Find research datasets worth reusing

opencc-by-4.0Nov 2023View details →

A Construction Waste Landfill Dataset of Two Districts in Beijing, China from High Resolution Satellite Images

CWLD_model project shows scripts and instructions on how to use this dataset to train a segmentation model. requirements.txt files provide the libraries you need to run your project. The README.md document details the deployment process and features of each module. You can also visit the GitHub page for scripts and instructions on how to use this dataset for visualizing and plotting basic statistics. The models and the code to execute them are released on <a href="https://github.com/huangleinxidimejd/CWLD_Model">https://github.com/huangleinxidimejd/CWLD_Model</a>. <h2>Training details</h2> The model was trained with two GPUs, an Nvidia GeForce RTX 2080Ti, and the following parameters: <ul> <li>'train_batch_size': 4,</li> <li>'val_batch_size': 4,</li> <li>'train_crop_size': 512,</li> <li>'val_crop_size': 512,</li> <li>'lr': 0.001, # the learning rate used during training. It determines how quickly the model learns from the data</li> <li>'Epoch Times': 200,</li> <li>'gpu': correct,</li> <li>'weight_decay': 5E-4,</li> <li>'Momentum': 0.9,</li> <li>'print_freq': 100,</li> <li>'predict_step': 5,</li> </ul> <h2>usage</h2> <ul> <li>After downloading the dataset from Zenodo, place the train and val files from the Deep Learning Datasets file into the data folder of the CWLD semantic segmentation model.</li> <li>Open: CWLD_ Open the root directory in CWLD_model/dataset/ and start training with the WasteSeg_Train.py file. The modelss module provides five convolutional networks, Improved_DeeplabV3_plus, PSPNet, ResNet, SegNet, and UNet, which can be selected and modified accordingly.</li> <li>The utils package provides a large number of data processing tools to use.</li> <li>The trained model can be predicted from a EvalSeg.py file.</li> </ul>

Semantic segmentation model of construction waste landfill based on high-resolution satellite images

CWLD_model project shows scripts and instructions on how to use this dataset (<a href="../records/10686118">https://zenodo.org/records/10686118</a>) to train a segmentation model. requirements.txt files provide the libraries you need to run your project. The README.md document details the deployment process and features of each module. You can also visit the GitHub page for scripts and instructions on how to use this dataset for visualizing and plotting basic statistics. The models and the code to execute them are released on <a href="https://github.com/huangleinxidimejd/CWLD_Model">https://github.com/huangleinxidimejd/CWLD_Model</a>. <h2>Training details</h2> The model was trained with two GPUs, an Nvidia GeForce RTX 2080Ti, and the following parameters: <ul> <li>'train_batch_size': 4,</li> <li>'val_batch_size': 4,</li> <li>'train_crop_size': 512,</li> <li>'val_crop_size': 512,</li> <li>'lr': 0.001, # the learning rate used during training. It determines how quickly the model learns from the data</li> <li>'Epoch Times': 200,</li> <li>'gpu': correct,</li> <li>'weight_decay': 5E-4,</li> <li>'Momentum': 0.9,</li> <li>'print_freq': 100,</li> <li>'predict_step': 5,</li> </ul> <h2>usage</h2> <ul> <li>After downloading the dataset from Zenodo, place the train and val files from the Deep Learning Datasets file into the data folder of the CWLD semantic segmentation model.</li> <li>Open: CWLD_ Open the root directory in CWLD_model/dataset/ and start training with the WasteSeg_Train.py file. The modelss module provides five convolutional networks, Improved_DeeplabV3_plus, PSPNet, ResNet, SegNet, and UNet, which can be selected and modified accordingly.</li> <li>The utils package provides a large number of data processing tools to use.</li> <li>The trained model can be predicted from a EvalSeg.py file.</li> </ul>

opencc-by-4.0Jul 2022View details →

Dataset of polygons with the contour of 900 juniper shrubs used to track shrub growth from 1977 to 2020 in Sierra Nevada (Spain) using very high resolution aerial and satellite RGB images.

