Wind speed prediction for site selection and reliable operation of wind power plants in coastal regions using machine learning algorithm variants

Sustainable Energy Research

Table 10 The evaluation metrics for 14 models on both validation and test segment for Dataset 1 (best results are bolded)

Weather station	Model	Validation dataset			Test dataset
Weather station	Model	MSE	MAE	R²	MSE	MAE	R²
Kutubdia	MLR	0.3955	0.4272	0.5808	0.4467	0.4371	0.5741
	Lasso	0.3955	0.4272	0.5808	0.4467	0.4371	0.5741
	Ridge	0.4052	0.4424	0.5705	0.4618	0.4526	0.5597
	Elastic Net	0.3989	0.4342	0.5771	0.4551	0.4445	0.5661
	KNN	0.3862	0.4122	0.5906	0.4472	0.4265	0.5737
	DT	0.3892	0.4171	0.5874	0.4448	0.4290	0.5760
	RF	0.3638	0.4022	0.6143	0.4155	0.4127	0.6038
	GBR	0.3477	0.3960	0.6314	0.4073	0.4085	0.6117
	AdaBoost	0.4331	0.4523	0.5409	0.4871	0.4646	0.5357
	XGBoost	0.3485	0.3969	0.6306	0.4031	0.4085	0.6157
	LightGBM	0.3437	0.3953	0.6357	0.4072	0.4079	0.6118
	CatBoost	0.3388	0.3912	0.6409	0.3942	0.4042	0.6242
	LSTM	0.3642	0.4143	0.6139	0.4206	0.4254	0.5990
	GRU	0.3685	0.4136	0.6094	0.4257	0.4242	0.5941
Cox's Bazar	MLR	1.1406	0.7451	0.4121	1.1681	0.7559	0.4097
	Lasso	1.1642	0.7510	0.3999	1.1843	0.7599	0.4015
	Ridge	1.1406	0.7451	0.4121	1.1681	0.7559	0.4097
	Elastic Net	1.1553	0.7476	0.4045	1.1788	0.7571	0.4042
	KNN	1.0651	0.6512	0.4510	1.1283	0.6711	0.4297
	DT	1.0297	0.6496	0.4693	1.1088	0.6716	0.4396
	RF	0.9655	0.6268	0.5023	1.0180	0.6464	0.4854
	GBR	0.9496	0.6249	0.5105	1.0024	0.6444	0.4933
	AdaBoost	0.9684	0.7280	0.4421	0.9536	0.7272	0.4501
	XGBoost	0.9416	0.6195	0.5147	1.0003	0.6416	0.4945
	LightGBM	0.9395	0.6183	0.5158	0.9944	0.6380	0.4974
	CatBoost	0.9328	0.6157	0.5192	0.9906	0.6363	0.4994
	LSTM	0.9895	0.6514	0.4900	1.0166	0.6645	0.4862
	GRU	1.0065	0.6482	0.4812	1.0431	0.6626	0.4728