Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
1,118
datasets available to search
ShareScore release 0.7.1
Dataset results
1,118 results for “sentinel”
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 5-band (RGB+NIR+SWIR) images of coasts.
<p>These Residual-UNet model data are based on 5-band RGB+NIR+SWIR (red, green, blue, near-infrared, and short-wave infrared) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571 </a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571</a></p>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)
<p><em><strong>Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)</strong></em></p> <p><strong>Description</strong></p> <p>579 images and 579 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>The label images are a subset of the following data release**** <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue, NIR, and SWIR bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li>nir.zip, a zipped folder containing the corresponding near-infrared (NIR) imagery</li> <li>swir.zip, a zipped folder containing the corresponding shortwave-infrared (SWIR) imagery</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_nir.zip, NIR images resized to 512x512x3 pixels</li> <li>resized_swir.zip, SWIR images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p>**** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other)
<p><strong>Description</strong></p> <p>1018 images and 1018 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (473) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, and Blue bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band images of varying sizes and extents</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p> </p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on 1-band MNDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571</p> <p> </p>
Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)
<p><em><strong>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)</strong></em></p> <p>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)</p> <p><strong>Description</strong></p> <p>4088 images and 4088 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 2 classes are 1=water, 0=other. Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue bands only</p> <p>These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Two data sources have been combined</p> <p><strong>Dataset 1</strong></p> <ul> <li>1018 image-label pairs from the following data release**** https://doi.org/10.5281/zenodo.7335647</li> <li>Labels have been reclassified from 4 classes to 2 classes.</li> <li>Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 2 classes.</li> <li>These images and labels have been made using the Doodleverse software package, Doodler*.</li> </ul> <p><strong>Dataset 2</strong></p> <ul> <li>3070 image-label pairs from the Sentinel-2 Water Edges Dataset (SWED)***** dataset, https://openmldata.ukho.gov.uk/, described by Seale et al. (2022)******</li> <li>A subset of the original SWED imagery (256 x 256 x 12) and labels (256 x 256 x 1) have been chosen, based on the criteria of more than 2.5% of the pixels represent water</li> </ul> <p><strong>File descriptions</strong></p> <ul> <li> classes.txt, a file containing the class names</li> <li> images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li> labels.zip, a zipped folder containing the 1-band label images</li> <li> overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (red=1=water, bllue=0=other)</li> <li> resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li> resized_labels.zip, label images resized to 512x512x1 pixels</li> </ul> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085https://doi.org/10.1029/2021EA002085. See https://github.com/Doodleverse/dash_doodler.</p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information</p> <p>****Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>*****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/</p> <p>******Seale, C., Redfern, T., Chatfield, P., Luo, C. and Dempsey, K., 2022. Coastline detection in satellite imagery: A deep learning approach on new benchmark data. Remote Sensing of Environment, 278, p.113044.</p>
Sentinel-2: Cloud Probability in Earth Engine
