Journal article Open Access

DeepMoon Supplemental Materials

Silburt, Ari; Ali-Dib, Mohamad; Zhu, Chenchong; Jackson, Alan; Menou, Kristen


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.1133969", 
  "language": "eng", 
  "title": "DeepMoon Supplemental Materials", 
  "issued": {
    "date-parts": [
      [
        2018, 
        1, 
        31
      ]
    ]
  }, 
  "abstract": "<p>This database contains supplemental materials to the journal article, &quot;Lunar Crater Identification via Deep Learning&quot;, which trained a&nbsp;convolutional neural network (convnet) to automate the identification of&nbsp;lunar craters.&nbsp; The database is meant to enable users&nbsp;to reproduce our work, or apply our model and data&nbsp;to new applications.&nbsp; For more information about the project&nbsp;please see the associated journal article.&nbsp; For the code, DeepMoon, and instructions on how to use the files in this database, see the GitHub link below. For a brief description of each file in this database, see the file list below.&nbsp;</p>\n\n<p>Code<br>\n--------<br>\nDeepMoon is available at https://github.com/silburt/DeepMoon</p>\n\n<p><br>\nFiles<br>\n-------</p>\n\n<p>dev_craters.hdf5 - Pandas HDFStore of crater locations and sizes for images in the validation dataset.</p>\n\n<p>dev_images.hdf5 - Input DEM images and output targets of the validation dataset.&nbsp; Also includes each image&#39;s longitude/latitude bounds, and the pixel bounds of the global DEM regions cropped to make each image.</p>\n\n<p>LunarLROLrocKaguya_118mperpix.png - LRO LOLA and Kaguya Terrain Camera DEM Merge, downsampled to 118 m/pixel and 8 bits/pixel.&nbsp; The original file can be found at: https://astrogeology.usgs.gov/search/map/Moon/LRO/LOLA/Lunar_LRO_LrocKaguya_DEMmerge_60N60S_512ppd.</p>\n\n<p>model_keras1.2.2.h5 -&nbsp;Keras model weights for the DeepMoon CNN, compatible with Keras version 1.2.2.</p>\n\n<p>model_keras2.h5 - Keras model weights for the DeepMoon CNN, compatible with Keras versions &gt;= 2.0.</p>\n\n<p>post-processed_sample_images.zip - Contains a set of sample images from the test dataset with the Moon DEM image, new identified craters, CNN target predictions, and ground-truth. The new craters from these images were used to estimate the post-processed false positive rate. See Instructions.txt in .zip file for more details.</p>\n\n<p>post-processed_test_craters.npy - numpy file containing post-processed craters&nbsp;identified by our pipeline&nbsp;on the test set. Each crater entry is&nbsp;arranged as a tuple: (longitude, latitude,&nbsp;radii), where longitude and latitude are in degrees, and radius is in kilometres.&nbsp;</p>\n\n<p>test_craters.hdf5 - Pandas HDFStore of crater locations and sizes for images in the test dataset.</p>\n\n<p>test_images.hdf5 - Input DEM images and output targets of the test dataset.&nbsp; Also includes each image&#39;s longitude/latitude bounds, and the pixel bounds of the global DEM regions cropped to make each image.</p>\n\n<p>train_craters.hdf5 - Pandas HDFStore of crater locations and sizes for images in the training dataset.</p>\n\n<p>train_images.hdf5 - Input DEM images and output targets of the training dataset.&nbsp; Also includes each image&#39;s longitude/latitude bounds, and the pixel bounds of the global DEM regions cropped to make each image.</p>\n\n<p>&nbsp;</p>", 
  "author": [
    {
      "family": "Silburt, Ari"
    }, 
    {
      "family": "Ali-Dib, Mohamad"
    }, 
    {
      "family": "Zhu, Chenchong"
    }, 
    {
      "family": "Jackson, Alan"
    }, 
    {
      "family": "Menou, Kristen"
    }
  ], 
  "type": "article-journal", 
  "id": "1133969"
}
3,475
15,772
views
downloads
All versions This version
Views 3,4753,478
Downloads 15,77215,763
Data volume 112.8 TB112.7 TB
Unique views 3,0203,023
Unique downloads 2,8112,810

Share

Cite as