This database provides as polygons the contours of 900 juniper shrubs (Juniperus communis L. and Juniperus sabina L.) along 5 decades (years 1977, 1984, 2001, 2010 and 2020). The contour of each of 900 shrubs manually mapped using the Google Satellite composite for the year 2020) was tracked back in time using orthophotos provided by REDIAM. Contours were obtained by manual annotation as polygon shapefiles in QGIS 3.10.3. Additionally, for the year 2020, the polygons were characterized with five attributes that gather ecological information: Morphotype (Hemispherical, Striped, Senescent, With rock), Presence of surrounding vegetation (Bare Soil, Surrounding Vegetation), Presence of nearby human land-uses (Surrounded by human facilities within 250 meters, Non-anthropized environment) Health status (as percentage of canopy cover with brown foliage: values between 0-5, where 0 corresponds to 100% photosynthetically active cover, decreasing the photosynthetically active cover until category 5 which corresponds to 100% damaged cover), and the subjective annotation certainty of the GIS technician (values between 0-5, where the value 0 corresponds to a very uncertain annotation up to the value 5 which corresponds to a fairly certain annotation).

openmit-licenseJan 2024View details →

Dataset - DeepWealth: A Generalizable Open-Source Deep Learning Framework using Satellite Images for Well-Being Estimation

This dataset encapsulates the Checkpoints obtained during the training process of the Deep Learning model, which can be used for new estimations. The aim of the DeepWealth package is to provide a generalizable Deep Learning framework for the use of remote sensing in poverty estimation. The combination of Deep Learning and Earth Observation data is increasingly being used to estimate socioeconomic conditions at regional and global scales. The proposed framework aligns with the Sustainable Development Goal SDG1 of ending poverty. The framework provides open-source data, code, and training models (checkpoints) for reproducibility and replicability. <ul> <li>The source code can be found in <a href="https://github.com/PARSECworld/DeepWealth" target="_blank" rel="noopener">https://github.com/PARSECworld/DeepWealth</a></li> <li>The metadata from source code can be found in <a href="https://github.com/PARSECworld/DeepWealth/blob/main/metadata.pdf" target="_blank" rel="noopener">https://github.com/PARSECworld/DeepWealth/blob/main/metadata.pdf</a></li> <li>The paper describing the development of this framework can be found at: Ben Abbes, A., Machicao, J., Corrêa, P. L. P., Specht, A., Devillers, R., Ometto, J. P., Kondo, Y., & Mouillot, D. (2024). DeepWealth: A generalizable open-source deep learning framework using satellite images for well-being estimation. SoftwareX, 27, 101785.  <a href="https://doi.org/10.1016/j.softx.2024.101785">https://doi.org/10.1016/j.softx.2024.101785</a> </li> </ul>

opencc-by-4.0Aug 2024View details →

Dataset for the publication "Superconducting gravimeter observations show that satellite-derived snow depth image improves the simulation of the snow water equivalent evolution in a high alpine site"

This datasset contains data to reproduce the following figures of the paper Superconducting gravimeter observations show that satellite-derived snow depth image improves the simulation of the snow water equivalent evolution in a high alpine site: <ul> <li> Time series data of Figures 1c and 2 </li> <li> Data (*.asc) used for plotting Figures 1d and 1e (as well as Figure S3 and S4) </li> <li>Pléiades snow depth map (Figure S1)</li> <li> Data used for plotting Figure S2 </li> </ul>

opencc-by-4.0Nov 2022View details →

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)

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) Description 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 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**. 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. 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> Imagery comes from the following 10 sand beach sites: <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> 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 File descriptions <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> References *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> **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> ***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 **** 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>

opencc-by-4.0Nov 2022View details →

Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other)

Description 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 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**. 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. Imagery comes from the following 10 sand beach sites: <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> 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 File descriptions <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> References *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> **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> ***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

opencc-by-4.0Nov 2022View details →

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other)

Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, other) Description 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 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**. Two data sources have been combined Dataset 1 <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> Dataset 2 <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> File descriptions <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> References *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. **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 ***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 ****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 *****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/ ******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.