<p>Links:</p> <ul> <li><a href="https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_CLOUD_PROBABILITY">Sentinel-2: Cloud Probability</a> in Earth Engine's Public Data Catalog</li> <li><a href="https://radiantearth.github.io/stac-browser/#/external/storage.googleapis.com/earthengine-stac/catalog/COPERNICUS/COPERNICUS_S2_CLOUD_PROBABILITY.json">Sentinel-2: Cloud Probability</a> in Earth Engine STAC viewed with STAC Browser</li> </ul> <p>The S2 cloud probability is created with the <a href="https://github.com/sentinel-hub/sentinel2-cloud-detector">sentinel2-cloud-detector</a> library (using <a href="https://github.com/microsoft/LightGBM">LightGBM</a>). All bands are upsampled using bilinear interpolation to 10m resolution before the gradient boost base algorithm is applied. The resulting <code>0..1</code> floating point probability is scaled to <code>0..100</code> and stored as a UINT8. Areas missing any or all of the bands are masked out. Higher values are more likely to be clouds or highly reflective surfaces (e.g. roof tops or snow).</p> <p>Sentinel-2 is a wide-swath, high-resolution, multi-spectral imaging mission supporting Copernicus Land Monitoring studies, including the monitoring of vegetation, soil and water cover, as well as observation of inland waterways and coastal areas.</p> <p>The Level-2 data can be found in the collection <a href="https://radiantearth.github.io/stac-browser/COPERNICUS_S2_SR">COPERNICUS/S2_SR</a>. The Level-1B data can be found in the collection <a href="https://radiantearth.github.io/stac-browser/COPERNICUS_S2">COPERNICUS/S2</a>. Additional metadata is available on assets in those collections.</p> <p>See <a href="https://developers.google.com/earth-engine/tutorials/community/sentinel-2-s2cloudless">this tutorial</a> explaining how to apply the cloud mask.</p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, D. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p>
Sentinel-5P Tropospheric Nitrogen Dioxide Density at 2 km from 2018-05 to 2022-11 Monthly Aggregation
<p>Layers include: Tropospheric Nitrogen Dioxide Density monthly median value May 2018 – November 2022. Derived using the <a href="https://eumap.readthedocs.io/en/latest/index.html#">eumap package in Python</a>. We derived three standard statistics: (1) 10th percentile (p10), median (m), and 90th percentile (p10).</p> <p>Band info</p> <table> <tbody> <tr> <td>Name</td> <td>Units</td> <td>Scale</td> <td> <p>Description</p> </td> </tr> <tr> <td>NO<sub>2</sub></td> <td>(µmol m<sup>-</sup><sup>2</sup>)</td> <td>0.1</td> <td>tropospheric nitrogen dioxide density</td> </tr> </tbody> </table> <p>Warning:</p> <p>Original data have the different range of latitude among months. In December, there are no data above N 58°, where is approximately between Iceland and Scotland. Therefore, when it comes to monthly aggregation, there is a strip across N 58° as an artifact. It is not suggested to use this dataset in the region above N 58°.</p> <p>For more info about the s5p NO<sub>2</sub> product see: <a href="https://maps.s5p-pal.com"><strong>https://maps.s5p-pal.com/</strong></a>. Antarctica is not included.</p> <p>To access and visualize maps use: <a href="http://www.openlandmap.org/">OpenLandMap.org</a></p> <p>If you discover a bug, artifact or inconsistency, or if you have a question please use some of the following channels:</p> <ul> <li>Technical issues and questions about the code: <a href="https://gitlab.com/openlandmap/global-layers/-/issues">https://gitlab.com/openlandmap/global-layers/-/issues</a> </li> <li>General questions and comments: <a href="https://disqus.com/home/forums/landgis/">https://disqus.com/home/forums/landgis/</a></li> </ul> <p>All files internally compressed using "COMPRESS=DEFLATE" creation option in GDAL in Cloud Optimised GeoTiff (COG). File naming convention:</p> <ul> <li>no2 = variable: nitrogen dioxide (µmol m<sup>-</sup><sup>2</sup>),</li> <li>s5p.l3.trop.tmwm= determination method: Copernicus Sentinel-5P product, level 3, tropospheric, temporal moving window median</li> <li>p10/p50/p90 = aggregation/statistics method: 10th/50th/90th percentile,</li> <li>2km = spatial resolution / block support: 2 km,</li> <li>a = vertical reference: above ground,</li> <li>start date_end date (i.e. 20180501_20180531) = time reference: from start date to end date</li> <li>go = bounding box: global land without Antarctica</li> <li>epsg.4326 = ESPG code: epsg.4326</li> <li>v20221219 = version code: creation date 20221219</li> </ul>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on NDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on MNDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263 </a></p>
Mapping ecosystem types and land cover types in the Seychelles granitic islands, using Earth Engine and Sentinel-2
<p>We share here maps produced using Earth Engine: https://code.earthengine.google.com/?accept_repo=users/bsenterre/gis</p> <p>The maps include a land cover classification based on Sentinel-2, at 10m resolution, using an Object-Based Image Analysis approach, for the Seychelles granitic islands. Based on the land cover, landform (modeled using TauDEM), altitude and expert knowledge, we then derived a model of ecosystem types, with 3 maps: current distribution, potential distribution and prehuman distribution.</p> <p>A report exists (18th May 2022) that describes in detail the methodology, and it is being used for the preparation of a publication. The maps uploaded here are in raster format (geotif), crs=4326, and are accompanied by QGIS legend files (.qml), so they should load in QGIS with their legend automatically.</p>
