Effects of RapidEye imagery’s red-edge band and vegetation indices on land cover classification in an arid region

Abstract

Land cover classification (LCC) in arid regions is of great significance to the assessment, prediction, and management of land desertification. Some studies have shown that the red-edge band of RapidEye images was effective for vegetation identification and could improve LCC accuracy. However, there has been no investigation of the effects of RapidEye images' red-edge band and vegetation indices on LCC in arid regions where there are spectrally similar land covers mixed with very high or low vegetation coverage information and bare land. This study focused on a typical inland arid desert region located in Dunhuang Basin of northwestern China. First, five feature sets including or excluding the red-edge band and vegetation indices were constructed. Then, a land cover classification system involving plant communities was developed. Finally, random forest algorithm-based models with different feature sets were utilized for LCC. The conclusions drawn were as follows: 1) the red-edge band showed slight contribution to LCC accuracy; 2) vegetation indices had a significant positive effect on LCC; 3) simultaneous addition of the red-edge band and vegetation indices achieved a significant overall accuracy improvement (3.46% from 86.67%). In general, vegetation indices had larger effect than the red-edge band, and simultaneous addition of them significantly increased the accuracy of LCC in arid regions.

Assessing Different Feature Sets’ Effects on Land Cover Classification in Complex Surface-Mined Landscapes by ZiYuan-3 Satellite Imagery

“…Because VI and PCs were linearly computed from spectral bands, their addition imported relevant, even redundant information, which might have led to accuracy losses. Although many studies indicated that the addition of VI contributed to the classification [19,41], some others also supported the conclusion in this study. For example, Adelabu et al [22] reported that, when using all the bands of RapidEye imagery, adding NDVI decreased the classification accuracy.…”

Crop Classification Based on Red Edge Features Analysis of GF-6 WFV Data

“…The test was based on the error matrix of two classifications and the chi-squared statistic value (χ 2 ) with one degree of freedom was calculated as follows: where f ij is the number of samples that are correctly classified by classification scheme i and incorrectly classified by classification scheme j (i = 1, 2; j = 1, 2). The difference between two classification schemes is statistically significant at the 95% confidence level ( p = 0.05) when the χ 2 value is greater than or equal to 3.84 [ 65 , 66 ]. In this study, McNemar’s test was used to evaluate whether there were significant differences in the classification accuracy between two classification schemes by RF classifier with different red edge features.…”

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

“…Chen et al [47] performed a paired t-test [88]. McNemar tests were used in some other studies, such as those described in Duro et al [89], Li et al [12], Li et al [90,91], and Maxwell et al [31]. In addition, a Mann-Whitney U-test [92] was used by Fassnacht et al [93].…”

“…It is worth noting that the McNemar test [87] is designed for two-class classification, while the other two tests are intended for multi-class classification. Because the McNemar test [87] is easy to implement compared to the t-and U-tests [88,92], it is also widely used for multi-class classification with relative reasonable results, such as in the above-mentioned studies [12,31,57,84,[89][90][91]. However, when the test set is large, this method is not applicable.…”