Search for: All records

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. 

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 

Conflict, manifesting as riots and protests, is a common occurrence in urban environments worldwide. Understanding their likely locations is crucial to policymakers, who may (for example) seek to provide overseas travelers with guidance on safe areas, or local policymakers with the ability to pre-position medical aid or police presences to mediate negative impacts associated with riot events. Past efforts to forecast these events have focused on the use of news and social media, restricting applicability to areas with available data. This study utilizes a ResNet convolutional neural network and high-resolution satellite imagery to estimate the spatial distribution of riots or protests within urban environments. At a global scale (N = 18,631 conflict events), by training our model to understand relationships between urban form and riot events, we are able to predict the likelihood that a given urban area will experience a riot or protest with accuracy as high as 97%. This research has the potential to improve our ability to forecast and understand the relationship between urban form and conflict events, even in data-sparse regions. 

The process of mapping shoreline structures (i.e., riprap, groins, breakwaters or bulkheads) is heavily reliant on in-situ field surveys and manual delineation using orthoimagery or aerial imagery. These processes are time and resource intensive, resulting in update times of longer than a decade for larger waterbodies. In this study, we explore the effectiveness of a deep learning approach to map shoreline armoring structures from remotely sensed high-resolution imagery. We focus on computationally efficient techniques which can be deployed in desktop environments similar to those used by human coders today, with the goal of providing a semi-automated technique which reduces the total amount of time required to delineate shoreline structures. We test a range of architectures using a dataset of over 10,000 observations of four classes of shoreline structure, finding that a ResNet18 based Pyramid Attention Network (PAN) architecture achieves 72% overall accuracy (60 cm resolution), with 80% and 94% prediction accuracy in breakwater and groins, respectively. This relatively lightweight implementation enabled a 1.5 kilometers of shoreline to be processed in 1.4 s (GPU) to 2.16 s (CPU) in simulated user environments. Finally, we present pyShore, an implementation of this deep learning algorithm made available for human coders to apply as a part of a semi-automated workflow.