https://creativecommons.org/licenses/by/4.0/",
"type": "text/html",
"title": "CC BY 4.0"
},
{
"rel": "describedby",
"href": "https://planetarycomputer.microsoft.com/dataset/io-lulc-9-class",
"type": "text/html",
"title": "Human readable dataset overview and reference"
}
],
"title": "IO-lulc-9-class-io-lulc-9-class",
"extent": {
"spatial": {
"bbox": [
[
-180,
-90,
180,
90
]
]
},
"temporal": {
"interval": [
[
"2017-01-01T00:00:00Z",
"2023-01-01T00:00:00Z"
]
]
}
},
"license": "CC-BY-4.0",
"keywords": [
"Global",
"Land Cover",
"Land Use",
"Sentinel"
],
"providers": [
{
"url": "https://www.esri.com/",
"name": "Esri",
"roles": [
"licensor"
]
},
{
"url": "https://www.impactobservatory.com/",
"name": "Impact Observatory",
"roles": [
"processor",
"producer",
"licensor"
]
},
{
"url": "https://planetarycomputer.microsoft.com",
"name": "Microsoft",
"roles": [
"host"
]
}
],
"summaries": {
"raster:bands": [
{
"nodata": 0,
"spatial_resolution": 10
}
]
},
"description": "Time series of annual global maps of land use and land cover (LULC). It currently has data from 2017-2022. The maps are derived from ESA Sentinel-2 imagery at 10m resolution. Each map is a composite of LULC predictions for 9 classes throughout the year in order to generate a representative snapshot of each year.\n\nThis dataset was generated by [Impact Observatory](http://impactobservatory.com/), who used billions of human-labeled pixels (curated by the National Geographic Society) to train a deep learning model for land classification. The global map was produced by applying this model to the Sentinel-2 annual scene collections on the Planetary Computer. Each of the maps has an assessed average accuracy of over 75%.\n\nThis map uses an updated model from the [10-class model](https://planetarycomputer.microsoft.com/dataset/io-lulc) and combines Grass(formerly class 3) and Scrub (formerly class 6) into a single Rangeland class (class 11). The original Esri 2020 Land Cover collection uses 10 classes (Grass and Scrub separate) and an older version of the underlying deep learning model. The Esri 2020 Land Cover map was also produced by Impact Observatory. The map remains available for use in existing applications. New applications should use the updated version of 2020 once it is available in this collection, especially when using data from multiple years of this time series, to ensure consistent classification.\n\nAll years are available under a Creative Commons BY-4.0.",
"item_assets": {
"data": {
"type": "image/tiff; application=geotiff; profile=cloud-optimized",
"roles": [
"data"
],
"title": "Global land cover data",
"file:values": [
{
"values": [
0
],
"summary": "No Data"
},
{
"values": [
1
],
"summary": "Water"
},
{
"values": [
2
],
"summary": "Trees"
},
{
"values": [
4
],
"summary": "Flooded vegetation"
},
{
"values": [
5
],
"summary": "Crops"
},
{
"values": [
7
],
"summary": "Built area"
},
{
"values": [
8
],
"summary": "Bare ground"
},
{
"values": [
9
],
"summary": "Snow/ice"
},
{
"values": [
10
],
"summary": "Clouds"
},
{
"values": [
11
],
"summary": "Rangeland"
}
]
}
},
"msft:region": "westeurope",
"stac_version": "1.0.0",
"msft:_created": "2024-10-15T15:38:42.009851Z",
"msft:_updated": "2024-10-15T15:38:42.009851Z",
"msft:group_id": "io-land-cover",
"msft:container": "io-lulc",
"stac_extensions": [
"https://stac-extensions.github.io/item-assets/v1.0.0/schema.json",
"https://stac-extensions.github.io/raster/v1.0.0/schema.json",
"https://stac-extensions.github.io/label/v1.0.0/schema.json",
"https://stac-extensions.github.io/file/v2.1.0/schema.json",
"https://stac-extensions.github.io/table/v1.2.0/schema.json",
"https://{storage_account}.blob.core.windows.net/{blob_container}/json-schemas/json-schemas/msft/v0.1/schema.json"
],
"msft:storage_account": "ai4edataeuwest",
"msft:short_description": "Global land cover information with 9 classes for for 2017-2022 at 10m resolution"
}
相关内容
反馈
此页面是否有帮助?
否
需要有关本主题的帮助?
想要尝试使用 Ask Learn 阐明或指导你完成本主题?
其他资源
-
Last updated on
2026-06-11