Monitoring Invasion Process of Spartina alterniflora by Seasonal Sentinel-2 Imagery and an Object-Based Random Forest Classification

Abstract

In the late 1990s, the exotic plant Spartina alterniflora (S. alterniflora), was introduced to the Zhangjiang Estuary of China for tidal zone reclamation and protection. However, it invaded rapidly and has caused serious ecological problems. Accurate information on the seasonal invasion of S. alterniflora is vital to understand invasion pattern and mechanism, especially at a high temporal resolution. This study aimed to explore the S. alterniflora invasion process at a seasonal scale from 2016 to 2018. However, due to the uncertainties caused by periodic inundation of local tides, accurately monitoring the spatial extent of S. alterniflora is challenging. Thus, to achieve the goal and address the challenge, we firstly built a high-quality seasonal Sentinel-2 image collection by developing a new submerged S. alterniflora index (SAI) to reduce the errors caused by high tide fluctuations. Then, an object-based random forest (RF) classification method was applied to the image collection. Finally, seasonal extents of S. alterniflora were captured. Results showed that (1) the red edge bands (bands 5, 6, and 7) of Sentinel-2 imagery played critical roles in delineating submerged S. alterniflora; (2) during March 2016 to November 2018, the extent of S. alterniflora increased from 151.7 to 270.3 ha, with an annual invasion rate of 39.5 ha; (3) S. alterniflora invaded with a rate of 31.5 ha/season during growing season and 12.1 ha/season during dormant season. To our knowledge, this is the first study monitoring S. alterniflora invasion process at a seasonal scale during continuous years, discovering that S. alterniflora also expands during dormant seasons. This discovery is of great significance for understanding the invasion pattern and mechanism of S. alterniflora and will facilitate coastal biodiversity conservation efforts.

A Simple Phenology-Based Vegetation Index for Mapping Invasive Spartina Alterniflora Using Google Earth Engine

“…9(b)]. Note that our observed invasion in Zhangjiang Estuary approximately commensurate with the detection conducted by Tian et al [33], who measured that the invasive area was 270.3 ha by the November 23rd of 2018.…”

“…Our study area is located in the southeastern coastal regions of mainland China. It includes Beibu Gulf in Guangxi Province [25], [33].…”

“…Reference data were randomly sampled as evenly as possible throughout the research sites covering S. alterniflora, Mangrove forests, and other land cover types (hereafter named "Others"), including water and mudflat (see Fig.S1-S6 in Supplementary Materials). With the assistance of the field survey reported in existing literature [33], [36], the land cover type of each point was allocated by visual interpretation of very high-resolution (VHR) image with spatial resolution less than 10 m [21]. Specifically, the visual interpretation was conducted by three experienced remote sensing experts, who have visited different coastal wetlands in China and have comprehensive understanding of the phenological characteristics of S. alterniflora and Mangrove trees.…”

“…Generally, ML classification methods require large numbers of features, such as spectral features, texture features, geometric features, etc. For example, Tian et al [33] detected submerged S. alterniflora in Zhangjiang Estuary, China using RF method based on a total of 35 spectral, geometry and texture features from Sentinel-2 imagery; the resultant mapping accuracy was over 90%. Tian et al [25] utilized Stacked Auto Encoder to detect S. alterniflora based on 12 spectral features composited by imageries at different seasons, and reported 96.22% overall accuracy; the study also reported that the classification accuracy dropped to 83.3% when only summer pixels were used.…”

Mapping the Essential Urban Land Use in Changchun by Applying Random Forest and Multi-Source Geospatial Data

“…In other words, the prediction accuracy of the unselected sample set is used to verify the performance of the model [62]. The higher the value, the more reliable the model [63,64]. In this study, scikit-learn was used to determine the optimal parameters according to the OOB_SCORE value calculated by the parameter cycle.…”