Object-based spectral-phenological features for mapping invasive Spartina alterniflora

Spartina alterniflora (S. alterniflora), a prevailing invasive species in the coastal zones, has resulted in significant ecosystem degradation and economic losses since its introduction to China in 1979. Among the existing studies that incorporate remote sensing to map S. alterniflora, the pixel-based phenological feature composite method (Ppf-CM) has proved to be successful due to its merits to overcome cloud contamination while exaggerating the spectral separability between S. alterniflora and its co-dominant native species. However, one major limitation of the Ppf-CM method is that it extracts phenological features from a single-pixel without accounting for its surrounding geospatial information that proved essential for more accurate mapping. In this study, we aim to ameliorate this problem by incorporating geometric, texture, and contextual information. To this end, we developed a new object-based phenological feature composite method (OPpf-CM). Specifically, we first generated a composite image by stacking two images that were respectively acquired during the distinctive phenological periods of S. alterniflora. Then we derived spectrally homogenous objects on the composite image through an unsupervised multiscale segmentation method. Various features derived from objects served as the input of support vector machine (SVM) classifier to produce a S. alterniflora map. To evaluate the performance of OPpfCM, we carried out a comparison of classification performance between our developed OPpf-CM method and the previously developed Ppf-CM one (Tian et al., 2020) with the aid of visual interpretation and accuracy statistics (i.e. confusion matrix). The results showed that OPpf-CM achieved a higher overall accuracy (98%) than Ppf-CM (96.67%) when validated with the ground reference data that was visually interpreted by the high spatial resolution imagery and field survey. Meanwhile, the identification of fragmented S. alterniflora patches along with mixed-cover areas can be significantly improved with the OPpf-CM method. We envision that the developed object-based spectral-phenological feature has the potential to be applied to mapping a wide spectrum of coastal vegetations.

Automated summary

This study aimed to improve upon the limitations of the Ppf-CM method by incorporating geometric, texture, and contextual information. A new object-based phenological feature composite method (OPpf-CM) was developed, which involved stacking two images acquired during distinctive phenological periods of Spartina alterniflora, deriving spectrally homogeneous objects, and using various features from these objects as input for a support vector machine classifier to generate a map of S. alterniflora with higher accuracy than the pixel-based method.