Search Results (65)

Accurate classification of salt marsh vegetation is vital for conservation efforts and environmental monitoring, particularly given the critical role these ecosystems play as carbon sinks. Understanding and quantifying the extent and types of habitats present in Ireland is essential to support national biodiversity goals and climate action plans. Unmanned Aerial Vehicles (UAVs) equipped with optical sensors offer a powerful means of mapping vegetation in these areas. However, many current studies rely on single-sensor approaches, which can constrain the accuracy of classification and limit our understanding of complex habitat dynamics. This study evaluates the integration of Red-Green-Blue (RGB), Multispectral Imaging (MSI), and Hyperspectral Imaging (HSI) to improve species classification compared to using individual sensors. UAV surveys were conducted with RGB, MSI, and HSI sensors, and the collected data were classified using Random Forest (RF), Spectral Angle Mapper (SAM), and Support Vector Machine (SVM) algorithms. The classification performance was assessed using Overall Accuracy (OA), Kappa Coefficient (k), Producer’s Accuracy (PA), and User’s Accuracy (UA), for both individual sensor datasets and the fused dataset generated via band stacking. The multi-camera approach achieved a 97% classification accuracy, surpassing the highest accuracy obtained by a single sensor (HSI, 92%). This demonstrates that data fusion and band reduction techniques improve species differentiation, particularly for vegetation with overlapping spectral signatures. The results suggest that multi-sensor UAV systems offer a cost-effective and efficient approach to ecosystem monitoring, biodiversity assessment, and conservation planning. Full article

Salt marsh ecosystems play a critical role in coastal protection, carbon sequestration, and biodiversity preservation. However, they are increasingly threatened by climate change and anthropogenic activities, necessitating precise vegetation mapping for effective conservation. This study investigated the effectiveness of spectral features and machine learning models in separating typical salt marsh vegetation types in the Yellow River Delta using uncrewed aerial vehicle (UAV)-derived multispectral imagery. The results revealed that the Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), and Optimized Soil Adjusted Vegetation Index (OSAVI) were pivotal in differentiating vegetation types, compared with spectral reflectance at individual bands. Among the evaluated models, U-Net achieved the highest overall accuracy (94.05%), followed by SegNet (93.26%). However, the U-Net model produced overly distinct and abrupt boundaries between vegetation types, lacking the natural transitions found in real vegetation distributions. In contrast, the SegNet model excelled in boundary handling, better capturing the natural transitions between vegetation types. Both deep learning models outperformed Random Forest (83.74%) and Extreme Gradient Boosting (83.34%). This study highlights the advantages of deep learning models for precise salt marsh vegetation mapping and their potential in ecological monitoring and conservation efforts. Full article

Managed dyke realignment (MR) is a nature-based technique that shifts dyke systems farther inland, allowing for restoration of tidal flow and tidal wetland vegetation. While restoration of tidal flow can result in rapid sediment accretion and vegetation recovery, dykelands on the east coast of Canada are often agricultural, with legacy vegetation and ditches present upon initiation of MR. We combined measurements of sediment flux and accretion, digital surface and drainage network models, and vegetation mapping to understand the effects of legacy features on geomorphological evolution and restoration trajectory at a Bay of Fundy MR site. Removal of legacy vegetation and channels in a borrow pit allowed comparison with unaltered areas. Magnitudes of volumetric change from erosion at the channel mouth were similar to gains on the borrow pit, suggesting that channel mouth erosion could represent a significant sediment subsidy for restoring the marsh platform. Pre-existing pasture vegetation is likely to have slowed wetland vegetation establishment, suggesting that mowing prior to MR may speed recovery. Repeated high resolution vertically precise aerial surveys allowed understanding of the effects of elevation and proximity to the drainage network on spatial and temporal variability in marsh surface elevation increase and vegetation recovery. Full article

