Low elevation coastal zones (LECZ) are extensive throughout the southeastern United States. LECZ communities are threatened by inundation from sea level rise, storm surge, wetland degradation, land subsidence, and hydrological flooding. Communication among scientists, stakeholders, policy makers and minority and poor residents must improve. We must predict processes spanning the ecological, physical, social, and health sciences. Communities need to address linkages of (1) human and socioeconomic vulnerabilities; (2) public health and safety; (3) economic concerns; (4) land loss; (5) wetland threats; and (6) coastal inundation. Essential capabilities must include a network to assemble and distribute data and model code to assess risk and its causes, support adaptive management, and improve the resiliency of communities. Better communication of information and understanding among residents and officials is essential. Here we review recent background literature on these matters and offer recommendations for integrating natural and social sciences. We advocate for a cyber-network of scientists, modelers, engineers, educators, and stakeholders from academia, federal state and local agencies, non-governmental organizations, residents, and the private sector. Our vision is to enhance future resilience of LECZ communities by offering approaches to mitigate hazards to human health, safety and welfare and reduce impacts to coastal residents and industries.

Accurate mapping of nearshore bathymetry is essential for coastal management, navigation, and environmental monitoring. Traditional bathymetric mapping methods such as sonar surveys and LiDAR are often time-consuming and costly. This paper introduces BathyFormer, a novel vision transformer- and encoder-based deep learning model designed to estimate nearshore bathymetry from high-resolution multispectral satellite imagery. This methodology involves training the BathyFormer model on a dataset comprising satellite images and corresponding bathymetric data obtained from the Continuously Updated Digital Elevation Model (CUDEM). The model learns to predict water depths by analyzing the spectral signatures and spatial patterns present in the multispectral imagery. Validation of the estimated bathymetry maps using independent hydrographic survey data produces a root mean squared error (RMSE) ranging from 0.55 to 0.73 m at depths of 2 to 5 m across three different locations within the Chesapeake Bay, which were independent of the training set. This approach shows significant promise for large-scale, cost-effective shallow water nearshore bathymetric mapping, providing a valuable tool for coastal scientists, marine planners, and environmental managers.

Tidal marshes offer numerous ecological and economic benefits but are threatened by human development, sea-level rise, and invasive species. Routine mapping of their species composition is crucial for coastal management, yet current efforts are spatially and temporally limited and lack species identification. To address this, we used 3-m PlanetScope satellite imagery to classify four common marsh plants across Virginia’s Middle Peninsula in Chesapeake Bay, a region targeted for restoration given its ecological and economic significance. We developed a random forest classifier using May 2021 reference data from the Virginia Institute of Marine Science, delineating Spartina alterniflora, Phragmites australis, Spartina patens, and Juncus roemerianus at eight marshes. Balanced agreement was strong at 93%, ranging from 63% to 98% across individual marshes. We then expanded to the broader Middle Peninsula, using the Mann-Whitney U test to compare satellite- and reference-derived coverage of P. australis, finding moderate agreement despite a large temporal offset (r_rb = 0.45; N = 152). Following suitable model performance, we generated annual assessments for May 2021–2024. S. alterniflora was most extensively distributed, covering half of our study area. We also analyzed random forest class probabilities to inform data collection and model interpretation. Probabilities were generally above 0.6, although those accompanying J. roemerianus were notably lower. We present methods for large-scale species mapping to inform resource prioritization and coastal management, including a framework for communicating classification certainty, which is adaptable to stakeholder needs. Our framework can be used to retrain our classification model for application elsewhere, where local field data is available.

This article emphasizes the innovative integration of spatial data, remote sensing, machine learning, and community science to enhance adaptive management strategies aimed at supporting coastal resilience. By advancing the use of spatial analysis, this study addresses the pressing challenges posed by sea-level rise and shoreline erosion. The research focuses on mapping key shoreline features and coastal habitats in Virginia, USA, utilizing photo-interpretation and machine-learning techniques to update shoreline inventories efficiently and accurately. This novel approach not only improves the VIMS Shoreline Management Model (SMM) but also incorporates community science through a mobile application, allowing local residents to contribute valuable data on shoreline conditions and coastal habitats. By fostering community engagement and leveraging real-time information, decision-makers are better equipped to implement adaptive coastal management practices. Ultimately, this study highlights the critical importance of comprehensive spatial data and community involvement in developing effective strategies for enhancing coastal resilience in the face of climate change.

Cross-scale hydrodynamic modeling of managed realignment allows scientists to predict how marsh habitat and its morphology may develop over time, allowing for a forecast of project efficacy. However, relatively few studies analyze the paired morphological and vegetative evolution of sites, often neglecting the feedback between vegetation establishment, geomorphic change, and physical stressors, which may overestimate ecosystem services provided by the site. Here, the Semi-implicit Cross-scale Hydroscience Integrated System Model (SCHISM) based Tidal Marsh Model (TMM) was updated to incorporate physical stressors that affect marsh development and a simplified lifecycle approach. Freiston Shore, a managed realignment site in southeastern England within The Wash that was realigned in 2002, was used as a modeling test case to determine if these stressors enhance model performance in predicting the results of managed realignment. Adding stressors to control marsh extent resulted in slightly decreased marsh extent accuracy, but substantially improved the model’s ability to capture marsh creek and dike breach evolution within the site. Capturing marsh creek evolution resulted in substantially lower high-water level attenuation and faster flushing of the interior marsh, indicating that if stressors are not considered, high water level attenuation may be overestimated and flushing may be underestimated within managed realignment projects. From a management perspective, these results suggest that models used to evaluate managed realignment should prioritize the accurate representation of geomorphic processes, such as creek development, as these strongly influence site drainage, sediment transport, their coastal protection function, and long-term stability.