Land Cover Mapping Based on Multisource Spatial Data Mining Approach for Climate Simulation: A Case Study in the Farming-Pastoral Ecotone of North China

Table 5

The confusion matrix for the vegetation classification from land use type to land covers scheme.

Class	EN	DN	DB	MF	CS	OS	Classified total	Number correct	Accuracy
									Producer’s	User’s
EN	87920	452	121	389			9754	8792	90.14	90.86
DN	990	5346	327	213			5985	5346	89.32	84.62
DB	720	72	4783	412			5339	4783	89.59	87.70
MF	7130	448	223	4956			6340	4956	78.17	83.02
CS					3268	123	3391	3268	96.37	89.95
OS					365	4222	4587	4222	92.04	97.17
Ref. total	96760	6318	5454	5970	3633	4345	35396	31367
Overall classification accuracy = 88.62%								Overall Kappa statistics = 0.86

EN: evergreen needle leaved forest; DN: deciduous needle leaved forest; DB: deciduous broad leaved forest; MF: mixed forests; CS: closed shrublands; OS: open shrublands).