Table 1 Control parameters.

From: Development of a novel modeling framework based on weighted kernel extreme learning machine and ridge regression for streamflow forecasting

Time horizon

Models

Tuning parameters

t + 3

B-WKELM-R-GBO

\(a=1.90E+03\), \(b=2.00E+02\),\(c=2.00E+03\), γ \(=1985.56\),\({P}^{*}=0.48\)

B-Ridge-GBO

\({P}_{0}=0.45\)

B-GRNN-GBO

\(spread parameter=3\)

B-ENET-GBO

\(\alpha =0.01\), \(L1\_ratio=1\)

B-LGBM-GBO

\(r=0.04\), \(ms=43.25\),\(mv=0.28\), ra \(=5.99\), \(s=7.19\),\(c=0.93\)

MVMD

\(K=5\)

t + 7

B-WKELM-R-GBO

\(a=1.64E+03\), \(b=1.76E+03\),\(c=1.25E+03\), γ \(=200.99\),\({P}^{*}=6.99E-05\)

B-Ridge-GBO

\({P}_{0}=7.05E-5\)

B-GRNN-GBO

\(spread parameter=5\)

B-ENET-GBO

\(\alpha =0.01\), \(L1\_ratio=1\)

B-LGBM-GBO

\(r=0.15\), \(ms=66.30\),\(mv=0.57\), ra \(=3.06\), \(s=7.88\),\(c=0.01\)

MVMD

\(K=10\)

t + 14

B-WKELM-R-GBO

\(a=1.70E+03\), \(b=1.89E+03\),\(c=2.09E+02\), γ \(=33.67\),\({P}^{*}=4.13E-05\)

B-Ridge-GBO

\({P}_{0}=2.41E-05\)

B-GRNN-GBO

\(spread parameter=2.5\)

B-ENET-GBO

\(\alpha =0.0001\), \(L1\_ratio=1\)

B-LGBM-GBO

\(r=0.39\), \(ms=66.78\),\(mv=0.25\), ra \(=1.02\), \(s=3.44\),\(c=1E-3\)

MVMD

\(K=12\)