River meanders are one of the most recurrent and varied patterns in fluvial systems. Multiple attempts have been made to detect and categorise patterns in meandering rivers to understand their shape and evolution. A novel data-driven approach was used to classify single-bend meanders. A dataset containing approximately 10 million single-lobe meander bends was generated using the Kinoshita curve. A neural network autoencoder was trained over the curvature energy spectra of Kinoshita-generated meanders. Then, the trained network was then tested on real meander bends extracted from satellite images, and the energy spectrum in the meander curvature was reconstructed accurately thanks to the autoencoder architecture. The meander spectrum reconstruction was clustered, and three main bend shapes were found associated with the meander datasets, namely symmetric, upstream-skewed, and downstream-skewed. The autoencoder-based classification framework allowed bend shape detection along rivers, finding the dominant pattern with implications on migration trends. By studying the shift in the prevailing bend shape over time, cutoff events were approximately forecast along the Ucayali River, whose migration was remotely sensed for 32 years. Overall, the method proposed opens the venue to data-driven classifications to understand and manage meandering rivers. Bend shape classification can thus inform restoration and flood control practices and contribute to predicting meander evolution from satellite images or sedimentary records.

The bidispersity observed in the grain-size distribution of rock avalanches and volcanic debris avalanches (rock/debris avalanches) has been proposed as a property contributing to their long runout. This has been supported by small-scale analogue experimental studies which propose that a small proportions of fine particles, mixed with coarser, enhances granular avalanche runout. However, the mechanisms enabling this phenomenon and their resemblance to rock/debris avalanches have not been directly evaluated. Here, binary mixture granular avalanche experiments are employed to evaluate the potential of bidispersity in enhancing runout. Structure-from-motion photogrammetry is used to assess centre of mass mobility. The findings suggest that the processes generating increased runout in small-scale avalanches are scale-dependent and not representative of rock/debris avalanche dynamics. In small-scale experiments, the granular mass is size-segregated with fine particles migrating to the base through kinetic sieving. At the base, they reduce frictional areas between coarse particles and the substrate, and encourage rolling. The reduced frictional energy dissipation increases kinetic energy conversion, and avalanche mobility. However, kinetic sieving does not occur in rock/debris avalanches due to a dissimilar granular flow regime. The proposition of this hypothesis overlooks that scale-dependent behaviours of natural events are omitted in small-scale experiments. At the small scale, a collisional regime enables the necessary agitation for kinetic sieving. However, rock/debris avalanches are unlikely to acquire a purely collisional regime, and rather propagate under a frictional regime, lacking widespread agitation. Therefore, bidispersity is unlikely to enhance the mobility of rock/debris avalanches by enabling more efficient shearing at their base.