199,577 research outputs found
samapriya/awesome-gee-community-datasets: Community Catalog
No full text<p>The awesome-gee-community-catalog consists of community-sourced geospatial datasets made available for use by the larger Google Earth Engine community and shared publicly as Earth Engine assets. The project was started with the idea that a lot of research datasets are often unavailable for direct use and require preprocessing before use. This catalog lives and serves alongside the <a href="https://developers.google.com/earth-engine/datasets/catalog">Google Earth Engine data catalog</a> and also houses datasets often requested by the community under a variety of open licenses.</p>
<p>Go to the catalog to explore more: https://gee-community-catalog.org</p>
<p>You can read about the history and how this project started in the <a href="https://medium.com/geospatial-processing-at-scale/community-datasets-data-commons-in-google-earth-engine-8585d8baef1f">Medium Post article here</a></p>
<p><strong>Release frequency will be monthly for now</strong></p>
<p><img width="485" alt="catalog-banner" src="https://user-images.githubusercontent.com/6677629/193901877-586dde2b-6cdc-4709-b970-3dbe1b4e9a44.PNG"></p>
<h4>Updated 2024-02-09</h4>
<ul>
<li>Released 2.3.0 for awesome gee community catalog & stats</li>
<li>Added <a href="https://gee-community-catalog.org/projects/gshtd/">Global Seamless High-resolution Temperature Dataset (GSHTD)</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/glance_training/">GLANCE Global Landcover Training dataset</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/af_trees">High resolution map of African tree cover</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/gabam">Global annual Burned Area Maps</a> to include 2020 and 2021</li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
<h4>Updated 2024-01-18</h4>
<ul>
<li>Added <a href="https://gee-community-catalog.org/projects/climate_trace/">Climate Trace Global Emissions Data</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/rgi/">Randolph Glacier Inventory</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/japan_eq2024">Emergency Observation Data for the 2024 Sea of Japan Earthquake</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/umbra_opendata">Umbra SAR Open Data: Sea of Japan Earthquake Jan 2024</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/landfire/">Landfire Mosaics LF v2.3.0</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/health_sites/">Nodes and ways datasets from Global Health sites Mapping Projects</a></li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
<h4>Updated 2024-01-04</h4>
<ul>
<li>Added <a href="https://gee-community-catalog.org/projects/fpar/">Sensor-Independent MODIS & VIIRS LAI/FPAR CDR 2000 to 2022</a></li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
<h4>Updated 2023-11-30</h4>
<ul>
<li>Added <a href="https://gee-community-catalog.org/projects/global_buildings">Global Google-Microsoft Open Buildings Dataset</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/usgs_topo">USGS Historical Topo Maps</a></li>
<li>Released 2.2.0 for awesome gee community catalog & catalog stats</li>
</ul>
samapriya/awesome-gee-community-datasets: Community Catalog
No full text<p>The awesome-gee-community-catalog consists of community-sourced geospatial datasets made available for use by the larger Google Earth Engine community and shared publicly as Earth Engine assets. The project was started with the idea that a lot of research datasets are often unavailable for direct use and require preprocessing before use. This catalog lives and serves alongside the <a href="https://developers.google.com/earth-engine/datasets/catalog">Google Earth Engine data catalog</a> and also houses datasets often requested by the community under a variety of open licenses.</p>
<p>Go to the catalog to explore more: https://gee-community-catalog.org</p>
<p>You can read about the history and how this project started in the <a href="https://medium.com/geospatial-processing-at-scale/community-datasets-data-commons-in-google-earth-engine-8585d8baef1f">Medium Post article here</a></p>
<p><strong>Release frequency will be monthly for now</strong></p>
<p><img width="485" alt="catalog-banner" src="https://user-images.githubusercontent.com/6677629/193901877-586dde2b-6cdc-4709-b970-3dbe1b4e9a44.PNG"></p>
<h4>Updated 2024-04-02</h4>
<ul>
<li>Released 2.5.0 for awesome gee community catalog & stats</li>
<li>Added <a href="https://gee-community-catalog.org/projects/nbac/">Canada National Burned Area Composite (NBAC)</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/avhrr-ltdr/">ESA Fire Disturbance Climate Change Initiative (CCI)</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/pk_nssed/">National-Scale Soil Erosion Dataset for Pakistan (2005 and 2015)</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/speedtest">Global fixed broadband and mobile (cellular) network performance</a></li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
<h4>Updated 2024-03-07</h4>
<ul>
<li>Released 2.4.0 for awesome gee community catalog & stats</li>
<li>Added <a href="https://gee-community-catalog.org/projects/globgm/">GLOBGM v1.0 global-scale groundwater model</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/india_river_trends/">Temporal trends of Surface water across Indian Rivers & Basins</a></li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
samapriya/awesome-gee-community-datasets: Community Catalog
No full text<p>The awesome-gee-community-catalog consists of community-sourced geospatial datasets made available for use by the larger Google Earth Engine community and shared publicly as Earth Engine assets. The project was started with the idea that a lot of research datasets are often unavailable for direct use and require preprocessing before use. This catalog lives and serves alongside the <a href="https://developers.google.com/earth-engine/datasets/catalog">Google Earth Engine data catalog</a> and also houses datasets often requested by the community under a variety of open licenses.</p>