SEN12TP - Sentinel-1 and -2 images, timely paired
<p>The SEN12TP dataset (<strong>Sen</strong>tinel-<strong>1</strong> and -<strong>2</strong> imagery, timely <strong>p</strong>aired) 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 <span class="math-tex">\(\sigma^\circ\)</span> radar backscatter also the radiometric terrain corrected <span class="math-tex">\(\gamma^\circ\)</span> radar backscatter is calculated and included. <span class="math-tex">\(\gamma^\circ\)</span> values are calculated using the volumetric model presented by Vollrath et. al 2020.</p> <p>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.</p> <p>Please cite the following paper when using the dataset, in which the design and creation is detailed:<br> T. Roßberg and M. Schmitt. <strong>A globally applicable method for NDVI estimation from Sentinel-1 SAR backscatter using a deep neural network and the SEN12TP dataset</strong>. <em>PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science</em>, 2023. <a href="https://doi.org/10.1007/s41064-023-00238-y">https://doi.org/10.1007/s41064-023-00238-y</a>.</p> <p> </p> <p>The file <code>sen12tp-metadata.json</code> 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).</p> <p>Naming scheme: The images are contained in directories called <em>{roi_id}_{scene_id}</em>, 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 <em>{scene_id}_{modality}.tif</em>. Multiple modalities are included: radar backscatter and multispectral optical images, the elevation as DSM (digital surface model) and different land cover maps.</p> <table summary="Included modalities in the dataset."> <caption>Data modalities</caption> <thead> <tr> <th scope="col">name</th> <th scope="col">Modality</th> <th scope="col">GEE collection</th> </tr> </thead> <tbody> <tr> <td>s1</td> <td>Sentinel-1 radar backscatter</td> <td><a href="https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S1_GRD"><code>COPERNICUS/S1_GRD</code></a></td> </tr> <tr> <td>s2</td> <td>Sentinel-2 Level-2A (Bottom of atmosphere, BOA) multispectral optical data with added cloud probability band</td> <td><a href="https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_SR"><code>COPERNICUS/S2_SR</code></a><br> <a href="https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_CLOUD_PROBABILITY"><code>COPERNICUS/S2_CLOUD_PROBABILITY</code></a></td> </tr> <tr> <td>dsm</td> <td>30m digital surface model</td> <td><a href="https://developers.google.com/earth-engine/datasets/catalog/JAXA_ALOS_AW3D30_V3_2"><code>JAXA/ALOS/AW3D30/V3_2</code></a></td> </tr> <tr> <td>worldcover</td> <td>land cover, 10m resolution</td> <td><a href="https://developers.google.com/earth-engine/datasets/catalog/ESA_WorldCover_v100"><code>ESA/WorldCover/v100</code></a></td> </tr> </tbody> </table> <p> </p> <p>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.</p> <table> <caption>Modality Bands</caption> <tbody> <tr> <td><strong>Modality</strong></td> <td><strong>Band count</strong></td> <td><strong>Band names in tif file</strong></td> <td><strong>Notes</strong></td> </tr> <tr> <td>s1</td> <td>5</td> <td>VV_sigma0, VH_sigma0, VV_gamma0flat, VH_gamma0flat, incAngle</td> <td>VV/VH_sigma0 are the <span class="math-tex">\(\sigma^\circ\)</span> values,<br> VV/VH_gamma0flat are the radiometric terrain corrected <span class="math-tex">\(\gamma^\circ\)</span> backscatter values<br> incAngle is the incident angle</td> </tr> <tr> <td>s2</td> <td>13</td> <td>B1, B2, B3, B4, B5, B7, B7, B8, B8A, B9, B11, B12, cloud_probability</td> <td>multispectral optical bands and the probability that a pixel is cloudy, calculated with the <a href="https://github.com/sentinel-hub/sentinel2-cloud-detector">sentinel2-cloud-detector</a> library<br> optical reflectances are bottom of atmosphere (BOA) reflectances calculated using <em>sen2cor</em></td> </tr> <tr> <td>dsm</td> <td>1</td> <td>DSM</td> <td>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.</td> </tr> <tr> <td>worldcover</td> <td>1</td> <td>Map</td> <td>Landcover class</td> </tr> </tbody> </table> <p> </p> <p><strong>Checking the file integrity</strong><br> After downloading and decompression the file integrity can be checked using the provided file of md5 checksum.<br> Under Linux: <code>md5sum --check --quiet md5sums.txt</code></p> <p> </p> <p><strong>References:</strong></p> <p>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.</p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p><em><strong>Version 3: Updated 2023-04-25</strong></em></p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p> <p>Classes: {0=other, 1=water}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, D. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384242">https://doi.org/10.5281/zenodo.7384242</a></p>
FORMS: Forest Multiple Source height, wood volume, and biomass maps in France at 10 to 30 m resolution based on Sentinel-1, Sentinel-2, and GEDI data with a deep learning approach.