opencc-by-4.0Feb 2023View details →

Suomi 100 satellite's images: The auroral and the star images

Spacecraft: Suomi 100 Instrument: Camera <ul> <li>White light RGB camera</li> <li>Resolution: 2048 x 1536 pixels</li> <li>Angle of view: 43.6° x 33.4° (horizontal x vertical)</li> </ul> On-board data processing: <ul> <li>Debayering</li> <li>Color correction</li> <li>Gamma correction (gamma=2.2, gamma-break: 0.1)</li> <li>JPEG compression</li> </ul> Data: Three images     1. The auroral image: Original (ID: 001229, rotated 180°) <ul> <li>File: img001229.jpg</li> <li>Imaging time: January 22, 2019, 18:08:20 UT</li> <li>Location: 62.17°N, 47.64°E, 582865 m (WGS84)</li> <li>Attitude: heading -31.21°, tilt 68.89°, roll -1.85°</li> <li>Integration time: 2.4 seconds</li> <li>Sensor gain: x128</li> </ul>     2. The auroral image: Processed version (see Knuuttila et al., JoSS, 2022, for details) <ul> <li>File: img001229_processed.png</li> <li>Inverted on-board data processing (excl. debayering)</li> <li>Subtracted the star image (ID: 001264) to compensate warm pixel effec</li> </ul>     3. The original star image used for background subtraction (ID: 001264) <ul> <li>File: img001264.jpg</li> <li>Imaging time: January 23, 2019, 18:13 UT</li> <li>Attitude: declination -1.3°, right ascension 97.1°, celestial north clock angle -21.8° (J2000)</li> <li>Integration time: 1.6 seconds</li> <li>Sensor gain: x32</li> </ul>

opencc-by-4.0Jun 2023View details →

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)

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) Description Supplementary dataset to: 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 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 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**. 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 File descriptions <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> References 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 *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> **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>

opencc-by-4.0Jul 2023View details →

Input and output data (images + boulder labels, model setup, model weights and more) for the manuscript "Automatic characterization of boulders on planetary surfaces from high-resolution satellite images"

File 1: raw_data_BOULDERING.zip Size: 8.8 GB Summary: It contains all of the rasters (planetary images) and labeled boulders (raw data): <ul> <li> a boulder-mapping file, which is the manually digitized outline of boulders. </li> <li> a ROM file (stands for Region of Mapping), which depicts the image patches on which the boulder mapping has been conducted. </li> <li> a global-tiles file, which shows all of the image patches within a raster. </li> </ul> There are multiple locations/images per planetary body. Structure: <pre>. └── raw_data/ ├── earth/ │ └── image_name/ │   ├── shp/ │   │ ├── <image_name>-ROM.shp │   │ ├── <image_name>-boulder-mapping.shp │   │ └── <image_name>-global-tiles.shp │   └── raster/ │     └── <image_name>.tif ├── mars/ │ └── image_name/ │   ├── shp/ │   │ ├── <image_name>-ROM.shp │   │ ├── <image_name>-boulder-mapping.shp │   │ └── <image_name>-global-tiles.shp │   └── raster/ │     └── <image_name>.tif └── moon/   └── image_name/     ├── shp/     │ ├── <image_name>-ROM.shp     │ ├── <image_name>-boulder-mapping.shp     │ └── <image_name>-global-tiles.shp     └── raster/       └── <image_name>.tif</pre>   File 2: best_model.zip Size: 624.7 MB Summary: This zip file contains all of the inputs and outputs required/obtained from the training of the BoulderNet Mask R-CNN model (model setup, augmentation pipeline, model weights, log during training, logged metrics): <ul> <li> augmentation_pipeline.json (required as inputs for the training of the algorithm to apply augmentations). See <a href="https://github.com/astroNils">https://github.com/astroNils</a> and the MLtools repository for more information. </li> </ul> <ul> <li> Base-RCNN-FPN.yaml (base model setup file). </li> <li> config.yaml (complete model setup file, merge of the base and Mars-Moon-Earth setup file). </li> <li> Mars-MoonEarth-v050...yaml (model setup file). </li> <li> log.txt (log during training of the algorithm). </li> <li> model_0055999.pth (model weights at second last saving step) </li> <li> model_0063999.pth (model weights at last saving step) </li> </ul> We advice the use of model weights model_0055999.pth (to avoid slight overfitting). File 3: Apr2023-Mars-Moon-Earth-mask-5px.zip (pre-processed input images) Size: 252.8 MB Summary: This zip files contains the input data (images and boulder outlines) for the train, validation and test datasets. See <a href="https://github.com/astroNils">https://github.com/astroNils</a> and the MLtools repository for more information in how-to-use the different files. <ul> <li> The json folder contains json files that can be given as input (as a custom dataset) to the Detectron2 platform. The only differences between the two files is how the bounding boxes around masks have been generated. We advised to use "Apr2023-Mars-Moon-Earth-mask-5px.json". </li> <li> The pkl folder and pickle file includes some informations about the 950 image patches in our boulder dataset. </li> <li> The pre-processing folder contains all of the training, validation and test image patches and corresponding shapefiles. </li> <li> The shapefile folder is actually empty (it should not be there!). </li> </ul> Structure: <pre>. └── preprocessed_inputs/   ├── json   ├── pkl   ├── preprocessing/   │   ├── train/   │   │   ├── images   │   │   └── labels   │   ├── validation/   │   │   ├── images   │   │   └── labels   │   └── test/   │       ├── images   │       └── labels   └── shp</pre>