Salt marsh vegetation in the Yellow River Delta, including Phragmites australis (P. australis), Suaeda salsa (S. salsa), and Tamarix chinensis (T. chinensis), is essential for the stability of wetland ecosystems. In recent years, salt marsh vegetation has experienced severe degradation, which is primarily due to invasive species and human activities. Therefore, the accurate monitoring of the spatial distribution of these vegetation types is critical for the ecological protection and restoration of the Yellow River Delta. This study proposes a multi-source remote sensing data fusion method based on Sentinel-1 and Sentinel-2 imagery, integrating the temporal characteristics of optical and SAR (synthetic aperture radar) data for the classification mapping of salt marsh vegetation in the Yellow River Delta. Phenological and polarization features were extracted to capture vegetation characteristics. A random forest algorithm was then applied to evaluate the impact of different feature combinations on classification accuracy. Combining optical and SAR time-series data significantly enhanced classification accuracy, particularly in differentiating P. australis, S. salsa, and T. chinensis. The integration of phenological features, polarization ratio, and polarization difference achieved a classification accuracy of 93.51% with a Kappa coefficient of 0.917, outperforming the use of individual data sources. Full article

Tidal marshes play a globally critical role in carbon and hydrologic cycles by sequestering carbon dioxide from the atmosphere and exporting dissolved organic carbon to connected estuaries. These ecosystems provide critical habitat to a variety of fauna and also reduce coastal flood impacts. Accurate characterization of tidal marsh inundation dynamics is crucial for understanding these processes and ecosystem services. In this study, we developed remote sensing-based inundation classifications over a range of tidal stages for marshes of the Mid-Atlantic and Gulf of Mexico regions of the United States. Inundation products were derived from C-band and L-band synthetic aperture radar (SAR) imagery using backscatter thresholding and temporal change detection approaches. Inundation products were validated with in situ water level observations and radiometric modeling. The Michigan Microwave Canopy Scattering (MIMICS) radiometric model was used to simulate radar backscatter response for tidal marshes across a range of vegetation parameterizations and simulated hydrologic states. Our findings demonstrate that inundation classifications based on L-band SAR—developed using backscatter thresholding applied to single-date imagery—were comparable in accuracy to the best performing C-band SAR inundation classifications that required change detection approaches applied to time-series imagery (90.0% vs. 88.8% accuracy, respectively). L-band SAR backscatter threshold inundation products were also compared to polarimetric decompositions from quad-polarimetric Phased Array L-band Synthetic Aperture Radar 2 (PALSAR-2) and L-band Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR) imagery. Polarimetric decomposition analysis showed a relative shift from volume and single-bounce scattering to double-bounce scattering in response to increasing tidal stage and associated increases in classified inundated area. MIMICS modeling similarly showed a relative shift to double-bounce scattering and a decrease in total backscatter in response to inundation. These findings have relevance to the upcoming NASA-ISRO Synthetic Aperture Radar (NISAR) mission, as threshold-based classifications of wetland inundation dynamics will be employed to verify that NISAR datasets satisfy associated mission science requirements to map wetland inundation with classification accuracies better than 80% at 1 hectare spatial scales. Full article

Salt marshes, as one of the most productive ecosystems on earth, have experienced fragmentation, degradation, and losses due to the impacts of climate change and human overexploitation. Accurate monitoring of vegetation distribution and composition is crucial for salt marsh protection. However, achieving accurate mapping has posed a challenge. Leveraging the high spatiotemporal resolution of the Sentinel series data, this study developed a method for high-accuracy mapping based on monthly changes across the vegetation life cycle, utilizing the random forest algorithm. This method was applied to identify Phragmites australis, Suaeda salsa, Spartina alterniflora, and the mixed-vegetation zones of Tamarix chinensis in the Yellow River Delta, and to analyze the key features of the model. The results indicate that: (1) integrating Sentinel-1 and Sentinel-2 satellite data achieved superior mapping accuracy (OA = 90.7%) compared to using either satellite individually; (2) the inclusion of SAR data significantly enhanced the classification accuracy within the mixed-vegetation zone, with “SAR_divi” in July emerging as the pivotal distinguishing feature; and (3) the overall extent of salt marsh vegetation in the Yellow River Delta remained relatively stable from 2018 to 2022, with the largest area recorded in 2020 (265.69 km²). These results demonstrate the robustness of integrating Sentinel-1 and Sentinel-2 features for mapping salt marsh, particularly in complex mixed-vegetation zones. Such insights offer valuable guidance for the conservation and management of salt marsh ecosystems. Full article

