Landsat Observations of Two Decades of Wetland Changes in the Estuary of Poyang Lake during 2000–2019

The stability of wetlands is threatened by the combined effects of global climate change and human activity. In particular, the vegetation cover status of lake wetlands has changed. Here, the change in vegetation cover at the estuary of Poyang Lake was monitored, and its influencing factors are studied to elucidate the dynamic change characteristics of vegetation at the inlet of this lake. Flood and water level changes are two of the main factors affecting the evolution of wetland vegetation at the estuary of Poyang Lake. Therefore, Landsat data from 2000 to 2019 were used to study the spatial and temporal variation in the Normalized Difference Vegetation Index (NDVI) in the vegetation cover area. Theil–Sen Median trend analysis and Mann–Kendall tests were used to study the long-term trend characteristics of NDVI. The response between NDVI and the explanatory variables at the estuary of Poyang Lake was quantified using regression tree analysis to study the regional climate, water level, and flood inundation duration. Results showed the following: (1) Vegetation in a large area of the study area improved significantly from 2000 to 2010 and only slightly from 2010 to 2019, and few areas with slight degradation of vegetation were found. In most of these areas, the vegetation from 2000 to 2010 exhibited a gradual change, from nothing to something, which started around 2004; (2) The main variable that separated the NDVI values was the mean water level in October. When the mean October water level was greater than 14.467 m, the study area was still flooded in October. Thus, the regional value of BestNDVI was approximately 0.3, indicating poor vegetation growth. When the mean water level in October was less than 14.467 m, the elevation of the study area was higher than the water level value, and after the water receded in October, the wetland vegetation exhibited autumn growth in that year. Thus, the vegetation in the study area grew more abundantly. These results could help manage and protect the degraded wetland ecology.

Experimental Tree Mortality Does Not Induce Marsh Transgression in a Chesapeake Bay Low-Lying Coastal Forest

Transgression into adjacent uplands is an important global response of coastal wetlands to accelerated rates of sea level rise. “Ghost forests” mark a signature characteristic of marsh transgression on the landscape, as changes in tidal inundation and salinity cause bordering upland tree mortality, increase light availability, and the emergence of tidal marsh species due to reduced competition. To investigate these mechanisms of the marsh migration process, we conducted a field experiment to simulate a natural disturbance event (e.g., storm-induced flooding) by inducing the death of established trees (coastal loblolly pine, Pinus taeda) at the marsh-upland forest ecotone. After this simulated disturbance in 2014, we monitored changes in vegetation along an elevation gradient in control and treatment areas to determine if disturbance can lead to an ecosystem shift from forested upland to wetland vegetation. Light availability initially increased in the disturbed area, leading to an increase in biodiversity of vegetation with early successional grass and shrub species. However, over the course of this 5-year experiment, there was no increase in inundation in the disturbed areas relative to the control and pine trees recolonized becoming the dominant plant cover in the disturbed study areas. Thus, in the 5 years since the disturbance, there has been no overall shift in species composition toward more hydrophytic vegetation that would be indicative of marsh transgression with the removal of trees. These findings suggest that disturbance is necessary but not sufficient alone for transgression to occur. Unless hydrological characteristics suppress tree re-growth within a period of several years following disturbance, the regenerating trees will shade and outcompete any migrating wetland vegetation species. Our results suggest that complex interactions between disturbance, biotic resistance, and slope help determine the potential for marsh transgression.

Object-Based Wetland Vegetation Classification Using Multi-Feature Selection of Unoccupied Aerial Vehicle RGB Imagery

Wetland vegetation is an important component of wetland ecosystems and plays a crucial role in the ecological functions of wetland environments. Accurate distribution mapping and dynamic change monitoring of vegetation are essential for wetland conservation and restoration. The development of unoccupied aerial vehicles (UAVs) provides an efficient and economic platform for wetland vegetation classification. In this study, we evaluated the feasibility of RGB imagery obtained from the DJI Mavic Pro for wetland vegetation classification at the species level, with a specific application to Honghu, which is listed as a wetland of international importance. A total of ten object-based image analysis (OBIA) scenarios were designed to assess the contribution of five machine learning algorithms to the classification accuracy, including Bayes, K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), and random forest (RF), multi-feature combinations and feature selection implemented by the recursive feature elimination algorithm (RFE). The overall accuracy and kappa coefficient were compared to determine the optimal classification method. The main results are as follows: (1) RF showed the best performance among the five machine learning algorithms, with an overall accuracy of 89.76% and kappa coefficient of 0.88 when using 53 features (including spectral features (RGB bands), height information, vegetation indices, texture features, and geometric features) for wetland vegetation classification. (2) The RF model constructed by only spectral features showed poor classification results, with an overall accuracy of 73.66% and kappa coefficient of 0.70. By adding height information, VIs, texture features, and geometric features to construct the RF model layer by layer, the overall accuracy was improved by 8.78%, 3.41%, 2.93%, and 0.98%, respectively, demonstrating the importance of multi-feature combinations. (3) The contribution of different types of features to the RF model was not equal, and the height information was the most important for wetland vegetation classification, followed by the vegetation indices. (4) The RFE algorithm effectively reduced the number of original features from 53 to 36, generating an optimal feature subset for wetland vegetation classification. The RF based on the feature selection result of RFE (RF-RFE) had the best performance in ten scenarios, and provided an overall accuracy of 90.73%, which was 0.97% higher than the RF without feature selection. The results illustrate that the combination of UAV-based RGB imagery and the OBIA approach provides a straightforward, yet powerful, approach for high-precision wetland vegetation classification at the species level, in spite of limited spectral information. Compared with satellite data or UAVs equipped with other types of sensors, UAVs with RGB cameras are more cost efficient and convenient for wetland vegetation monitoring and mapping.

