Table 10 Training and test statistics of the models for EPAN prediction—Station 2 (Model 3) LSTM-HHO.

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

Tmin, Tmax

0.8083

0.6173

0.8993

0.8934

0.8453

0.6382

0.8752

0.8613

Tmin, Ra

0.8536

0.6608

0.8496

0.8482

0.9358

0.6658

0.8473

0.8428

Tmax, Ra

0.8364

0.7056

0.8604

0.8568

0.8867

0.7303

0.8542

0.8512

Tmin, Tmax, Ra

0.7608

0.5804

0.8712

0.8695

0.8326*

0.5956

0.8979

0.8936

Tmin, Tmax, Ra, α

0.8202

0.6852

0.8255

0.8234

0.8543

0.6957

0.8204

0.8173

M2

Tmin, Tmax

0.6716

0.5203

0.9028

0.9006

0.7304

0.5564

0.8834

0.8816

Tmin, Ra

0.8572

0.6704

0.8526

0.8492

0.7356

0.5856

0.8806

0.8793

Tmax, Ra

0.6906

0.5407

0.9021

0.8993

0.8208

0.6452

0.8542

0.8508

Tmin, Tmax, Ra

0.7864

0.6106

0.8968

0.8928

0.8473

0.6737

0.8753

0.8713

Tmin, Tmax, Ra, α

0.6528

0.4938

0.9138

0.9124

0.6824

0.5382

0.9045

0.8998

M3

Tmin, Tmax

0.6843

0.4929

0.8983

0.8972

0.7808

0.6226

0.8893

0.8852

Tmin, Ra

0.7608

0.6013

0.8758

0.8718

0.8679

0.6468

0.8404

0.8378

Tmax, Ra

0.7293

0.5658

0.8862

0.8834

0.8004

0.6193

0.8781

0.8726

Tmin, Tmax, Ra

0.7116

0.5336

0.8954

0.8893

0.9193

0.7247

0.8596

0.8558

Tmin, Tmax, Ra, α

0.7858

0.6057

0.8667

0.8639

0.8186

0.6652

0.8515

0.8502

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