The Scientific World Journal / 2021 / Article / Tab 5 / Research Article
Improvement in the Accuracy of the Postclassification of Land Use and Land Cover Using Landsat 8 Data Based on the Majority of Segment-Based Filtering Approach Table 5 Results of the accuracy assessment for the LULC classification based on the RF classifier with the MaSegFil approach.
LULC class C_0 C_1 C_2 C_3 C_4 C_5 C_6 C_7 C_8 C_9 C_10 Total User accuracy Kappa C_0 108 0 1 0 0 1 0 0 0 0 0 110 0.982 0.000 C_1 27 268 21 0 0 8 0 0 0 0 0 324 0.827 0.000 C_2 31 9 99 0 0 2 24 17 4 0 0 186 0.532 0.000 C_3 3 0 0 4 0 0 4 0 0 0 0 11 0.364 0.000 C_4 0 0 0 0 3 0 0 0 0 0 0 3 1.000 0.000 C_5 24 17 4 0 0 39 0 0 0 0 0 84 0.464 0.000 C_6 14 0 2 1 0 0 599 9 0 0 0 625 0.958 0.000 C_7 3 0 1 0 0 0 14 374 0 4 0 396 0.944 0.000 C_8 17 0 5 0 0 0 29 7 209 0 0 267 0.783 0.000 C_9 1 0 0 0 0 0 2 2 0 65 5 75 0.867 0.000 C_10 0 0 0 0 0 0 0 0 0 1 45 46 0.978 0.000 Total 228 294 133 5 3 50 672 409 213 70 50 2127 0.000 0.000 Procedure accuracy 0.474 0.912 0.744 0.800 1.000 0.780 0.891 0.914 0.981 0.929 0.900 0.000 0.852 0.000 Kappa 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.000 0.821
C_0: primary dryland forest; C_1: secondary dryland forest; C_2: fields; C_3: open field; C_4: wetland forest; C_5: plantation; C_6: settlement; C_7: rice fields; C_8: shrubs; C_9: fishpond; C_10: water body.