An official website of the United States government
Tidal creeks play a vital role in influencing geospatial evolution and marsh ecological communities in coastal landscapes. However, evaluating the geospatial characteristics of numerous creeks across a site and understanding their ecological relationships pose significant challenges due to the labor-intensive nature of manual delineation from imagery. Traditional methods rely on manual annotation in GIS interfaces, which is slow and tedious. This study explores the application of Attention-based Dense U-Net (ADU-Net), a deep learning image segmentation model, for automatically classifying creek pixels in high-resolution (0.5 m) orthorectified aerial imagery in coastal Georgia, USA. We observed that ADU-Net achieved an outstanding F1 score of 0.98 in identifying creek pixels, demonstrating its ability in tidal creek mapping. The study highlights the potential of deep learning models for automated tidal creek mapping, opening avenues for future investigations into the role of creeks in marshes’ response to environmental changes.
more »
« less
This content will become publicly available on December 31, 2025
Mapping the tidal marshes of coastal Virginia: a hierarchical transfer learning approach
Coastal wetlands, especially tidal marshes, play a crucial role in supporting ecosystems and slowing shoreline erosion. Accurate and cost-effective identification and classification of various marshtypes, such as high and low marshes, are important for effective coastal management and conservation endeavors. However, mapping tidal marshes is challenging due to heterogeneous coastal vegetation and dynamic tidal influences. In this study, we employ a deep learning segmentation model to automate the identification and classification of tidal marsh communities in coastal Virginia, USA, using seasonal, publicly available satellite and aerial images. This study leverages the combined capabilities of Sentinel-2 and National Agriculture Imagery Program (NAIP)imagery and a UNet architecture to accurately classify tidal marsh communities. We illustrate that by leveraging features learned from data abundant regions and small quantities of high-quality training data collected from the target region, an accuracy as high as 88% can be achieved in the classification of marsh types, specifically high marsh and low marsh, at a spatial resolution of 0.6 m.This study contributes to the field of marsh mapping by highlighting the potential of combining multispectral satellite imagery and deep learning for accurate and efficient marsh type classification
more »
« less
- Award ID(s):
- 2317591
- PAR ID:
- 10537803
- Publisher / Repository:
- Taylor & Francis
- Date Published:
- Journal Name:
- GIScience & Remote Sensing
- Volume:
- 61
- Issue:
- 1
- ISSN:
- 1548-1603
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Sea level rise (SLR) is threatening coastal marshes, leading to large‐scale marsh loss in several micro‐tidal systems. Early recognition of marsh vulnerability to SLR is critical in these systems to aid managers to take appropriate restoration or mitigation measures. However, it is not clear if current marsh vulnerability indicators correctly assess long‐term stability of the marsh system. In this study, two indicators of marsh stress were studied: (i) the skewness of the marsh elevation distribution, and (ii) the abundance of codominant species in mixtures. We combined high‐precision elevation measurements (GPS), LiDAR imagery, vegetation surveys and water level measurements to study these indicators in an organogenic micro‐tidal system (Blackwater River, Maryland, USA), where large‐scale historical conversion from marshes to shallow ponds resulted in a gradient of increasing marsh loss. The two indicators reveal increasingly stressed marshes along the marsh loss gradient, but suggest that the field site with the most marsh loss seems to experience less stress. For the latter site, previous research indicates that wind waves generated on interior marsh ponds contribute to lateral erosion of surrounding marsh edges and hence marsh loss. The eroded marsh sediment might temporarily provide the remaining marshes with the necessary sediment to keep up with relative SLR. However, this is only a short‐term alleviation, as lateral marsh edge erosion and sediment export lead to severe marsh loss in the long term. Our findings indicate that marsh elevation skewness and the abundance of codominant species in mixtures can be used to supplement existing marsh stress indicators, but that additional indices such as fetch length and the sediment budget should be included to account for lateral marsh erosion and sediment export and to correctly assess long‐term stability of micro‐tidal marshes. © 2020 John Wiley & Sons, Ltd.more » « less
-
