Enter GRB Measurements

Measurement Key Machine-z Feature Classifier Feature Value
BAT T90 [sec] T90 Yes No
BAT Fluence (15-150 keV) [10^-7 erg/cm^2] Fluence Yes No
BAT 1-sec Peak Photon Flux (15-150 keV) [ph/cm^2/sec] 1sPeakPhotonFlux Yes No
CPL=1, PL=0 C_PL Yes Yes
XRT Early Flux (0.3-10 keV) [10^-11 erg/cm^2/s] XRTEarlyFlux Yes Yes
XRT Spectral Index (Gamma) XRTSpectralIndex Yes Yes
XRT Column Density (NH) [10^21 cm^-2] NH No Yes
V Mag=1 Limit=0 VMagLimit Yes Yes
B Mag=1 Limit=0 BMagLimit No Yes
UVW1 Mag=1 Limit=0 UVW1MagLimit Yes No
UVM2 Mag=1 Limit=0 UVM2MagLimit Yes No
UVW2 Mag=1 Limit=0 UVW2MagLimit Yes Yes
White Mag=1 Limit=0 WhiteMagLimit Yes Yes

Historical High-z GRBs. Click a GRB to load features and calculate machine-z and the high-z classification.

GRB 080913 GRB 090423 GRB 151112A GRB 151027B

Please note machine-z and high-z classification may take few minutes to calculate.

High-z Classifier Performance

Plot Loading... Please wait...

The receiver operating characteristic (ROC) curve for the high-z classifier using the best 8 features.

Plot Loading... Please wait...

Performance curves for high-z classifier. The top panel (a) compares the fraction of bursts recommended for follow up and the fraction requested from the classifier. The middle panel (b) shows the purity of the burst sample selected for follow-up (the fraction of bursts that were followed up that are actually at high redshift). The bottom panel (c) shows the efficiently of the classifier (the fraction of all high-redshift bursts that were followed up).

Machine-z Performance

Plot Loading... Please wait...

Comparison of corrected machine-z predictions with true redshift. The correlation coefficient between the two quantities is 0.57.

Plot Loading... Please wait...

Distribution of relative differences between machine-z predictions and true redshifts.

Please see the following publication for more details on machine-z and the high-z classifier.

Machine-z: Rapid Machine Learned Redshift Indicator for Swift Gamma-ray Bursts

Go to