Table 7.

Error matrix for accuracy assessment of LULC classification based on deep learning (Rousset et al. [47]).

	a	b	c	d	e	f	g	h	i	j	k	l
Urban areas (a)	720	320	0	90	10	20	10	0	10	0	0	0
Industrial Areas (b)	30	430	0	0	0	0	0	0	0	0	0	0
Worksites and mines (c)	0	0	860	20	150	0	10	20	270	690	20	50
Road Networks (d)	50	180	10	580	70	0	0	0	0	20	0	40
Trails (e)	10	10	20	30	80	0	0	10	20	10	0	10
Forests (f)	60	30	0	60	70	770	190	20	50	10	40	30
Medium-density Vegetation (g)	90	20	30	70	250	170	690	460	270	30	10	50
Low-density vegetation (h)	40	10	30	40	160	20	80	470	90	60	0	30
Bare rocks (i)	0	0	0	10	40	0	10	10	120	0	0	10
Bare soil (j)	0	0	20	50	40	0	0	10	20	140	0	40
Water surfaces (k)	0	0	0	0	0	10	0	0	10	0	880	10
Engravements (l)	0	0	30	50	130	10	10	0	140	40	50	370
Column total
Overall accuracy	0.52
Kappa	0.48