Sediment grain size is a critical parameter for sediment mobilization and transport, but often has the highest uncertainty of any coastal sediment transport model input parameter. SandSnap is an initiative to engage the public to amass a beach grain size database by taking photos of the beach sand with a coin in the image for scale and uploading the image to a web application. Images are analyzed with two deep learning convolutional neural networks one to detect the coin and the second to measure the grain size, which is trained on sediment samples within the sand regime. The results for nine gradation metrics are returned to the user within 2 min of image upload. Results from 263 test images have a mean percent error of −6.5% and median absolute error of 22.4% for the median grain size (d50) with a small fine bias of −0.042 mm. The use of the database is highlighted by applying SandSnap output as an input to the AeoLiS aeolian sediment transport model to predict coastal dune growth at a nearly national scale using the full eight grain size classes (d10 – d90) from the SandSnap database. These outputs are used to inform the potential value of having spatially comprehensive grain size distribution information as part of coastal engineering design and planning. Education and outreach techniques for the SandSnap initiative are described in the manuscript. Though some challenges remain, the spatially and temporally robust beach grain size database being developed by SandSnap will help to improve numerous coastal engineering analyses including coastal resilience and vulnerability quantification, beach nourishment life cycle and uncertainty analysis, beach compatibility for the beneficial use of dredged sediment, and large-scale coastal morphology modeling.