Table 5 Comparative evaluation of machine learning model Performance.

Season	Model	Train_R²	Train_RMSE	Train_MAE	Test_R²	Test_RMSE	Test_MAE
Annual	Random Forest	0.9459	0.0463	0.0325	0.9031	0.0627	0.0438
Annual	Gradient Boosting	0.9263	0.0541	0.0389	0.8998	0.0637	0.0449
Annual	CatBoost	0.9127	0.0589	0.0421	0.8985	0.0641	0.0455
Spring	Random Forest	0.9424	0.0501	0.0355	0.9024	0.0659	0.0464
Spring	Gradient Boosting	0.9188	0.0594	0.0431	0.8981	0.0673	0.0482
Spring	CatBoost	0.9062	0.0639	0.0463	0.8966	0.0678	0.0488
Summer	Random Forest	0.9436	0.0483	0.0341	0.9008	0.0653	0.0451
Summer	Gradient Boosting	0.9234	0.0563	0.0406	0.8988	0.0661	0.0458
Summer	CatBoost	0.9139	0.0596	0.0431	0.8962	0.0669	0.0462
Autumn	Random Forest	0.9401	0.0515	0.0367	0.9018	0.0701	0.0498
Autumn	CatBoost	0.9018	0.0659	0.0484	0.8861	0.0718	0.0518
Autumn	Gradient Boosting	0.9118	0.0624	0.0461	0.8831	0.0727	0.0523
Winter	Random Forest	0.9352	0.0614	0.0402	0.8974	0.0811	0.0529
Winter	Gradient Boosting	0.9058	0.0741	0.0495	0.8788	0.0841	0.0552
Winter	CatBoost	0.8904	0.0799	0.0536	0.8779	0.0845	0.0561

Quick links

Search