<p>Go to the catalog to explore more: https://gee-community-catalog.org</p>
<p>You can read about the history and how this project started in the <a href="https://medium.com/geospatial-processing-at-scale/community-datasets-data-commons-in-google-earth-engine-8585d8baef1f">Medium Post article here</a></p>
<p><strong>Release frequency will be monthly for now</strong></p>
<p><img width="485" alt="catalog-banner" src="https://user-images.githubusercontent.com/6677629/193901877-586dde2b-6cdc-4709-b970-3dbe1b4e9a44.PNG"></p>
<h4>Updated 2024-02-22</h4>
<ul>
<li>Added provisional dataset <a href="https://gee-community-catalog.org/projects/glc_fcs/">GLC_FCS30D - Global 30-meter Land Cover Change Dataset (1985-2022)</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/ca_sbfi/">Canadian Satellite-Based Forest Inventory (SBFI)</a></li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
<h4>Updated 2024-02-09</h4>
<ul>
<li>Released 2.3.0 for awesome gee community catalog & stats</li>
<li>Added <a href="https://gee-community-catalog.org/projects/gshtd/">Global Seamless High-resolution Temperature Dataset (GSHTD)</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/glance_training/">GLANCE Global Landcover Training dataset</a></li>
<li>Added <a href="https://gee-community-catalog.org/projects/af_trees">High resolution map of African tree cover</a></li>
<li>Updated <a href="https://gee-community-catalog.org/projects/gabam">Global annual Burned Area Maps</a> to include 2020 and 2021</li>
<li>Updated Weekly updates to <a href="https://gee-community-catalog.org/projects/usdm/">USDM drought monitor</a></li>
</ul>
samapriya/Planet-GEE-Pipeline-CLI: Planet-GEE-Pipeline-CLI
No full text<p>While moving between assets from Planet Inc and Google Earth Engine it was imperative to create a pipeline that allows for easy transitions between the two service end points and this tool is designed to act as a step by step process chain from Planet Assets to batch upload and modification within the Google Earth Engine environment. The ambition is apart from helping user with batch actions on assets along with interacting and extending capabilities of existing GEE CLI. It is developed case by case basis to include more features in the future as it becomes available or as need arises.</p>
<p>This release also contains a windows installer which bypasses the need for you to have admin permission, it does however require you to have python in the system path meaning when you open up command prompt you should be able to type python and start it within the command prompt window. Post installation using the installer you can just call ppipe using the command prompt similar to calling python. Give it a go post installation type</p>
<p>ppipe -h</p>
<p>The tool has been successfully tested on Windows 10 and Ubuntu 16 both running Python 2.7</p>
Credits
<p><a href="https://jetstream-cloud.org/">JetStream</a> A portion of the work is suported by JetStream Grant TG-GEO160014.</p>
<p>Also supported by <a href="https://www.planet.com/markets/ambassador-signup/">Planet Labs Ambassador Program</a></p>
<p>Original upload function adapted from <a href="https://github.com/tracek/gee_asset_manager">Lukasz's asset manager tool</a></p>
Changelog
v0.1.9
<ul>
<li>Changes made to reflect updated GEE Addon tools</li>
<li>general improvements</li>
</ul>
v0.1.8
<ul>
<li>Minor fixes to parser and general improvements</li>
<li>Planet Key is now stored in a configuration folder which is safer "C:\users.config\planet"</li>
<li>Earth Engine now requires you to assign a field type for metadata meaning an alphanumeric column like satID cannot also have numeric values unless specified explicitly . Manifest option has been added to handle this (just use -mf "planetscope")</li>
<li>Added capability to query download size and local disk capacity before downloading planet assets.</li>
<li>Added the list function to generate list of collections or folders including reports</li>
<li>Added the collection size tool which allows you to estimate total size or quota used from your allocated quota.</li>
<li>ogr2ft feature is removed since Earth Engine now allows vector and table uploading.</li>
</ul>
italosrodrigues/GEE-RF-LC-code: GEE-RF-code
No full text<p>The code used for the Randon Forest (RF) model in Google Earth Engine (GEE)</p>
<p>For Land Sat 5: RF_LS5</p>
<p>For Land Sat 8: RF_LS8</p>
<p>This model was used by Italo Rodrigues as part of his PhD project "Multi-decadal Floodplain Classification and Trend Analysis in the Upper Columbia River Valley, British Columbia" as a first approach for land cover classification.</p>
<p>The model inputs are divided in to files:</p>
<p>Training pixels data (70% used for training)</p>
<p>Validation pixels data (30% reserved for training)</p>
<p>In this research, we utilise a variety of reference remote sensing data sources: UAV and Airborne LiDAR, aerial photographs, geotagged photos, Sentinel 2, and historical classified land cover (Hermosilla et al., 2022) to generate training samples per each year.</p>
<p>To extract or determine the most reliable training pixels within areas of unchanging landcover class, the time series classification of Hermosilla et al. (2022) was used. Land cover permanence was calculated by summing the number of times each land cover class pixel was identified in the same pixel location. Reference rasters contain a numerical pixel value (i.e. 1 – open water; 2 – marsh; 3 – wet meadow; 4 – woody/shrub) that corresponds to each land cover in the input rasters. The 1984 land cover raster was chosen as the reference raster because this was the first year of the record, thereby providing a baseline or starting point from which to compare. The permanent land cover raster was then used within GEE to mask out permanent zones within the study floodplain that showed potential as training areas. Training pixels were then allocated within these training areas and used over the whole time-series. However, in the years with available higher resolution imagery (i.e., sporadically throughout the time series: Aerial photographs – 1984 to 1991, 2005, 2007, and 2009; Sentinel 2 – 2016 to 2022; Airborne LiDAR – 2018; UAV LiDAR and geotagged photos – 2022), which by expert interpretive identification of land cover class was possible to increase the number of training pixels in these years with more reference datasets.</p>
