Table 7.
Performance measures (F1 scores) of the best ensemble model (LeNet2, LeNet3, and MiniVGGNet4) by the averaging method and individual CNN models (LeNet3 and MiniVGGNet3).

Class name	LeNet3	MiniVGGNet3	LeNet2 + LeNet3 + MiniVGGNet4
Cedar-C	0.99	0.98	1.00
Cedar-L	0.98	0.94	0.99
Cypress-C	0.99	0.97	1.00
Cypress-L	0.94	0.98	0.98
KoreanPine-C	0.99	0.97	1.00
KoreanPine-L	0.92	0.84	0.96
KoreanRedPine-C	0.99	1.00	1.00
KoreanRedPine-L	0.90	0.85	0.96
Larch-C	1.00	1.00	1.00
Larch-L	0.99	0.97	1.00