opencc-by-4.0Sep 2016View details →

Satellite images of the 17 July 2016 Aru Co glacier collapse

These satellite images were made to visualize the Aru Co glacier avalanche. Some of them were used in these blog posts: <ul> <li>Séries Temporelles (2016, August 25) Sentinel-2A captures a giant ice avalanche in Tibet. http://www.cesbio.ups-tlse.fr/multitemp/?p=8294</li> <li>Séries Temporelles (2016, August 25) Sentinel-2A (and Landsat-8) capture a giant ice avalanche in Tibet http://www.cesbio.ups-tlse.fr/multitemp/?p=8327</li> </ul> Files description: <ul> <li>File 2016-07-21_S2.tif: Sentinel-2A image of the Aru Co glacier avalanche acquired on 21-Jul-2016 (4 days after the event). RGB composite of bands B4,B3,B2 scaled to bytes between 0 and 0.5 from level 1C product (orthorectified top-of-atmosphere reflectances). Format: Geotiff, WGS 84 / UTM zone 44N.</li> <li>File 2016-06-24_L8mos.tif: Landsat-8 image of the Aru Co area acquired on 24-Jun-2016 (23 days before the event). RGB composite of bands B4,B3,B2 scaled to bytes between 0 and 0.5 from level 1C product (orthorectified top-of-atmosphere reflectances). Format: Geotiff, WGS 84 / UTM zone 44N.</li> <li>File anim.gif: animated sequence of both images using the lowest resolution image (Landsat-8)</li> <li>File diff_S2minusL8_band3.tif: difference between the band 3 of the 2016-07-21 Sentinel-2A image and the 2016-06-24 Landsat-8 image after a nearest neighbour resampling of the Sentinel-2 image to the same resolution as the Landsat-8 image (30 m).</li> <li>2016-07-25_S1.tif : Sentinel-1 image of the Aru Co glacier avalanche acquired on 25-Jul-2016 (8 days after the event). VV co-polar band, ascending orbit. The images was pre-processed to backscatter coefficient in decibels after thermal noise removal, radiometric calibration and terrain correction.</li> <li>2016-07-25_S1.tif : Sentinel-1 image of the Aru Co glacier avalanche acquired on 25-Jul-2016 (8 days after the event). VV co-polar band, ascending orbit. The image was pre-processed to backscatter coefficient in decibels after thermal noise removal, radiometric calibration and terrain correction.</li> <li>2016-07-01_S1.tif : Sentinel-1 image of the Aru Co glacier avalanche acquired on 07-Jul-2016 (10 days before the event). VV co-polar band, ascending orbit. The image was pre-processed to backscatter coefficient in decibels after thermal noise removal, radiometric calibration and terrain correction.</li> <li>2016-07-21-01_S1_diff_smoothed_Lee.tif : difference between both Sentinel-1 images after applying a refined Lee filter on the radar intensities</li> </ul> Spatial extent of all the images in WGS 84 UTM 44N and lon/lat coordinates : Upper Left ( 602260.000, 3777670.000) ( 82d 6'32.64"E, 34d 8' 5.67"N) Lower Left ( 602260.000, 3755030.000) ( 82d 6'23.08"E, 33d55'50.74"N) Upper Right ( 640720.000, 3777670.000) ( 82d31'33.86"E, 34d 7'49.56"N) Lower Right ( 640720.000, 3755030.000) ( 82d31'20.72"E, 33d55'34.75"N)