<p>The model result is a single raster file including the four aforementioned land covers; also, the area (km2) of each land cover, overall accuracy, and Kappa coefficient of the classification will be displayed in the right bar of the GEE.</p>
<p>The historical land cover maps (Hermosilla et al., 2022)) used to create and identify the Land cover permanent zones are open access and are available at https://opendata.nfis.org/mapserver/nfis-change_eng.html</p>
GEE-Assisted Forward Regression for Spatial Latent Variable Models
No full textMultivariate spatial data, where multiple responses are recorded at a set of spatial locations, are widely collected in many disciplines. One common approach for analyzing such data is spatial generalized linear latent variable models (spatial GLLVMs), where the latent variables are used to model both the spatial correlation between locations and correlations between responses. However, inference such as variable selection for spatial GLLVMs is computationally demanding, as the marginal likelihood involves a high-dimensional and often intractable integral. To overcome this, we propose to use spatial generalized estimating equations (GEEs) to perform fast, GEE-assisted forward regression for spatial GLLVMs. Focusing on counts and nonnegative continuous responses, we use spatial GEEs to build a forward solution path by choosing the candidate variable which maximizes a score statistic at each point on the path. A model is then selected from this path based on a modified score information criterion. The proposed approach is computationally efficient, relying only on GEEs which are quick to update, coupled with a novel theoretical result linking the coefficients from spatial GEEs to that of spatial GLLVMs. We show that the proposed approach can asymptotically identify all truly important nonzero predictors in the underlying spatial GLLVM. Simulations demonstrate that, when the data are generated from a sparse spatial GLLVM, GEE-assisted forward regression performs well at recovering this sparsity, while taking only a fraction of the computation time required to fit just a single (saturated) spatial GLLVM. Supplementary materials for this article are available online.</p
GEE-Assisted Variable Selection for Latent Variable Models with Multivariate Binary Data
No full textMultivariate data are commonly analyzed using one of two approaches: a conditional approach based on generalized linear latent variable models (GLLVMs) or some variation thereof, and a marginal approach based on generalized estimating equations (GEEs). With research on mixed models and GEEs having gone down separate paths, there is a common mindset to treat the two approaches as mutually exclusive, with which to use driven by the question of interest. In this article, focusing on multivariate binary responses, we study the connections between the parameters from conditional and marginal models, with the aim of using GEEs for fast variable selection in GLLVMs. This is accomplished through two main contributions. First, we show that GEEs are zero consistent for GLLVMs fitted to multivariate binary data. That is, if the true model is a GLLVM but we misspecify and fit GEEs, then the latter is able to asymptotically differentiate between truly zero versus nonzero coefficients in the former. Building on this result, we propose GEE-assisted variable selection for GLLVMs using score- and Wald-based information criteria to construct a fast forward selection path followed by pruning. We demonstrate GEE-assisted variable selection is selection consistent for the underlying GLLVM, with simulation studies demonstrating its strong finite sample performance and computational efficiency.</p
GEE-based Bell model for longitudinal count outcomes
No full textLongitudinal count models are usually constructed based on Poisson and negative binomial distributions. Recently, a single-parameter discrete Bell distribution has been presented as an alternative to well-known count distributions. In this study, a new marginal model is proposed for longitudinal count responses based on Bell distribution to handle overdispersion and dependency structure. Bell distribution is more practical in that it has fewer parameters than the negative binomial distribution and still handle overdispersion with a single parameter. Focusing on demonstrating that regression diagnostics supplement the Bell marginal model based on GEE to serve as sensitivity analysis. The Bell marginal model is used to analyze the number of accidents caused injuries in Greece during the 5-year time period. The half-normality plots indicate that the Bell marginal model provides better fit than other marginal models for the accident dataset. The common working covariance selection criterias and properties of parameter estimations are investigated for the Bell marginal model in the simulation study. Parameter estimations of the new model based on GEEs are obtained by geeM R package with the user-defined function. Diagnostic measures and simulated envelope algorithm are also provided for the proposed model.</p
Statistical data for GEE and combined model GEE (NAWM = normal-appearing white matter, VC = visual cortex).
No full text<p>Statistical data for GEE and combined model GEE (NAWM = normal-appearing white matter, VC = visual cortex).</p
- …
