An official website of the United States government
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
A Deep Learning Approach to Segment Coastal Marsh Tidal Creek Networks from High-Resolution Aerial Imagery
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
- Award ID(s):
- 1832178
- PAR ID:
- 10561072
- Publisher / Repository:
- Remote Sensing
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 16
- Issue:
- 14
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 2659
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Coastal salt marshes store large amounts of carbon but the magnitude and patterns of greenhouse gas (GHG; i.e., carbon dioxide (CO2) and methane (CH4)) fluxes are unclear. Information about GHG fluxes from these ecosystems comes from studies of sediments or at the ecosystem‐scale (eddy covariance) but fluxes from tidal creeks are unknown. We measured GHG concentrations in water, water quality, meteorological parameters, sediment CO2efflux, ecosystem‐scale GHG fluxes, and plant phenology; all at half‐hour intervals over 1 year. Manual creek GHG flux measurements were used to calculate gas transfer velocity (k) and parameterize a model of water‐to‐atmosphere GHG fluxes. The creek was a source of GHGs to the atmosphere where tidal patterns controlled diel variability. Dissolved oxygen and wind speed were negatively correlated with creek CH4efflux. Despite lacking a seasonal pattern, creek CO2efflux was correlated with drivers such as turbidity across phenological phases. Overall, nighttime creek CO2efflux (3.6 ± 0.63 μmol/m2/s) was at least 2 times higher than nighttime marsh sediment CO2efflux (1.5 ± 1.23 μmol/m2/s). Creek CH4efflux (17.5 ± 6.9 nmol/m2/s) was 4 times lower than ecosystem‐scale CH4fluxes (68.1 ± 52.3 nmol/m2/s) across the year. These results suggest that tidal creeks are potential hotspots for CO2emissions and could contribute to lateral transport of CH4to the coastal ocean due to supersaturation of CH4(>6,000 μmol/mol) in water. This study provides insights for modeling GHG efflux from tidal creeks and suggests that changes in tide stage overshadow water temperature in determining magnitudes of fluxes.more » « less
-
Abstract Expansion of drainage networks through the headward erosion of tidal creeks is an eco‐geomorphologic response of salt marshes to accelerated sea‐level rise (SLR). This response can counter the negative impacts of an elevation deficit by increasing drainage and encouraging plant health, thereby reducing potential for submergence and marsh platform loss. In the wetlands of Cape Romain, SC, intense bioturbation near creek heads by the common marsh crabSesarma reticulatumhas been found to facilitate sediment erosion and rapid creek growth. This keystone grazer has been recently observed to have increasing influence on landscape evolution throughout the southeast US coast. Here, we compare measurements taken at Sapelo Island, GA, with those previously collected at Cape Romain, to confirm that eco‐geomorphic feedbacks facilitating creek growth at each location are similar, and to compare these processes under differing background conditions. We use sediment cores, precise elevation measurements and historical imagery to compare substrate properties, elevation within the tidal frame, creek growth rates and drainage morphology at both sites. Our results show identical processes; however, the higher elevation of the marsh at Sapelo Island leads to shallower and shorter periods of tidal inundation, explaining the greater soil strength and lower belowground biomass compared with the marsh at Cape Romain. The smaller tidal range at the site in Cape Romain compared with Sapelo Island translates to a proportionally shallower depth of tidal creeks, which therefore requires less erosion to produce headward creek extension. These effects are likely to have contributed to slower growth rates of tidal creeks at Sapelo Island during the past several decades of SLR. Our findings highlight the similarities in process but differences in rates in how marshes are responding to climate‐related stress.more » « less
-
We are currently living in the era of big data. The volume of collected or archived geospatial data for land use and land cover (LULC) mapping including remotely sensed satellite imagery and auxiliary geospatial datasets is increasing. Innovative machine learning, deep learning algorithms, and cutting-edge cloud computing have also recently been developed. While new opportunities are provided by these geospatial big data and advanced computer technologies for LULC mapping, challenges also emerge for LULC mapping from using these geospatial big data. This article summarizes the review studies and research progress in remote sensing, machine learning, deep learning, and geospatial big data for LULC mapping since 2015. We identified the opportunities, challenges, and future directions of using geospatial big data for LULC mapping. More research needs to be performed for improved LULC mapping at large scales.more » « less
-
Rapid global warming is catalyzing widespread permafrost degradation in the Arctic, leading to destructive land-surface subsidence that destabilizes and deforms the ground. Consequently, human-built infrastructure constructed upon permafrost is currently at major risk of structural failure. Risk assessment frameworks that attempt to study this issue assume that precise information on the location and extent of infrastructure is known. However, complete, high-quality, uniform geospatial datasets of built infrastructure that are readily available for such scientific studies are lacking. While imagery-enabled mapping can fill this knowledge gap, the small size of individual structures and vast geographical extent of the Arctic necessitate large volumes of very high spatial resolution remote sensing imagery. Transforming this ‘big’ imagery data into ‘science-ready’ information demands highly automated image analysis pipelines driven by advanced computer vision algorithms. Despite this, previous fine resolution studies have been limited to manual digitization of features on locally confined scales. Therefore, this exploratory study serves as the first investigation into fully automated analysis of sub-meter spatial resolution satellite imagery for automated detection of Arctic built infrastructure. We tasked the U-Net, a deep learning-based semantic segmentation model, with classifying different infrastructure types (residential, commercial, public, and industrial buildings, as well as roads) from commercial satellite imagery of Utqiagvik and Prudhoe Bay, Alaska. We also conducted a systematic experiment to understand how image augmentation can impact model performance when labeled training data is limited. When optimal augmentation methods were applied, the U-Net achieved an average F1 score of 0.83. Overall, our experimental findings show that the U-Net-based workflow is a promising method for automated Arctic built infrastructure detection that, combined with existing optimized workflows, such as MAPLE, could be expanded to map a multitude of infrastructure types spanning the pan-Arctic.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs16142659
