Training Classifiers, Supervised Classification and Error Assessment

• How to add raster and vector data from the catalog in Google Earth Engine;

• Train a classifier;

• Perform the error assessment;

• Download the results.

The Google Satellite Embedding dataset is a global, analysis-ready collection of learned geospatial embeddings. Each 10-meter pixel in this dataset is a 64-dimensional representation, or "embedding vector," that encodes temporal trajectories of surface conditions at and around that pixel as measured by various Earth observation instruments and datasets, over a …

Meet Earth EngineGoogle Earth Engine combines a multi-petabyte catalog of satellite imagery and geospatial datasets with planetary-scale analysis capabilities and makes it available for scientists, researchers, and developers to detect changes, map trends, and quantify differences on the Earth's surface.SATELLITE IMAGERY+YOUR ALGORITHMS+REAL WORLD APPLICATIONSLEARN MOREGLOBAL-SCALE INSIGHTExplore our interactive timelapse viewer to travel back in time and see how the world has changed over the past twenty-nine years. Timelapse is one example of how Earth Engine can help gain insight into petabyte-scale datasets.EXPLORE TIMELAPSEREADY-TO-USE DATASETSThe public data archive includes more than thirty years of historical imagery and scientific datasets, updated and expanded daily. It contains over twenty petabytes of geospatial data instantly available for analysis.EXPLORE DATASETSSIMPLE, YET POWERFUL APIThe Earth Engine API is available in Python and JavaScript, making it easy to harness the power of Google’s cloud for your own geospatial analysis.EXPLORE THE APIGoogle Earth Engine has made it possible for the first time in history to rapidly and accurately process vast amounts of satellite imagery, identifying where and when tree cover change has occurred at high resolution. Global Forest Watch would not exist without it. For those who care about the future of the planet Google Earth Engine is a great blessing!-Dr. Andrew Steer, President and CEO of the World Resources Institute.CONVENIENT TOOLSUse our web-based code editor for fast, interactive algorithm development with instant access to petabytes of data.LEARN ABOUT THE CODE EDITORSCIENTIFIC AND HUMANITARIAN IMPACTScientists and non-profits use Earth Engine for remote sensing research, predicting disease outbreaks, natural resource management, and more.SEE CASE STUDIESREADY TO BE PART OF THE SOLUTION?SIGN UP NOWTERMS OF SERVICE PRIVACY ABOUT GOOGLE

Google Earth

## Overview

Google Earth is a dataset for instance segmentation tasks - it contains Green annotations for 872 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Data Management

• Create and edit fusion tables

• Upload imagery, vector, and tabular data using Fusion Tables and KMLs

• Share data with other Google Earth Engine (GEE) users as well as download imagery after manipulation in GEE.

PLEASE NOTE: These data do not include data over Tasmania. Please see links relevant to that area.

GEODATA TOPO 250K Series 3 is a vector representation of the major topographic features appearing on the 1:250,000 scale NATMAPs supplied in KML format and is designed for use in a range of commercial GIS software. Data is arranged within specific themes. All data is based on the GDA94 coordinate system.

GEODATA TOPO 250K Series 3 is available as a free download product in Personal Geodatabase, ArcView Shapefile or MapInfo TAB file formats. Each package includes data arranged in ten main themes - cartography, elevation, framework, habitation, hydrography, infrastructure, terrain, transport, utility and vegetation. Data is also available as GEODATA TOPO 250K Series 3 for Google Earth in kml format for use on Google Earth TM Mapping Service.

Product Specifications

Themes: Cartography, Elevation, Framework, Habitation, Hydrography, Infrastructure, Terrain, Transport, Utility and Vegetation

Coverage: National (Powerlines not available in South Australia)

Currency: Data has a currency of less than five years for any location

Coordinates: Geographical

Datum: Geocentric Datum of Australia (GDA94)

Formats: Personal Geodatabase, kml, Shapefile and MapInfo TAB

Release Date: 26 June 2006

This data provides the integrated cadastral framework for Canada Lands. The cadastral framework consists of active and superseded cadastral parcel, roads, easements, administrative areas, active lines, points and annotations. The cadastral lines form the boundaries of the parcels. COGO attributes are associated to the lines and depict the adjusted framework of the cadastral fabric. The cadastral annotations consist of lot numbers, block numbers, township numbers, etc. The cadastral framework is compiled from Canada Lands Survey Records (CLSR), registration plans (RS) and location sketches (LS) archived in the Canada Lands Survey Records.