Unoccupied aerial systems (UASs) are increasingly being deployed in coastal environments to rapidly map and monitor changes to geomorphology, vegetation, and infrastructure, particularly in difficult to access areas. UAS data, relative to airplane or satellite data, typically have higher spatial resolution, sensor customization, and increased flexibility in temporal resolution, which benefits monitoring applications. UAS data have been used to map and monitor invasive species occurrence and expansion, such as Phragmites australis, a reed species in wetlands throughout the eastern United States. To date, the work on this species has been largely opportunistic or ad hoc. Here, we statistically and qualitatively compare results from several sensors and classification workflows to develop baseline understanding of the accuracy of different approaches used to map Phragmites. Two types of UAS imagery were collected in a Phragmites-invaded salt marsh setting—natural color red-green-blue (RGB) imagery and multispectral imagery spanning visible and near infrared wavelengths. We evaluated whether one imagery type provided significantly better classification results for mapping land cover than the other, also considering trade-offs like overall accuracy, financial costs, and effort. We tested the transferability of classification workflows that provided the highest thematic accuracy to another barrier island environment with known Phragmites stands. We showed that both UAS sensor types were effective in classifying Phragmites cover, with neither resulting in significantly better classification results than the other for Phragmites detection (overall accuracy up to 0.95, Phragmites recall up to 0.86 at the pilot study site). We also found the highest accuracy workflows were transferrable to sites in a barrier island setting, although the quality of results varied across these sites (overall accuracy up to 0.97, Phragmites recall up to 0.90 at the additional study sites). Full article

Wetland ecosystems are experiencing rapid degradation due to human activities, particularly the diversion of natural flows for various purposes, leading to significant alterations in wetland hydrology and their ecological functions. However, understanding and quantifying these eco-hydrological changes, especially concerning inundation dynamics, presents a formidable challenge due to the lack of long-term, observation-based spatiotemporal inundation information. In this study, we classified wetland areas into ten equal-interval classes based on inundation probability derived from a dense, 30-year time series of Landsat-based inundation maps over an Australian dryland riparian wetland, Macquarie Marshes. These maps were then compared with three simplified vegetation patches in the area: river red gum forest, river red gum woodland, and shrubland. Our findings reveal a higher inundation probability over a small area covered by river red gum forest, exhibiting persistent inundation over time. In contrast, river red gum woodland and shrubland areas show fluctuating inundation patterns. When comparing percentage inundation with the Normalized Difference Vegetation Index (NDVI), we observed a notable agreement in peaks, with a lag time in NDVI response. A strong correlation between NDVI and the percentage of inundated area was found in the river red gum woodland patch. During dry, wet, and intermediate years, the shrubland patch consistently demonstrated similar inundation probabilities, while river red gum patches exhibited variable probabilities. During drying events, the shrubland patch dried faster, likely due to higher evaporation rates driven by exposure to solar radiation. However, long-term inundation probability exhibited agreement with the SAGA wetness index, highlighting the influence of topography on inundation probability. These findings provide crucial insights into the complex interactions between hydrological processes and vegetation dynamics in wetland ecosystems, underscoring the need for comprehensive monitoring and management strategies to mitigate degradation and preserve these vital ecosystems. Full article

Coastal wetlands are vulnerable to accelerated sea-level rise, yet knowledge about their extent and distribution is often limited. We developed a land cover classification of wetlands in the coastal plains of the southern United States along the Gulf of Mexico (Texas, Louisiana, Mississippi, Alabama, and Florida) using 6161 very-high (2 m per pixel) resolution WorldView-2 and WorldView-3 satellite images from 2012 to 2015. Area extent estimations were obtained for the following vegetated classes: marsh, scrub, grass, forested upland, and forested wetland, located in elevation brackets between 0 and 10 m above sea level at 0.1 m intervals. Sea-level trends were estimated for each coastal state using tide gauge data collected over the period 1983–2021 and projected for 2100 using the trend estimated over that period. These trends were considered conservative, as sea level rise in the region accelerated between 2010 and 2021. Estimated losses in vegetation area due to sea level rise by 2100 are projected to be at least 12,587 km², of which 3224 km² would be coastal wetlands. Louisiana is expected to suffer the largest losses in vegetation (80%) and coastal wetlands (75%) by 2100. Such high-resolution coastal mapping products help to guide adaptation plans in the region, including planning for wetland conservation and coastal development. Full article

