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 11 Creating and comparing 14 models using tenfold cross-validation and hyperparameter tuning with Hyperopt optimization for Dataset 2 (best results are bolded)

Weather station	Model	10-fold cross-validation			Hyperparameter tuning with Hyperopt
Weather station	Model	MSE	MAE	R²	MSE	MAE	R²
Kutubdia	MLR	0.4976	0.5310	0.7868	0.4976	0.5310	0.7868
	Lasso	1.9781	1.0706	0.1533	0.5115	0.5361	0.7809
	Ridge	0.4976	0.5310	0.7868	0.4976	0.5310	0.7868
	Elastic Net	1.3426	0.8776	0.4252	0.5103	0.5373	0.7814
	KNN	0.4106	0.4725	0.8240	0.3913	0.4607	0.8324
	DT	0.6882	0.6104	0.7049	0.4571	0.4973	0.8041
	RF	0.3473	0.4286	0.8512	0.4057	0.4705	0.8261
	GBR	0.3861	0.4607	0.8345	0.3351	0.4200	0.8564
	AdaBoost	0.6405	0.6127	0.7255	0.5284	0.5457	0.7736
	XGBoost	0.3413	0.4234	0.8538	0.3339	0.4192	0.8569
	LightGBM	0.3348	0.4215	0.8565	0.3332	0.4200	0.8572
	CatBoost	0.3224	0.4117	0.8618	0.3218	0.4117	0.8621
	LSTM	0.4171	0.4825	0.8215	0.4107	0.4793	0.8241
	GRU	0.4237	0.4874	0.8187	0.4223	0.4869	0.8191
Cox's Bazar	MLR	0.5343	0.5504	0.8121	0.5343	0.5504	0.8121
	Lasso	2.1950	1.1540	0.2288	0.5524	0.5602	0.8057
	Ridge	0.5343	0.5504	0.8121	0.5343	0.5505	0.8121
	Elastic Net	1.5971	0.9822	0.4388	0.5513	0.5618	0.8062
	KNN	0.4495	0.4964	0.8419	0.4275	0.4844	0.8497
	DT	0.7535	0.6428	0.7351	0.4889	0.5205	0.8280
	RF	0.3810	0.4521	0.8660	0.4311	0.4887	0.8484
	GBR	0.4111	0.4763	0.8554	0.3692	0.4455	0.8702
	AdaBoost	0.7095	0.6509	0.7505	0.5635	0.5664	0.8019
	XGBoost	0.3801	0.4484	0.8663	0.3688	0.4445	0.8703
	LightGBM	0.3637	0.4420	0.8721	0.3642	0.4419	0.8720
	CatBoost	0.3541	0.4347	0.8755	0.3533	0.4342	0.8758
	LSTM	0.4498	0.5031	0.8420	0.4543	0.5061	0.8403
	GRU	0.4648	0.5124	0.8367	0.4727	0.5183	0.8340