As a symptom of accelerated sea level rise and historic impacts to tidal hydrology from agricultural and mosquito control activities, coastal marshes in the Northeastern U.S. are experiencing conversion to open water through edge loss, widening and headward erosion of tidal channels, and the formation and expansion of interior ponds. These interior ponds often form in high elevation marsh, confounding the notion applied in predictive modeling that salt marshes convert to open water when elevation falls below a critical surface inundation threshold. The installation of tidal channel extension features, or runnels, is a technique that has been implemented to reduce water levels and permit vegetation reestablishment in drowning coastal marshes, although there are limited data available to recommend its advisability. We report on 5 years of vegetation and hydrologic monitoring of two locations where a total of 600-m of shallow (0.15–0.30-m in diameter and depth) runnels were installed in 2015 and 2016 to enhance drainage, in the Pettaquamscutt River Estuary, in southern Rhode Island, United States. Results from this Before-After Control-Impact (BACI) designed study found that runnel installation successfully promoted plant recolonization, although runnels did not consistently promote increases in high marsh species presence or diversity. Runnels reduced the groundwater table (by 0.07–0.12 m), and at one location, the groundwater table experienced a 2-fold increase in the fraction of the in-channel tidal range that was observed in the marsh water table. We suggest that restoration of tidal hydrology through runnel installation holds promise as a tool to encourage revegetation and extend the lifespan of drowning coastal marshes where interior ponds are expanding. In addition, our study highlights the importance of considering the rising groundwater table as an important factor in marsh drowning due to expanding interior ponds found on the marsh platform.more » « less
-
High resolution mapping of coastal habitats is invaluable for resource inventory, change detection, and inventory of aquaculture applications. However, coastal areas, especially the interior of mangroves, are often difficult to access. An Unmanned Aerial Vehicle (UAV), equipped with a multispectral sensor, affords an opportunity to improve upon satellite imagery for coastal management because of the very high spatial resolution, multispectral capability, and opportunity to collect real-time observations. Despite the recent and rapid development of UAV mapping applications, few articles have quantitatively compared how much improvement there is of UAV multispectral mapping methods compared to more conventional remote sensing data such as satellite imagery. The objective of this paper is to quantitatively demonstrate the improvements of a multispectral UAV mapping technique for higher resolution images used for advanced mapping and assessing coastal land cover. We performed multispectral UAV mapping fieldwork trials over Indian River Lagoon along the central Atlantic coast of Florida. Ground Control Points (GCPs) were collected to generate a rigorous geo-referenced dataset of UAV imagery and support comparison to geo-referenced satellite and aerial imagery. Multi-spectral satellite imagery (Sentinel-2) was also acquired to map land cover for the same region. NDVI and object-oriented classification methods were used for comparison between UAV and satellite mapping capabilities. Compared with aerial images acquired from Florida Department of Environmental Protection, the UAV multi-spectral mapping method used in this study provided advanced information of the physical conditions of the study area, an improved land feature delineation, and a significantly better mapping product than satellite imagery with coarser resolution. The study demonstrates a replicable UAV multi-spectral mapping method useful for study sites that lack high quality data.more » « less
-
null (Ed.)Abstract. The presence of bare patches within otherwise vegetated coastal marshes is sometimes considered to be a symptom of marsh dieback and the subsequent loss of important ecosystem services. Here we studied the topographical conditions determining the presence and revegetation of bare patches in three marsh sites with contrasting tidal range, sediment supply, and plant species: the Scheldt estuary (the Netherlands), Venice lagoon (Italy), and Blackwater marshes (Maryland, USA). Based on GIS (geographic information system) analyses of aerial photos and lidar imagery of high resolution (≤2×2 m pixels), we analyzed the topographic conditions under which bare patches occur, including their surface elevation, size, distance from channels, and whether they are connected or not to channels. Our results demonstrate that, for the different marsh sites, bare patches can be connected or unconnected to the channel network and that there is a positive relationship between the width of the connecting channels and the size of the bare patches, in each of the three marsh sites. Further, pixels located in bare patches connected to channels occur most frequently at the lowest elevations and farthest distance from the channels. Pixels in bare patches disconnected from channels occur most frequently at intermediate elevations and distances from channels, and vegetated marshes dominate at highest elevations and shortest distances from channels. In line with previous studies, revegetation in bare patches is observed in only one site with the highest tidal range and highest sediment availability, and it preferentially occurs from the edges of small unconnected bare patches at intermediate elevations and intermediate distances from channels. Although our study is only for three different marsh sites with large variations in local conditions, such as tidal range, sediment availability, and plant species, it suggests that similar topographic conditions determine the occurrence of bare patches. Such insights may inform decision makers on coastal marsh management on where to focus monitoring of early signatures of marsh degradation.more » « less