Accompanying climate change and sea level rise, tidal marsh mortality in coastal wetlands has been globally observed that urges the documentation of high-resolution, 3D marsh inventory to assist resilience planning. Drone Lidar has proven useful in extracting the fine-scale bare earth terrain and canopy height. Beyond that, this study performed marsh biomass mapping from drone Lidar point cloud in a S. alterniflora-dominated estuary on the Southeast U.S. coast. Three point classes (ground, low-veg, and high-veg) were classified via point cloud deep learning. Considering only vegetation points in the vertical profile, a profile area-weighted height (H_PA) was extracted at a grid size of 50 cm × 50 cm. Vegetation point densities were also extracted at each grid. Adopting the plant-level allometric equations of stem biomass from long-term S. alterniflora surveys, a Lidar biomass index (Lidar_BI) was built to represent the relative quantity of marsh biomass in a range of [0, 1] across the estuary. Compared with the clipped dry biomass samples, it achieved a comparable and slightly better performance (R² = 0.5) than the commonly applied spectral index approaches (R² = 0.4) in the same marsh field. This study indicates the feasibility of the drone Lidar point cloud for marsh biomass mapping. More advantageously, the drone Lidar approach yields information on plant community architecture, such as canopy height and plant density distributions, which are key factors in evaluating marsh habitat and its ecological services. Full article

Wetlands are integral components of agricultural landscapes, providing a wide range of ecological, economic, and social benefits essential for sustainable development and rural livelihoods. Globally, they are vulnerable ecological assets facing several significant threats including water extraction and regulation, land clearing and reclamation, and climate change. Classification and mapping of wetlands in agricultural landscapes is crucial for conserving these ecosystems to maintain their ecological integrity amidst ongoing land-use changes and environmental pressures. This study aims to establish a robust framework for wetland classification and mapping in intensive agricultural landscapes using time series of Sentinel-2 imagery, with a focus on the Gwydir Wetland Complex situated in the northern Murray–Darling Basin—Australia’s largest river system. Using the Google Earth Engine (GEE) platform, we extracted two groups of predictors based on six vegetation indices time series calculated from multi-temporal Sentinel-2 surface reflectance (SR) imagery: the first is statistical features summarizing the time series and the second is phenological features based on harmonic analysis of time series data (HANTS). We developed and evaluated random forest (RF) models for each level of classification with combination of different groups of predictors. Our results show that RF models involving both HANTS and statistical features perform strongly with significantly high overall accuracy and class-weighted F1 scores (p < 0.05) when comparing with models with either statistical or HANTS variables. While the models have excellent performance (F-score greater than 0.9) in distinguishing wetlands from other landcovers (croplands, terrestrial uplands, and open waters), the inter-class discriminating power among wetlands is class-specific: wetlands that are frequently inundated (including river red gum forests and wetlands dominated by common reed, water couch, and marsh club-rush) are generally better identified than the ones that are flooded less frequently, such as sedgelands and woodlands dominated by black box and coolabah. This study demonstrates that HANTS features extracted from time series Sentinel data can significantly improve the accuracy of wetland mapping in highly fragmentated agricultural landscapes. Thus, this framework enables wetland classification and mapping to be updated on a regular basis to better understand the dynamic nature of these complex ecosystems and improve long-term wetland monitoring. Full article

When droughts occur, freshwater inputs to coastal wetlands can become scarce and hypersalinity can become a problem. In 2023, a severe drought negatively affected a Texas watershed known as Lake Austin that fed a large expanse of wetlands on East Matagorda Bay. To study the hypersalinity problem in these wetlands, we identified freshwater inflows and mapped vegetation changes over time. We found that from 1943 to 2023, the upper portion of the Lake Austin watershed lost freshwater wetlands to agricultural conversion, and ranged from fresh to brackish, with salinity rapidly rising to a maximum of 31 mS during the summer drought of 2023. The lower portion of the watershed gained saltwater wetlands due to sea level rise, and marshes became hypersaline (64–96 mS) during the 2023 drought, endangering its biota. But after large precipitation events, the entire Lake Austin basin rapidly freshened but then returned to its normal salinities within a week as the tides re-delivered saltwater into its basin. Given current climatic trends, we expect that freshwater inflow will continue to slightly increase for the Lake Austin watershed but also that there will be more extreme periods of episodic drought that negatively affect its wetlands. Accordingly, we assessed several potential restoration actions that would improve freshwater flow and delivery to the Lake Austin coastal wetlands. Full article

