| Summary: | The propagation of the invasive <italic>Spartina alterniflora</italic> (<italic>S. alterniflora</italic>) has seriously affected the health of coastal wetland ecosystems in China and thus requires an urgent response. In this article, we construct a feature vector set containing phenological and other time-series features based on the google earth engine platform by combining dense time-series images from the sentinel-1 and sentinel-2 satellites. We obtained the dataset of the annual distribution of <italic>S. alterniflora</italic> in the Yellow river delta from 2016 to 2021 by developing an object-oriented random forest classification model. The results show that <italic>S. alterniflora</italic> has different phenological features from other wetland plants that played an important role in its classification based on the images. A combination of multiple phenological and temporal features improved the classification accuracy of <italic>S. alterniflora</italic> (multi-year average overall accuracy: 95.38%; user accuracy: 95.01%; producer accuracy: and 95.17%). Our results suggest that from 2016 to 2021, the growth rate of the area occupied by <italic>S. alterniflora</italic> was 2.17 km<sup>2</sup> per year, and a new patch of the <italic>S. alterniflora</italic> appeared in the south of the study area in 2018. The article here provides scientific data to support the monitoring and control of the invasive <italic>S. alterniflora</italic> at a large scale.
|
|---|