Table 6.

Regression model’s performance (R², RMSE, MAE, RMSE%, MAE%) obtained from the complete dataset (2017–2018–2019) between total soluble solids and NDVI filtered (NDVI_f), canopy thickness (Thick), canopy volume (VolDem), NDVI filtered and canopy thickness (NDVI_f Thick), NDVI filtered, canopy thickness and canopy volume (NDVI_f Thick VolDem). Each cell presents 2 values, the first calculated without cross validation, and the second using fivefold cross validation. The best resulting models are bold typed.

Brix (°)	NDVI_f	Thick	VolDem	NDVI_f*Thick	NDVI_f*Thick*VolDem
Linear
R2	0.33–0.28	0.26–0.22	0.36–0.36	0.34–0.28	0.40–0.36
RMSE	1.97–2.13	2.09–2.18	1.96–2.01	1.99–2.12	1.90–2.01
MAE	1.66–1.79	1.75–1.82	1.65–1.67	1.66–1.75	1.55–1.65
RMSE%	0.09–0.09	0.09–0.1	0.09–0.08	0.09–0.09	0.08–0.09
MAE%	0.07–0.08	0.08–0.08	0.07–0.07	0.07–0.08	0.07–0.07
Trees fine
R2	0.54–0.09	0.56–0.24	0.69–0.38	0.63–0.30	0.65–0.20
RMSE	1.67–2.39	1.62–2.15	1.35–1.96	1.50–2.08	1.45–2.24
MAE	1.29–2.01	1.34–1.79	1.07–1.64	1.22–1.78	1.13–1.88
RMSE%	0.07–0.11	0.07–0.09	0.06–0.09	0.07–0.09	0.06–0.1
MAE%	0.06–0.09	0.06–0.08	0.05–0.07	0.05–0.08	0.05–0.08
RF boosted
R2	0.32–0.14	0.37–0.32	0.38–0.34	0.46–0.30	0.50–0.34
RMSE	2.01–2.31	1.93–2.03	1.92–2.03	1.79–2.08	1.72–2.04
MAE	1.54–1.93	1.47–1.71	1.44–1.72	1.42–1.73	1.35–1.71
RMSE%	0.09–0.1	0.08–0.09	0.08–0.09	0.08–0.09	0.08–0.09
MAE%	0.07–0.08	0.06–0.08	0.06–0.08	0.06–0.08	0.06–0.08
SVM fine Gaussian
R2	0.40–0.22	0.46–0.19	0.60–0.30	0.66–0.32	0.69–0.32
RMSE	1.89–2.21	1.79–2.22	1.55–2.09	1.42–2.07	1.35–2.06
MAE	1.42–1.9	1.26–1.76	1.18–1.76	0.88–1.70	0.78–1.65
RMSE%	0.08–0.1	0.08–0.1	0.07–0.09	0.06–0.09	0.06–0.09
MAE%	0.07–1.9	0.06–0.08	0.06–0.08	0.06–0.07	0.06–0.07
Gaussian exp GPR
R2	0.37–0.20	0.47–0.35	0.55–0.40	0.57–0.31	0.57–0.40
RMSE	1.95–2.24	1.78–1.99	1.63–1.93	1.59–2.07	1.59–1.94
MAE	1.58–1.86	1.51–1.69	1.36–1.61	1.32–1.71	1.33–1.66
RMSE%	0.09–0.1	0.08–0.09	0.07–0.08	0.07–0.09	0.07–0.09
MAE%	0.07–0.08	0.07–0.07	0.06–0.08	0.06–0.08	0.06–0.07