Dynamic connectivity in a fluvial network for identifying hotspots of geomorphic change

Dynamical processes occurring on the hierarchical branching structure of a river network tend to heterogeneously distribute fluxes on the network, often concentrating them into clusters, i.e., places of excess flux accumulation. Here, we put forward the hypothesis that places in the network predisposed (due to process dynamics and network topology) to accumulate excess sediment over a considerable river reach and over a considerable period of time reflect locations where a local imbalance in sediment flux may occur thereby highlighting a susceptibility to potential fluvial geomorphic change. We develop a dynamic connectivity framework which uses the river network structure and a simplified Lagrangian transport model to trace fluxes through the network and integrate emergent clusters through a cluster persistence index (CPI). The framework was applied to sand transport in the Greater Blue Earth River Network in the Minnesota River Basin. Three hotspots of fluvial geomorphic change were defined as locations where high rates of channel migration were observed and places of high CPI coincided with two of these hotspots of possibly sediment-driven change. The third hotspot was not identified by high CPI, but instead is believed to be a hotspot of streamflow-driven change based on additional information and the fact that high bed shear stress coincided with this hotspot. The proposed network-based dynamic connectivity framework has the potential to place dynamical processes occurring at small scales into a network context to understand how reach-scale changes cascade into network-scale effects, useful for informing the large-scale consequences of local management actions.