Scientific Reports

Table 12 Training and test statistics of the models for EPAN prediction – Station 2 (Model 5) LSTM-APO.

From: Metaheuristic-enhanced deep learning for monthly pan evaporation prediction under limited climatic data

Model inputs	Training period				Test period
	RMSE	MAE	R²	NSE	RMSE		MAE	R²	NSE
M1 (70%−30%)
Tmin, Tmax	0.6034	0.4703	0.9263	0.9252	0.7772		0.6082	0.9391	0.9356
Tmin, Ra	0.6886	0.5368	0.9052	0.9038	0.7578		0.5774	0.9028	0.8996
Tmax, Ra	0.6395	0.4857	0.9168	0.9152	0.7476		0.5653	0.9093	0.9054
Tmin, Tmax, Ra	0.5682	0.4354	0.9346	0.9334	0.7269^*		0.5591	0.9276	0.9244
Tmin, Tmax, Ra, α	0.7629	0.6309	0.8474	0.8452	0.8358		0.5858	0.8392	0.8358
M2 (75%−25%)
Tmin, Tmax	0.4059	0.3154	0.9738	0.9706	0.4338		0.3454	0.9606	0.9614
Tmin, Ra	0.6868	0.5267	0.8976	0.8961	0.7036		0.5506	0.8908	0.8893
Tmax, Ra	0.5727	0.4368	0.9319	0.9293	0.5894		0.4608	0.9284	0.9256
Tmin, Tmax, Ra	0.4804	0.3757	0.9514	0.9502	0.5299		0.4219	0.9439	0.9405
Tmin, Tmax, Ra, α	0.6583	0.5129	0.9073	0.9056	0.7336		0.5637	0.8827	0.8796
M3 (80%−20%)
Tmin, Tmax	0.5258	0.4046	0.9438	0.9426	0.7108		0.5807	0.9124	0.9096
Tmin, Ra	0.6479	0.5108	0.9136	0.9124	0.7654		0.5928	0.8774	0.8743
Tmax, Ra	0.5726	0.4429	0.9325	0.9313	0.7306		0.5636	0.9182	0.9145
Tmin, Tmax, Ra	0.5052	0.3951	0.9489	0.9475	0.6819		0.5654	0.9246	0.9208
Tmin, Tmax, Ra, α	0.4708	0.3664	0.9554	0.9541	0.6725		0.5538	0.9328	0.9282

^*Bold numbers indicates the best value (minimum RMSE or MAE and maximum R² or NSE).

Back to article page

Search

Advanced search

Quick links