Bedload transport occurs when a sufficiently strong flow of fluid shears a bed of loose sedimentary grains of millimeter or larger size. Here, we show that a recently proposed artificial numerical method to alter fluid-particle interactions in grain-resolved numerical bedload simulations is physically unrealistic. We conclude, supported by independent modeling, that data created using this method, unlike previously claimed, does not resolve the issue of grain shape effects on bedload transport.

Coastal flooding can cause significant damage to coastal ecosystems, infrastructure, and communities and is expected to increase in frequency with the acceleration of sea level rise. In order to respond to it, it is crucial to measure and model their frequency and intensity. Here, we show deep-learning techniques can be successfully used to automatically detect flooding events from complex coastal imagery, opening the way to real-time monitoring and data acquisition for model development.