opencc-by-4.0Oct 2023View details →

CloudTracks: A Dataset for Localizing Ship Tracks in Satellite Images of Clouds

The CloudTracks dataset consists of 1,780 MODIS satellite images hand-labeled for the presence of more than 12,000 ship tracks. More information about how the dataset was constructed may be found at <a href="http://github.com/stanfordmlgroup/CloudTracks">github.com/stanfordmlgroup/CloudTracks</a>. The file structure of the dataset is as follows:CloudTracks/     full/        images/           (sample image name) mod2002121.1920D.png        jsons/           (sample json name) mod2002121.1920D.jsonThe naming convention is as follows: mod2002121.1920D: the first 3 letters specify which of the sensors on the two MODIS satellites captured the image, mod for Terra and myd for Aqua. This is followed by a 4 digit year (2002) and a 3 digit day of the year (121). The following 4 digits specify the time of day (1920; 24 hour format in the UTC timezone), followed by D or N for Day or Night.The 1,780 MODIS Terra and Aqua images were collected between 2002 and 2021 inclusive over various stratocumulus cloud regions (such as the East Pacific and East Atlantic) where ship tracks have commonly been observed. Each image has dimension 1354 x 2030 and a spatial resolution of 1km. Of the 36 bands collected by the instruments, we selected channels 1, 20, and 32 to capture useful physical properties of cloud formations.The labels are found in the corresponding JSON files for each image. The following keys in the json are particularly important:imagePath: the filename of the image. shapes: the list of annotations corresponding to the image, where each element of the list is a dictionary corresponding to a single instance annotation. The dictionary has a key with value "shiptrack" or "uncertain" which is the label of the annotation and the corresponding value is a linestrip detailing the ship track path.Further pre-processing details may be found at the GitHub link above. If you have any questions about the dataset, contact us at: <a href="mailto:mahmedch@stanford.edu">mahmedch@stanford.edu</a>, <a href="mailto:lynakim@stanford.edu">lynakim@stanford.edu</a>, <a href="mailto:jirvin16@cs.stanford.edu">jirvin16@cs.stanford.edu</a>

openetalab-2.0Apr 2024View details →

Companinon Dataset for PASTIS : VHR satellite images (SPOT 6-7)

To enhance the spatial resolution and utility of <a href="https://github.com/VSainteuf/pastis-benchmark">PASTIS-R dataset</a>, we introduce PASTIS-HD, which integrates contemporaneous VHR satellite images (SPOT 6-7), resampled to a 1m resolution and converted to 8 bits. This enhancement significantly improves the dataset's spatial content, providing more granular information for agricultural parcel segmentation. This folder can be added to the PASTIS-R dataset to get the PASTIS-HD version. The SPOT images are opendata thanks to the Dataterra Dinamis initiative in the case of the <a href="https://dinamis.data-terra.org/opendata/">"Couverture France DINAMIS" program</a>. If you use PASTIS please cite the <a href="https://arxiv.org/abs/2107.07933" rel="nofollow">related paper</a>: <blockquote> @article{garnot2021panoptic,   title={Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks},   author={Sainte Fare Garnot, Vivien  and Landrieu, Loic },   journal={ICCV},   year={2021} } </blockquote> For the PASTIS-R optical-radar fusion dataset, please also cite <a href="https://arxiv.org/abs/2112.07558v1" rel="nofollow">this paper</a>: <blockquote> <pre>@article{garnot2021mmfusion, title = {Multi-modal temporal attention models for crop mapping from satellite time series}, journal = {ISPRS Journal of Photogrammetry and Remote Sensing}, year = {2022}, doi = {https://doi.org/10.1016/j.isprsjprs.2022.03.012}, author = {Vivien {Sainte Fare Garnot} and Loic Landrieu and Nesrine Chehata}, }</pre> </blockquote> For the PASTIS-HD with the 3 modality optical-radar time series plus VHR images dataset, please also cite <a href="https://arxiv.org/abs/2404.08351">this paper</a>: <blockquote> @article{astruc2024omnisat,   title={Omni{S}at: {S}elf-Supervised Modality Fusion for {E}arth Observation},   author={Astruc, Guillaume and Gonthier, Nicolas and Mallet, Clement and Landrieu, Loic},   journal={arXiv preprint arXiv:2404.08351},   year={2024} } </blockquote>

