No abstract

Segmentation, or the classification of pixels (grid cells) in imagery, is ubiquitously applied in the natural sciences. Manual methods are often prohibitively time-consuming, especially those images consisting of small objects and/or significant spatial heterogeneity of colors or textures. Labeling complicated regions of transition that in Earth surface imagery are represented by collections of mixed-pixels, -textures, and -spectral signatures, can be especially error-prone because it is difficult to reliably unmix, identify and delineate consistently. However, the success of supervised machine learning (ML) approaches is entirely dependent on good label data. We describe a fast, semi-automated, method for interactive segmentation of N-dimensional (x, y, N) images into two-dimensional (x, y) label images. It uses human-in-the-loop ML to achieve consensus between the labeler and a model in an iterative workflow. The technique is reproducible; the sequence of decisions made by human labeler and ML algorithms can be encoded to file, so the entire process can be played back and new outputs generated with alternative decisions and/or algorithms. We illustrate the scientific potential of segmentation of imagery of diverse settings and image types using six case studies from river, estuarine, and open coast environments. These photographic and non-photographic imagery consist of 1-and 3-bands on regular and irregular grids ranging from centimeters to tens of meters. We demonstrate high levels of agreement in label images generated by several labelers on the same imagery, and make suggestions to achieve consensus and measure uncertainty, ideal for widespread application in training supervised ML for image segmentation.Plain Language Summary Labeling pixels in scientific images by hand is time-consuming and error-prone, so we would like to train computers to do that for us. We can use automated techniques from Artificial Intelligence or AI, like one called Deep Learning, but it needs a lot of example images and corresponding labels that have been made by hand. So, we still need to label quite a lot of images at the pixel level-called image segmentation. We made a computer program called Doodler that speeds up the process; you label some pixels, and it labels the rest. It is the fastest method we know of for image segmentation because it is semi-automated. We also show that it produces accurate and precise labeling, as we demonstrated by having multiple people use this method to label the same images. Because it is so fast and accurate, it allows us to get enough data to train Deep Learning models to do segmentation on all the images we have, from the past and in the future. Doodler therefore enables geoscientists to use Artificial Intelligence to extract much more information from their imagery, in service of geoscience in general.

Barrier islands are valued for their habitats and natural resources, recreational opportunities, high property values (e.g., Conroy & Milosch, 2011;Jin et al., 2015) and role in protecting the mainland from coastal storms (Grzegorzewski et al., 2011;Stone & McBride, 1998). Scientific understanding of their response to storms in the presence of changing climate and rising sea level is important for assessing their vulnerability and making decisions on infrastructure protection and resource management. The long-term survival of barrier islands depends on their ability to migrate upwards and landwards apace with relative sea-level rise (

Hurricanes are known to play a critical role in reshaping coastlines, but often only impacts on the open ocean coast are considered, ignoring seaward-directed forces and responses. The identification of subaerial evidence for storm-induced seaward transport is a critical step towards understanding its impact on coastal resiliency. The visual features, found in the National Oceanic and Atmospheric Administration, National Geodetic Survey Emergency Response Imagery (ERI) collected after recent hurricanes on the U.S. East Atlantic and Gulf of Mexico coasts, include scours and channelized erosion, but also deposition on the shoreface or in the nearshore as deltas and fans of various sizes. We catalog all available ERI and describe recently formed features found on the North Core Banks, North Carolina, after Hurricane Dorian (2019); the Carolina coasts after Hurricane Isaias (2020); the Isles Dernieres, Louisiana, after Hurricane Zeta (2020); and the southwest coast of Louisiana, after Hurricanes Laura and Delta (2020). Hundreds of features were identified over nearly 200 km of coastline with the density of features exceeding 20 per km in some areas. Individual features range in size from 5 m to 500 m in the alongshore, with similar dimensions in the cross-shore direction, including the formation or reactivation of outlets. The extensive occurrence of these storm-induced return-flow and seawardflow morphologic features demonstrates that their role in coastal evolution and resilience may be more prominent than previously thought. Based on these observations we propose clarifying terms for return- and seaward-flow features to distinguish them from more frequently documented landward-flow features and advocate for their inclusion in coastal change hazards classification schemes and coastal evolution morphodynamic models.