Characterizing Leaf Nutrients of Wetland Plants and Agricultural Crops with Nonparametric Approach Using Sentinel-2 Imagery Data

In arid environments of the world, particularly in sub-Saharan Africa and Asia, floodplain wetlands are a valuable agricultural resource. However, the water reticulation role by wetlands and crop production can negatively impact wetland plants. Knowledge on the foliar biochemical elements of wetland plants enhances understanding of the impacts of agricultural practices in wetlands. This study thus used Sentinel-2 multispectral data to predict seasonal variations in the concentrations of nine foliar biochemical elements in plant leaves of key floodplain wetland vegetation types and crops in the uMfolozi floodplain system (UFS). Nutrient concentrations in different floodplain plant species were estimated using Sentinel-2 multispectral data derived vegetation indices in concert with the random forest regression. The results showed a mean R2 of 0.87 and 0.86 for the dry winter and wet summer seasons, respectively. However, copper, sulphur, and magnesium were poorly correlated (R2 ≤ 0.5) with vegetation indices during the summer season. The average % relative root mean square errors (RMSE’s) for seasonal nutrient estimation accuracies for crops and wetland vegetation were 15.2 % and 26.8%, respectively. There was a significant difference in nutrient concentrations between the two plant types, (R2 = 0.94 (crops), R2 = 0.84 (vegetation). The red-edge position 1 (REP1) and the normalised difference vegetation index (NDVI) were the best nutrient predictors. These results demonstrate the usefulness of Sentinel-2 imagery and random forests regression in predicting seasonal, nutrient concentrations as well as the accumulation of chemicals in wetland vegetation and crops.

The Utility of Sentinel-2 MSI Data to Estimate Wetland Vegetation Leaf Area Index in Natural and Rehabilitated Wetlands

Wetland ecosystems are being modified and threatened due to anthropogenic activities and climate change, hence the urgent need for wetland restoration. Wetland rehabilitation is important in the reversal of these dire conditions, and this can be pursued through restoring damaged wetland ecosystems and recovering wetland vegetation. Wetland biophysical properties such as leaf area index (LAI) are important indicators of vegetation productivity and stress. Therefore, the study sought to test the potential of Sentinel-2 multispectral instrument (MSI) derived standard bands, traditional vegetation indices and red-edge derived vegetation indices in estimating wetland vegetation LAI across natural and rehabilitated wetlands. Traditional field surveys were carried out for LAI measurement of wetland vegetation using the LAI-2200 Plant Canopy Analyser. Partial Least Squares Regression (PLSR) algorithms were used to compare the estimation strength of models derived from all Sentinel-2 MSI bands, conventional vegetation indices and red-edge derived vegetation indices. Leave-one-out cross-validation (LOOCV) was completed on a selected measured dataset to evaluate the performance and accuracy of the estimation models. The optimal models for estimating wetland vegetation LAI were produced based on red-edge bands centred between the 705–783 nm as well as the 865 nm (Band 8a) of the electromagnetic spectrum. The results showed that vegetation indices derived from red-edge bands performed better at estimating LAI for both wetlands with a root mean square error of prediction (RMSE) of 0.32 m2/m2 and R2 of 0.61 for the natural wetland, and RMSE of 0.51 m2/m2 and R2 of 0.75 for the rehabilitated wetland. The optimal model for predicting LAI across natural and rehabilitated wetlands was attained based on red-edge bands centred at 705 nm (Band 5), 740 nm (Band 6), 783 nm (Band 7) as well as 865 nm (Band 8a) yielding a RMSE of 0.51 m2/m2 and R2 of 0.54. Overall, the results underscore the importance of remotely sensed derived data and vegetation indices in the optimal characterisation of wetland vegetation productivity which can be utilized in the monitoring and management of wetland ecosystems.