РИС. 2. Места нахождениЯ Amuranodonta kijaensis на территории Хинганского Заповедника, АмурскаЯ обл.: А. Схема расположениЯ лесничеств: 1 – Антоновское, 2 – Лебединское, 3 – Хинганское. B. ТопографическаЯ карта Антоновского вдхр. у пос. Архара. С, D. Топографические карты и спутниковый снимок оЗ. Яценково на территории Антоновского лесничества. E–G. ТопографическаЯ карта и спутниковый снимок оЗ. ПереШеечное на территории Лебединского лесничества. МасШтабные линейки: 20 км (А), 4 км (В, Е), 5 км (С), 1 км (D, G), 2 км (F). FIG. 2. Localities of Amuranodonta kijaensis in the Khingansky Reserve, Amur Region: A. Layout of forestry areas: 1 – Antonovsky, 2 – Lebedinsky, 3 – Khingansky. B. Topographic map of Antonovskoe Reservoir near Arkhara village. C, D. Topographic maps and satellite image of Yatsenkovo lake, Antonovsky forestry. E–G. Topographic map and satellite image of Peresheechnoe lake, Lebedinsky forestry. Scale bars: 20 km (A), 4 km (B, E), 5 km (C), 1 km (D, G), 2 km (F). in Новые данные об охранЯемом пресноводном двустворчатом моллюске Amuranodonta kijaensis Moskvicheva, 1973 (Unionidae, Anodontinae)

РИС. 2. Места нахождениЯ Amuranodonta kijaensis на территории Хинганского Заповедника, АмурскаЯ обл.: А. Схема расположениЯ лесничеств: 1 – Антоновское, 2 – Лебединское, 3 – Хинганское. B. ТопографическаЯ карта Антоновского вдхр. у пос. Архара. С, D. Топографические карты и спутниковый снимок оЗ. Яценково на территории Антоновского лесничества. E–G. ТопографическаЯ карта и спутниковый снимок оЗ. ПереШеечное на территории Лебединского лесничества. МасШтабные линейки: 20 км (А), 4 км (В, Е), 5 км (С), 1 км (D, G), 2 км (F). FIG. 2. Localities of Amuranodonta kijaensis in the Khingansky Reserve, Amur Region: A. Layout of forestry areas: 1 – Antonovsky, 2 – Lebedinsky, 3 – Khingansky. B. Topographic map of Antonovskoe Reservoir near Arkhara village. C, D. Topographic maps and satellite image of Yatsenkovo lake, Antonovsky forestry. E–G. Topographic map and satellite image of Peresheechnoe lake, Lebedinsky forestry. Scale bars: 20 km (A), 4 km (B, E), 5 km (C), 1 km (D, G), 2 km (F).

РИС. 3. Место нахождениЯ Amuranodonta kijaensis в Хабаровском крае: А. Карта-схема краЯ. В. Приустьевый участок р. Амур. С, D. ТопографическаЯ карта и спутниковый снимок с. Чныррах с укаЗанием места сбора. МасШтабные линейки: 200 км (А), 16 км (B), 4 км (C) и 200 м (D). FIG. 3. Locality of Amuranodonta kijaensis in the Khabarovsk Territory: A. Scheme map of the region. B. Amur River mouth area. C, D. Topographic map and satellite image of Chnyrrakh village indicating the collection site. Scale bars: 200 km (А), 16 km (B), 4 km (C), and 200 m (D). in Новые данные об охранЯемом пресноводном двустворчатом моллюске Amuranodonta kijaensis Moskvicheva, 1973 (Unionidae, Anodontinae)

РИС. 3. Место нахождениЯ Amuranodonta kijaensis в Хабаровском крае: А. Карта-схема краЯ. В. Приустьевый участок р. Амур. С, D. ТопографическаЯ карта и спутниковый снимок с. Чныррах с укаЗанием места сбора. МасШтабные линейки: 200 км (А), 16 км (B), 4 км (C) и 200 м (D). FIG. 3. Locality of Amuranodonta kijaensis in the Khabarovsk Territory: A. Scheme map of the region. B. Amur River mouth area. C, D. Topographic map and satellite image of Chnyrrakh village indicating the collection site. Scale bars: 200 km (А), 16 km (B), 4 km (C), and 200 m (D).