Since their introduction in 2012, Local Climate Zones (LCZs) emerged as a new standard for characterizing urban landscapes, providing a holistic classification approach that takes into account micro-scale land-cover and associated physical properties. This global map of Local Climate Zones, at 100m pixel size and representative for the nominal year …

Kaggle Ships In Google Earth Dfqwt

## Overview

Kaggle Ships In Google Earth Dfqwt is a dataset for object detection tasks - it contains Kaggle Ships In Google Earth Dfq annotations for 794 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [Public Domain license](https://creativecommons.org/licenses/Public Domain).

Summary

Earth Map (earthmap.org) is a web-based FAO-Google tool for quick multi-temporal analysis of environment and climate parameters for evidence-based policies integrating cloud technologies and freely available datasets. Earth Map can analyse and display data that are already present in Google Earth Engine (earthengine.google.com) as other freely available datasets that have been gathered, processed and uploaded to the platform.

Data domains range from temperature to precipitation, fires, population, vegetation, evapotranspiration, water, land use/cover, elevation, soil, satellite images, etc. Most of the data include multi-temporal series allowing to have a time machine for several environmental parameters.

Earth Map aims to lower the access to some feature of Earth Engine through a simple graphical interface with drop-down menus. Any user can run environmental and climatic analysis on their area of interest and in a matter of few seconds.

https://data.apps.fao.org/catalog/dataset/a7116f30-254f-43c3-85ce-6756b4dd5259/resource/2d9c30c0-b593-4879-9096-1b3e87cc248a/download/earth-map-screenshot.png" alt="EarthMap Screenshot">

Application

Users without prior experience in GIS or remote sensing, but with knowledge of the land to be analysed, can use Earth Map to produce images, tables and statistics describing the environmental and climatic context and history of an area. Therefore, Earth Map can play a strategic role in providing guidance in project design but also in project monitoring and final evaluation.

Even in countries where data appear to be scarce, the remote-sensing data in Earth Engine are integrated with additional freely available datasets to provide timely analysis, customized for the objectives of the projects. The tool allows to gather an in-depth multi-temporal perspective of the environmental and climatic conditions with a focus on the study of the anomalies and their frequency.

Background

Earth Map has been developed in the framework of the FAO-Google partnership, in synergy with the FAO Hand-in-Hand Geospatial Platform and thanks to the support of the International Climate Initiative (IKI) of the German Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU). The team behind Earth Map is the same team that developed Collect Earth (www.openforis.org/tools/collect-earth.html) and it is still maintaining it; Collect Earth is another FAO-Google application to produce detailed statistics of land use, land use change and forest through a point sampling approach and freely available remote sensing data.

The SEN12TP dataset (Sentinel-1 and -2 imagery, timely paired) contains 2319 scenes of Sentinel-1 radar and Sentinel-2 optical imagery together with elevation and land cover information of 1236 distinct ROIs taken between 28 March 2017 and 31 December 2020. Each scene has a size of 20km x 20km at 10m pixel spacing. The time difference between optical and radar images is at most 12h, but for almost all scenes it is around 6h since the orbits of Sentinel-1 and -2 are shifted like that. Next to the \(\sigma^\circ\) radar backscatter also the radiometric terrain corrected \(\gamma^\circ\) radar backscatter is calculated and included. \(\gamma^\circ\) values are calculated using the volumetric model presented by Vollrath et. al 2020.

The uncompressed dataset has a size of 222 GB and is split spatially into a train (~90%) and a test set (~10%). For easier download the train set is split into four separate zip archives.

Please cite the following paper when using the dataset, in which the design and creation is detailed:
T. Roßberg and M. Schmitt. A globally applicable method for NDVI estimation from Sentinel-1 SAR backscatter using a deep neural network and the SEN12TP dataset. PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2023. https://doi.org/10.1007/s41064-023-00238-y.

The file sen12tp-metadata.json includes metadata of the selected scenes. It includes for each scene the geometry, an ID for the ROI and the scene, the climate and land cover information used when sampling the central point, the timestamps (in ms) when the Sentinel-1 and -2 image was taken, the month of the year, and the EPSG code of the local UTM Grid (e.g. EPSG:32643 - WGS 84 / UTM zone 43N).

Naming scheme: The images are contained in directories called {roi_id}_{scene_id}, as for some unique regions image pairs of multiple dates are included. In each directory are six files for the different modalities with the naming {scene_id}_{modality}.tif. Multiple modalities are included: radar backscatter and multispectral optical images, the elevation as DSM (digital surface model) and different land cover maps.

