Dataset Open Access

Active Learning with RESSPECT: Data Set

da Silva de Souza, Rafael; Kennamer, Noble; de Oliveira Ishida, Emille Eugenia

This folder contains pre-processed simulated data first made available by Rick Kessler for the 
Supernova Photometric Classification Challenge (SNPCC).

All data were feature extracted using the Bazin parametric function.

This version of the data set was used to obtain the results reported in Kennamer et al., 2020 - Active learning with RESSPECT: resource allocation for extragalactic astronomical transients. Published during the 2020 IEEE Symposium Series on Computational Intelligence. The code used to obtain the results shown in the paper is available in the COINtoolbox (github). 

This work was developed under the RESSPECT project, an inter-collaboration agreement established between the LSST Dark Energy Science Collaboration (LSST-DESC) and the Cosmostatistics Initiative (COIN) in order to develop an active learning pipeline to advise the allocation of telescope resources.

The Cosmostatistics Initiative was supported by the French government via a CNRS-MOMENTUM grant from 2018-2020 under the project: Active Learning for Large Scale Sky Surveys.
Files (415.7 MB)
Name Size
IEEE2020.tar.gz
md5:19f408e6da71dce5c05aa5546c99d25e
415.7 MB Download
README
md5:f4e87bde151cd7d1678a1527572eac78
1.3 kB Download
34
15
views
downloads
All versions This version
Views 3434
Downloads 1515
Data volume 2.9 GB2.9 GB
Unique views 2929
Unique downloads 1212

Share

Cite as