I tiakina i:
Ngā taipitopito rārangi puna kōrero
Kaituhi matua: Makinen, T. Lucas
Hōputu: Recurso digital
Reo:Ingarihi
I whakaputaina: Zenodo 2020
Ngā marau:
Urunga tuihono:https://doi.org/10.5281/zenodo.4133772
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Rārangi ihirangi:
  • <p>Sample data for training and testing the deep21 deep learning model for 21cm cosmology. The object of the experiment is to separate radio cosmological signal from foreground contaminants, with a Principal Component Analysis (PCA) preprocessing step. Data were originally generated in .fits file format via <a href="http://intensitymapping.physics.ox.ac.uk/CRIME.html">CRIME Simulation Package</a> (see <a href="https://arxiv.org/abs/1405.1751">Alonso et al. 2014</a> for details).</p> <p>Included are binary numpy (.npy) files for 5 full-sky simluations of the cosmological signal, observed signal, and reference PCA-subtracted maps. Loading files with Numpy will yield arrays of shape (<span class="math-tex">\(N_{\rm voxels}, N_x, N_y, N_\nu\)</span>) = (950, 64, 64, 64), with 192 voxels per simulation.</p> <p>Designed for use with the <a href="https://colab.research.google.com/drive/1wQnmelM33Qjq-nHeVD9JkTHXER1PAJM0?hl=en#scrollTo=rUk2wvTTulLY">browser-based deep21 tutorial</a> on Google Colab (fuller explanation of experiment also available). Full-scale processing scripts are available on the <a href="https://github.com/tlmakinen/deep21">deep21 GitHub repository</a>.</p> <p> </p>