Data modalities

name	Modality	GEE collection
s1	Sentinel-1 radar backscatter	COPERNICUS/S1_GRD
s2	Sentinel-2 Level-2A (Bottom of atmosphere, BOA) multispectral optical data with added cloud probability band	COPERNICUS/S2_SR COPERNICUS/S2_CLOUD_PROBABILITY
dsm	30m digital surface model	JAXA/ALOS/AW3D30/V3_2
worldcover	land cover, 10m resolution	ESA/WorldCover/v100

The following bands are included in the tif files, for an further explanation see the documentation on GEE. All bands are resampled to 10m resolution and reprojected to the coordinate reference system of the Sentinel-2 image.

Modality Bands

Modality	Band count	Band names in tif file	Notes
s1	5	VV_sigma0, VH_sigma0, VV_gamma0flat, VH_gamma0flat, incAngle	VV/VH_sigma0 are the \(\sigma^\circ\) values, VV/VH_gamma0flat are the radiometric terrain corrected \(\gamma^\circ\) backscatter values incAngle is the incident angle
s2	13	B1, B2, B3, B4, B5, B7, B7, B8, B8A, B9, B11, B12, cloud_probability	multispectral optical bands and the probability that a pixel is cloudy, calculated with the sentinel2-cloud-detector library optical reflectances are bottom of atmosphere (BOA) reflectances calculated using sen2cor
dsm	1	DSM	Height above sea level. Signed 16 bits. Elevation (in meter) converted from the ellipsoidal height based on ITRF97 and GRS80, using EGM96†1 geoid model.
worldcover	1	Map	Landcover class

Checking the file integrity
After downloading and decompression the file integrity can be checked using the provided file of md5 checksum.
Under Linux: md5sum --check --quiet md5sums.txt

References:

Vollrath, Andreas, Adugna Mullissa, Johannes Reiche (2020). "Angular-Based Radiometric Slope Correction for Sentinel-1 on Google Earth Engine". In: Remote Sensing 12.1, Art no. 1867. https://doi.org/10.3390/rs12111867.

The Shuttle Radar Topography Mission (SRTM) digital elevation dataset was originally produced to provide consistent, high-quality elevation data at near global scope. This version of the SRTM digital elevation data has been processed to fill data voids, and to facilitate its ease of use.

Geospatial Services Land management within the US Forest Service and on the 900,000+ acre Monongahela National Forest (NF) is driven by a wide mix of resource and societal demands that prove a challenge in fulfilling the Forest Service’s mission of “Caring for the Land and Serving the People.” Programmatically, the 2006 Land and Resource Management Plan guide natural resource management activities on lands administered by the Monongahela National Forest. The Forest Plan describes management direction and practices, resource protection methods and monitoring, desired resource conditions, and the availability and suitability of lands for resource management. Technology enables staff to address these land management issues and Forest Plan direction by using a science-based approach to facilitate effective decisions. Monongahela NF geospatial services, using enabling-technologies, incorporate key tools such as Environmental Systems Research Institute’s ArcGIS desktop suite and Trimble’s global positioning system (GPS) units to meet program and Forest needs. Geospatial Datasets The Forest has a broad set of geospatial datasets that capture geographic features across the eastern West Virginia landscape. Many of these datasets are available to the public through our download site. Selected geospatial data that encompass the Monongahela National Forest are available for download from this page. A link to the FGDC-compliant metadata is provided for each dataset. All data are in zipped format (or available from the specified source), in one of two spatial data formats, and in the following coordinate system: Coordinate System: Universal Transverse Mercator Zone: 17 Units: Meters Datum: NAD 1983 Spheroid: GRS 1980 Map files – All map files are in pdf format. These maps illustrate the correlated geospatial data. All maps are under 1 MB unless otherwise noted. Metadata file – This FGDC-compliant metadata file contains information pertaining to the specific geospatial dataset. Shapefile – This downloadable zipped file is in ESRI’s shapefile format. KML file – This downloadable zipped file is in Google Earth’s KML format. Resources in this dataset:Resource Title: Monongahela National Forest Geospatial Data. File Name: Web Page, url: https://www.fs.usda.gov/detail/mnf/landmanagement/gis/?cid=stelprdb5108081 Selected geospatial data that encompass the Monongahela National Forest are available for download from this page.

Using 335,709 Landsat images on the Google Earth Engine, we built the first Landsat-derived annual land cover product of China (CLCD) from 1985 to 2019. We collected the training samples by combining stable samples extracted from China's Land-Use/Cover Datasets (CLUD), and visually-interpreted samples from satellite time-series data, Google Earth and Google Map. Several temporal metrics were constructed via all available Landsat data and fed to the random forest classifier to obtain classification results. A post-processing method incorporating spatial-temporal filtering and logical reasoning was further proposed to improve the spatial-temporal consistency of CLCD.

"*_albert.tif" are projected files via a proj4 string "+proj=aea +lat_1=25 +lat_2=47 +lat_0=0 +lon_0=105 +x_0=0 +y_0=0 +datum=WGS84 +units=m +no_defs".

