openet-landsat-lai


Nameopenet-landsat-lai JSON
Version 0.2.0 PyPI version JSON
download
home_page
SummaryEarth Engine based Landsat LAI functions
upload_time2024-03-06 20:33:33
maintainer
docs_urlNone
author
requires_python>=3.8
licenseApache-2.0
keywords lai openet earth engine evapotranspiration landsat
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            # Landsat Leaf Area Index (LAI) Algorithms

The Landsat based LAI estimation algorithm employs a machine learning approach that uses MODIS LAI as a reference data source. This algorithm is primarily driven by an extensive training sample set of MODIS LAI and Landsat surface reflectance, generated using Landsat SR and MODIS LAI images over 2006 to 2018. Each sample was extracted at MODIS resolution (500m), and the MODIS LAI, aggregated Landsat surface reflectance, as well as NLCD land cover type were recorded. For a Landsat SR image, the algorithm will first draw the training set (saved as a GEE asset), train random forest models, and then the apply to the Landsat image. For the random forest model, the feature space includes Landsat surface reflectance in red, green, NIR and SWIR1 bands, Normalized Difference Vegetation Index (NDVI), Normalized Different Water Index (NDWI), the geographic coordinates, and the sun viewing angle of the Landsat scene. The target variable is MODIS LAI. Separate models are built for each Landsat sensor and individual biomes. There are eight predefined biome types based on NLCD. Each training operation involves around 40,000 to 60,000 samples.

            

Raw data

            {
    "_id": null,
    "home_page": "",
    "name": "openet-landsat-lai",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.8",
    "maintainer_email": "Charles Morton <charles.morton@dri.edu>",
    "keywords": "LAI,OpenET,Earth Engine,Evapotranspiration,Landsat",
    "author": "",
    "author_email": "Yanghui Kang <ykang38@wisc.edu>, Yun Yang <yun.yang@msstate.edu>",
    "download_url": "https://files.pythonhosted.org/packages/b6/06/1f4bfbcfb94fcf516b71208dcd1066894ef355286368760a43fa6621a76c/openet-landsat-lai-0.2.0.tar.gz",
    "platform": null,
    "description": "# Landsat Leaf Area Index (LAI) Algorithms\n\nThe Landsat based LAI estimation algorithm employs a machine learning approach that uses MODIS LAI as a reference data source. This algorithm is primarily driven by an extensive training sample set of MODIS LAI and Landsat surface reflectance, generated using Landsat SR and MODIS LAI images over 2006 to 2018. Each sample was extracted at MODIS resolution (500m), and the MODIS LAI, aggregated Landsat surface reflectance, as well as NLCD land cover type were recorded. For a Landsat SR image, the algorithm will first draw the training set (saved as a GEE asset), train random forest models, and then the apply to the Landsat image. For the random forest model, the feature space includes Landsat surface reflectance in red, green, NIR and SWIR1 bands, Normalized Difference Vegetation Index (NDVI), Normalized Different Water Index (NDWI), the geographic coordinates, and the sun viewing angle of the Landsat scene. The target variable is MODIS LAI. Separate models are built for each Landsat sensor and individual biomes. There are eight predefined biome types based on NLCD. Each training operation involves around 40,000 to 60,000 samples.\n",
    "bugtrack_url": null,
    "license": "Apache-2.0",
    "summary": "Earth Engine based Landsat LAI functions",
    "version": "0.2.0",
    "project_urls": {
        "Homepage": "https://github.com/Open-ET/openet-landsat-lai"
    },
    "split_keywords": [
        "lai",
        "openet",
        "earth engine",
        "evapotranspiration",
        "landsat"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "b6061f4bfbcfb94fcf516b71208dcd1066894ef355286368760a43fa6621a76c",
                "md5": "f2354b6dc0ea2cf390cf0bc183ef9e2d",
                "sha256": "aa198931482b2832b64534063aad47ed097a6fd47e9748f9258a29fe8e62f665"
            },
            "downloads": -1,
            "filename": "openet-landsat-lai-0.2.0.tar.gz",
            "has_sig": false,
            "md5_digest": "f2354b6dc0ea2cf390cf0bc183ef9e2d",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.8",
            "size": 11457,
            "upload_time": "2024-03-06T20:33:33",
            "upload_time_iso_8601": "2024-03-06T20:33:33.382901Z",
            "url": "https://files.pythonhosted.org/packages/b6/06/1f4bfbcfb94fcf516b71208dcd1066894ef355286368760a43fa6621a76c/openet-landsat-lai-0.2.0.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-03-06 20:33:33",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "Open-ET",
    "github_project": "openet-landsat-lai",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": true,
    "lcname": "openet-landsat-lai"
}
        
Elapsed time: 1.06012s