Salt marshes play a critical role in supporting water quality, erosion control, flood protection, and carbon sequestration. Threats from climate change and human activities have prompted global restoration initiatives. We analyzed restoration efforts worldwide from 1978 to 2022, using the Web of Science database and SciMAT mapping tool. After a PRISMA screening to identify methodologies, success rates, and key indicators, a total of 62 publications underwent detailed analysis, to increase knowledge on the best practices to employ in future restoration interventions and evaluation of their effectiveness. The research reveals a growing interest in ecosystem dynamics, biodiversity, anthropogenic impacts, and ecosystem services. Assisted interventions emerged as the predominant restoration method, employing 15 indicators across vegetation, sediment, fauna, and water, each one using different metrics for the intervention evaluation based on how good the outcome of the interventions described in the reviewed studies met the desired result. Our analysis suggests that combining natural interventions such as managed realignment with reconnection to tidal waters, along with long-term monitoring of vegetation, fauna, and water indicators such as sedimentation and erosion rates, plant cover and biomass, as well as fauna diversity and density, leads to the most successful outcomes. We provide valuable insights into best practices for future restoration interventions, offering guidance to future practitioners and policymakers based on a comprehensive review of the scientific literature, contributing to the resilience of these vital ecosystems, and ensuring effective restoration actions in the coming years. Full article

Monitoring salt marshes with remote sensing is necessary to evaluate their state and restoration. Determining appropriate techniques for this can be overwhelming. Our study provides insight into whether a pixel- or object-based Random Forest classification approach is best for mapping vegetation in north temperate salt marshes. We used input variables from drone images (raw reflectances, vegetation indices, and textural features) acquired in June, July, and August 2021 of a salt marsh restoration and reference site in Aulac, New Brunswick, Canada. We also investigated the importance of input variables and whether using landcover classes representing areas of change was a practical way to evaluate variation in the monthly images. Our results indicated that (1) the classifiers achieved overall validation accuracies of 91.1–95.2%; (2) pixel-based classifiers outperformed object-based classifiers by 1.3–2.0%; (3) input variables extracted from the August images were more important than those extracted from the June and July images; (4) certain raw reflectances, vegetation indices, and textural features were among the most important variables; and (5) classes that changed temporally were mapped with user’s and producer’s validation accuracies of 86.7–100.0%. Knowledge gained during this study will inform assessments of salt marsh restoration trajectories spanning multiple years. Full article

Coastal wetlands encompass diverse ecosystems such as tidal marshes, mangroves, and seagrasses, which harbor substantial amounts of carbon (C) within their vegetation and soils. Despite their relatively small global extent, these wetlands exhibit carbon sequestration rates on par with those observed in terrestrial forests. The application of remote sensing technologies offers a promising means of monitoring aboveground biomass (AGB) in wetland environments. However, the scarcity of field data poses a significant challenge to the utilization of spaceborne data for accurate estimation of AGB in coastal wetlands. To address this limitation, this study presents a novel multi-scale approach that integrates field data, aerial imaging, and satellite platforms to generate high-quality biomass maps across varying scales. At the fine scale level, the AVIRIS-NG hyperspectral data were employed to develop a model for estimating AGB with an exceptional spatial resolution of 5 m. Subsequently, at a broader scale, large-scale and multitemporal models were constructed using spaceborne Sentinel-1 and Sentinel-2 data collected in 2021. The Random Forest (RF) algorithm was utilized to train spring, fall and multi-temporal models using 70% of the available reference data. Using the remaining 30% of untouched data for model validation, Root Mean Square Errors (RMSE) of 0.97, 0.98, and 1.61 Mg ha⁻¹ was achieved for the spring, fall, and multi-temporal models, respectively. The highest R-squared value of 0.65 was achieved for the multi-temporal model. Additionally, the analysis highlighted the importance of various features in biomass estimation, indicating the contribution of different bands and indices. By leveraging the wetland inventory classification map, a comprehensive temporal analysis was conducted to examine the average and total AGB dynamics across various wetland classes. This analysis elucidated the patterns and fluctuations in AGB over time, providing valuable insights into the temporal dynamics of these wetland ecosystems. Full article