Table 5 ESM individual model performance. ESM: Ensemble model, TSS: True Skill Statistics, ROC: Reciever Operating Characteristics, KAPPA: Cohen’s Kappa, ANN: Artificial Neural Networks, CTA: Classification Tree Analysis, FDA: Flexible Discriminant Analysis, GAM: Generalized Additive Model, GBM: Generalised Boosting Models, GLM: Generalised Linear Models, MARS: Multivariate Adaptive Regression Splines, SRE: Surface Range Envelope, RF: Breiman’s Random Forest for classification and regression.

Eval. metric	Models	Testing data	Cutoff	Sensitivity	Specificity
Eval. metric	Models	ESM with selected environmental layers	ESM with selected environmental layers	ESM with selected environmental layers	ESM with selected environmental layers
TSS	GAM	0.883	0.166	97.917	90.361
	RF	0.882	0.212	95.833	92.369
	GLM	0.887	0.247	97.917	90.763
	GBM	0.886	0.177	95.833	92.771
	CTA	0.799	0.461	87.5	92.369
	ANN	0.814	0.204	95.833	85.542
	SRE	0.384	0.495	39.583	98.795
	FDA	0.881	0.159	93.75	94.378
	MARS	0.911	0.186	97.917	93.173
ROC	GAM	0.975	0.164	97.917	90.361
	RF	0.977	0.219	95.833	92.771
	GLM	0.975	0.244	97.917	90.763
	GBM	0.972	0.177	95.833	92.771
	CTA	0.884	0.464	87.5	92.369
	ANN	0.932	0.241	95.833	85.944
	SRE	0.692	0.5	39.583	98.795
	FDA	0.975	0.148	100	88.755
	MARS	0.973	0.184	97.917	93.173
KAPPA	GAM	0.794	0.644	91.667	94.378
	RF	0.834	0.462	83.333	97.992
	GLM	0.761	0.65	89.583	93.574
	GBM	0.804	0.574	85.417	96.386
	CTA	0.72	0.461	87.5	92.369
	ANN	0.633	0.204	95.833	85.542
	SRE	0.491	0.495	39.583	98.795
	FDA	0.834	0.202	91.667	95.984
	MARS	0.803	0.186	97.917	93.173

Quick links

Search