CLCD in 2022 is now available.

1. Given that the USGS no longer maintains the Landsat Collection 1 data, we are now using the Collection 2 SR data to update the CLCD.

2. All files in this version have been exported as Cloud Optimized GeoTIFF for more efficient processing on the cloud. Please check here for more details.

3. Internal overviews and color tables are built into each file to speed up software loading and rendering.

Ships In Google Earth

## Overview

Ships In Google Earth is a dataset for object detection tasks - it contains Boat annotations for 794 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This JavaScript code has been developed to retrieve NDSI_Snow_Cover from MODIS version 6 for SNOTEL sites using the Google Earth Engine platform. To successfully run the code, you should have a Google Earth Engine account. An input file, called NWM_grid_Western_US_polygons_SNOTEL_ID.zip, is required to run the code. This input file includes 1 km grid cells of the NWM containing SNOTEL sites. You need to upload this input file to the Assets tap in the Google Earth Engine code editor. You also need to import the MOD10A1.006 Terra Snow Cover Daily Global 500m collection to the Google Earth Engine code editor. You may do this by searching for the product name in the search bar of the code editor.

The JavaScript works for s specified time range. We found that the best period is a month, which is the maximum allowable time range to do the computation for all SNOTEL sites on Google Earth Engine. The script consists of two main loops. The first loop retrieves data for the first day of a month up to day 28 through five periods. The second loop retrieves data from day 28 to the beginning of the next month. The results will be shown as graphs on the right-hand side of the Google Earth Engine code editor under the Console tap. To save results as CSV files, open each time-series by clicking on the button located at each graph's top right corner. From the new web page, you can click on the Download CSV button on top.

Here is the link to the script path: https://code.earthengine.google.com/?scriptPath=users%2Figarousi%2Fppr2-modis%3AMODIS-monthly

Then, run the Jupyter Notebook (merge_downloaded_csv_files.ipynb) to merge the downloaded CSV files that are stored for example in a folder called output/from_GEE into one single CSV file which is merged.csv. The Jupyter Notebook then applies some preprocessing steps and the final output is NDSI_FSCA_MODIS_C6.csv.

GLobAl building MOrphology dataset for URban climate modelling (GLAMOUR) offers the building footprint and height files at the resolution of 100 m in global urban centers.

the BH_100m contains the building height files where each file is named as BH_{lon_start}_{lon_end}_{lat_start}_{lat_end}.tif.

the BF_100m contains the building footprint files where each file is named as BF_{lon_start}_{lon_end}_{lat_start}_{lat_end}.tif.

Here lon_start, lon_end, lat_start, lat_end denote the starting and ending positions of the longitude and latitude of target mapping areas.

To avoid possible confusion, it should be clarified that the 'building footprint' in GLAMOUR represents the 'building surface fraction', i.e., the ratio of building plan area to total plan area.

We also offer the snapshot of source code used for the generation of the GLAMOUR dataset including:

GC_ROI_def.py defines regions of interest (ROI) used in the mapping of the GLAMOUR dataset.

GC_user_download.py retrieves satellite images including Sentinel-1/2, NASADEM and Copernicus DEM from Google Earth Engine and exports them into Google Cloud Storage.

GC_master_pred.py downloads exported data records from Google Cloud Storage and then performs the estimation of building footprint and height using Tensorflow-based models.

GC_postprocess.py performs postprocessing on initial estimations by pixel masking with the World Settlement Footprint layer for 2019 (WSF2019).

GC_postprocess_agg.py aggregates masked patches into larger tiles contained in the GLAMOUR dataset.

The Shuttle Radar Topography Mission (SRTM, see Farr et al. 2007) digital elevation data is an international research effort that obtained digital elevation models on a near-global scale. This SRTM V3 product (SRTM Plus) is provided by NASA JPL at a resolution of 1 arc-second (approximately 30m). This dataset has undergone a void-filling process using open-source data (ASTER GDEM2, GMTED2010, and NED), as opposed to other versions that contain voids or have been void-filled with commercial sources. For more information on the different versions see the SRTM Quick Guide. Documentation: User's Guide General Documentation Algorithm Theoretical Basis Document (ATBD)

As of June 30, 2021, Google Earth was the most downloaded travel app from Google Play in the Philippines. As of this date, the app had around a hundred million downloads. Apart from Google Earth, GPS tracking apps and translations apps were among the most downloaded travel apps in the country.

Our mission is to help you picture climate change and environmental changes happening on our home planet. Here you can search for and retrieve satellite images of Earth. Download them; export them to GoogleEarth; perform basic analysis. Tracking regional and global changes around the world just got easier.