РИС. 1. Место нахождениЯ Amuranodonta kijaensis в Зейском районе, АмурскаЯ обл.: А. Карта-схема области. B. Зейское вдхр. С, D. ТопографическаЯ карта и спутниковый снимок Залива в Западной части Зейского вдхр. у пос. Береговой с укаЗанием места сбора. МасШтабные линейки: 300 км (А), 50 км (В), 4 км (С) и 200 м (D). FIG. 1. Locality of Amuranodonta kijaensis in Zeya District, Amur Region: A. Schematic map of the region. B. Zeya Reservoir. C, D. Topographic map and satellite image of the bay in the western part of Zeya Reservoir near Beregovoi village indicating the collection site. Scale bars: 300 km (А), 50 km (В), 4 km (С), and 200 m (D). in Новые данные об охранЯемом пресноводном двустворчатом моллюске Amuranodonta kijaensis Moskvicheva, 1973 (Unionidae, Anodontinae)

РИС. 1. Место нахождениЯ Amuranodonta kijaensis в Зейском районе, АмурскаЯ обл.: А. Карта-схема области. B. Зейское вдхр. С, D. ТопографическаЯ карта и спутниковый снимок Залива в Западной части Зейского вдхр. у пос. Береговой с укаЗанием места сбора. МасШтабные линейки: 300 км (А), 50 км (В), 4 км (С) и 200 м (D). FIG. 1. Locality of Amuranodonta kijaensis in Zeya District, Amur Region: A. Schematic map of the region. B. Zeya Reservoir. C, D. Topographic map and satellite image of the bay in the western part of Zeya Reservoir near Beregovoi village indicating the collection site. Scale bars: 300 km (А), 50 km (В), 4 km (С), and 200 m (D).

opencc-by-sa-4.0Nov 2024View details →

Global ML-ready dataset for mining areas in satellite images

This dataset is a global resource for machine learning applications in mining area detection and semantic segmentation on satellite imagery. It contains Sentinel-2 satellite images and corresponding mining area masks + bounding boxes for 1,210 sites worldwide. Ground-truth masks are derived from <a href="https://doi.org/10.1594/PANGAEA.942325" target="_blank" rel="noopener">Maus et al. (2022)</a> and <a href="https://doi.org/10.5281/zenodo.6806817" target="_blank" rel="noopener">Tang et al. (2023)</a>, and validated through manual verification to ensure accurate alignment with Sentinel-2 imagery from specific timestamps.  The dataset includes three mask variants: <ul> <li>Masks exclusively from Maus et al. (n=1,090)</li> <li>Masks exclusively from Tang et al. (n=817)</li> <li>A preferred mask selected from either Maus or Tang based on alignment quality determined during manual review (n=1,210).</li> </ul> Each tile corresponds to a 2048x2048 pixel Sentinel-2 image, with metadata on mine type (surface, placer, underground, brine & evaporation) and scale (artisanal, industrial). For convenience, the preferred mask dataset is already split into training (75%), validation (15%), and test (10%) sets.  Furthermore, dataset quality was validated by re-validating test set tiles manually and correcting any mismatches between mining polygons and visually observed true mining area in the images, resulting in the following estimated quality metrics:  <table> <tbody> <tr> <td> </td> <td>Combined</td> <td>Maus</td> <td>Tang</td> </tr> <tr> <td>Accuracy</td> <td>99.78</td> <td>99.74</td> <td>99.83</td> </tr> <tr> <td>Precision</td> <td>99.22</td> <td>99.20</td> <td>99.24</td> </tr> <tr> <td>Recall</td> <td>95.71</td> <td>96.34</td> <td>95.10</td> </tr> </tbody> </table> Note that the dataset does not contain the Sentinel-2 images themselves but contains a reference to specific Sentinel-2 images. Thus, for any ML applications, the images must be persisted first. For example, Sentinel-2 imagery is available from Microsoft's Planetary Computer and filterable via STAC API: <a href="https://planetarycomputer.microsoft.com/dataset/sentinel-2-l2a" target="_blank" rel="noopener">https://planetarycomputer.microsoft.com/dataset/sentinel-2-l2a</a>. Additionally, the temporal specificity of the data allows integration with other imagery sources from the indicated timestamp, such as Landsat or other high-resolution imagery. Source code used to generate this dataset and to use it for ML model training is available at <a href="https://github.com/SimonJasansky/mine-segmentation" target="_blank" rel="noopener">https://github.com/SimonJasansky/mine-segmentation</a>. It includes useful Python scripts, e.g. to <a href="https://github.com/SimonJasansky/mine-segmentation/blob/main/src/data/05_persist_pixels_masks.py">download Sentinel-2 images via STAC API</a>, or to <a href="https://github.com/SimonJasansky/mine-segmentation/blob/main/src/data/06_make_chips.py">divide tile images (2048x2048px) into smaller chips (e.g. 512x512px)</a>.  A database schema, a schematic depiction of the dataset generation process, and a map of the global distribution of tiles are provided in the accompanying images.