Investigating and comparing the IRIS spectral lines Mg II, Si IV, and C II for flare precursor diagnostics

Open Access

Table 3.

Metrics to estimate the model performance.

Name	Metric
Accuracy	$Acc = \frac{TP + TN}{P + N}$ $\mathrm{Acc} = \frac{\mathrm{TP}+\mathrm{TN}}{\mathrm{P}+\mathrm{N}}$
Cohen’s Kappa	$κ = \frac{2 \times (TP \times TN - FN \times FP)}{(TP + FP) \times (FP + TN) + (TP + FN) \times (FN + TN)}$ $\kappa = \frac{2 \times(\mathrm{TP} \times \mathrm{TN}-\mathrm{FN} \times \mathrm{FP})}{(\mathrm{TP}+\mathrm{FP}) \times(\mathrm{FP}+\mathrm{TN})+(\mathrm{TP}+\mathrm{FN}) \times(\mathrm{FN} + \mathrm{TN})}$
True skill statistics	$TSS = \frac{TP}{P} - \frac{FP}{N}$ $\mathrm{TSS} = \frac{\mathrm{TP}}{\mathrm{P}} - \frac{\mathrm{FP}}{\mathrm{N}}$
True positive rate	$TPR (δ) = \int_{δ}^{\infty} f_{1} (y) d y$ $\mathrm{TPR}(\delta) = \int_{\delta}^{\infty} f_{1}(y) \mathrm{d}y$
False positive rate	$FPR (δ) = \int_{δ}^{\infty} f_{0} (y) d y$ $\mathrm{FPR}(\delta) = \int_{\delta}^{\infty} f_{0}(y) \mathrm{d}y$
Area under the curve	$AUC = \int_{δ = 0}^{1} TPR ({FPR}^{- 1} (δ)) d δ$ $\mathrm{AUC} = \int_{\delta=0}^{1} \mathrm{TPR}\left(\mathrm{FPR}^{-1}(\delta)\right) \mathrm{d}\delta$
ROC skill score	ROCSS = 2 ⋅ AUC − 1

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.