<p>The products can be vizualized at <a href="https://martinschwartz0.users.earthengine.app/view/forms-height-biomass-volume-viewer">https://martinschwartz0.users.earthengine.app/view/forms-height-biomass-volume-viewer</a></p> <p>- FORMS-H: Canopy height map of France at 10 m resolution. The units are in centimeter (10^-2 m).</p> <p>- FORMS-B: Above-ground biomass density map of France at 30 m resolution. The units are in Mg ha-1</p> <p>- FORMS-V: Wood volume density map of France at 30 m resolution. The units are in m3 ha-1</p> <p>Please refer to the paper <a href="https://doi.org/10.5194/essd-15-4927-2023">https://doi.org/10.5194/essd-15-4927-2023</a> for further details.</p>
June 2023 Supplement Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)
<p><strong>June 2023 Supplement of Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)</strong></p> <p><strong>Description</strong></p> <p>Supplementary dataset to:</p> <p>Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>This supplemental dataset consists of 283 RGB images and 283 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. Of these, 77 images-label pairs also have a corresponding NIR and SWIR satellite image. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. NIR, SWIR, Red, Green, and Blue bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band images of varying sizes and extents</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>nir.zip</li> <li>swir.zip</li> </ol> <p><strong>References</strong></p> <p>Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7335647</p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p> </p>
Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p>These Segformer model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following datasets**: <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a> and ***https://doi.org/10.5281/zenodo.8011926. Those datasets have been combined and the training and validation images and labels are provided here.</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>Model validation accuracy statistics</strong></p> <p>model name: overall accuracy, mean frequency weighted IoU, mean IoU, Matthews correlation. Bold indicates best overall</p> <ul> <li><strong>v5: .94, .90, .64, .87</strong></li> <li>v6: .93, .89, .63, .87</li> <li>v7: .92, .88, .61, .84</li> <li>v8: .93, .89, .63, .87</li> <li>v9: .92, .88, .62, .85</li> <li>v10: .93, .89, .63, .86</li> </ul> <p> </p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p>This is a sister model to this set of Residual UNets: Buscombe, Daniel. (2022). Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts. (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6950472</p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>***Buscombe, Daniel. (2023). June 2023 Supplement Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8011926 </p> <p> </p> <p> </p>
Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 MNDWI images of coasts.
<p><em><strong>Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 MNDWI images of coasts.</strong></em></p> <p>Models have been created using Segmentation Gym* using the following datasets ** https://zenodo.org/record/7384263 and ***: https://doi.org/10.5281/zenodo.7335647. Those datasets have been combined and the training and validation images and labels are provided here.</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>Model validation accuracy statistics</strong></p> <p>model name: overall accuracy, mean frequency weighted IoU, mean IoU, Matthews correlation. Bold indicates best overall</p> <p> v2: 0.808, 0.7309, 0.47864, 0.656<br> v3: 0.809, 0.7302, 0.4982, 0.664</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p>This is a sister model to these sets of Residual UNets:</p> <p> https://zenodo.org/record/7352850<br> https://zenodo.org/record/7557080</p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** Buscombe, Daniel. (2022). Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7384263</p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information</p> <p>***Buscombe, Daniel. (2023). June 2023 Supplement Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8011926 </p>
Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 NDWI images of coasts.
<p><strong>Doodleverse/CoastSeg Segformer models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 NDWI images of coasts.</strong></p> <p>Models have been created using Segmentation Gym* using the following datasets ** https://zenodo.org/record/7384263 and ***: https://doi.org/10.5281/zenodo.7335647. Those datasets have been combined and the training and validation images and labels are provided here.</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>Model validation accuracy statistics</strong></p> <p>model name: overall accuracy, mean frequency weighted IoU, mean IoU, Matthews correlation. Bold indicates best overall</p> <table> <tbody> <tr> <td>0.896016693115234</td> <td>0.832759195999637</td> <td>0.565748652153519</td> <td>0.806139409136944</td> </tr> </tbody> </table> <table> <tbody> <tr> <td>0.906008201175266</td> <td>0.847625161837392</td> <td>0.593821675882991</td> <td>0.819790462192222</td> </tr> </tbody> </table> <table> <tbody> <tr> <td>0.903999212053087</td> <td>0.844255821722932</td> <td>0.577444030164045</td> <td>0.813646408575</td> </tr> </tbody> </table> <p> </p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p>This is a sister model to these sets of Residual UNets:</p> <p>https://zenodo.org/record/7557072<br> https://zenodo.org/record/7352859</p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** https://zenodo.org/record/7384263</p> <p>***Buscombe, Daniel. (2023). June 2023 Supplement Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.8011926 </p>
Texas 2022 water clarity and color (FLAMe and Sentinel-2)
Water clarity and color were determined for six reservoirs using rapid spatial surveys from a sensor equipped boat and concurrent Sentinel-2 satellite imagery across Texas during drought conditions between the months of July and August 2022. From west to east, these systems include Red Bluff Reservoir, O.H. Ivie Lake, Lake Arrowhead, Lake Brownwood, Lake Waco, and Lake Bonham. For the water year leading up to the sampling dates, the precipitation ranged from 182 mm in Red Bluff Reservoir to 1036 mm in Lake Bonham. A total of 254 km of boat path were covered across the six reservoirs with a mean boat speed of 19.17 km/h. The data for this study covers three spatial approaches 1) along the boat path 2) longitudinal transects from dam to river arm and 3) whole system. For the boat path, data variables include turbidity measured continuously with a YSI EXO2 sonde, Secchi disk depth predicted from the turbidity values, normalized difference turbidity index (NDTI), and dominant wavelength. For both the longitudinal transects and whole system data, variables include the two remotely derived measures of clarity and color, NDTI and dominant wavelength. Data is also categorized by zone as either "arm" (reservoir arm) or "body" (main body) determined by a 4m depth threshold to compare between zones.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.