Subjective decisions in hydrologic model calibration can have drastic impacts on our understanding of basin processes and simulated fluxes. Here, we present a multicase approach to determine three pillars an appropriate hydrological configuration, i.e. data length, spin-up period, spatial resolution, using spatially distributed meso-scale (mHM) together with dynamically dimensioned search (DDS)...

Abstract Performing inference of Convolutional Neural Networks (CNNs) on Internet Things (IoT) edge devices ensures both privacy input data and possible run time reductions when compared to a cloud solution. As most are memory- compute-constrained, they cannot store execute complex CNNs. Partitioning distributing layer information across multiple reduce the amount computation each device presen...

The event-based leaderless and leader-following consensus problems of stochastic multi-agent systems (MAS) with state-dependent noises are investigated in the manuscript. fully event-triggered control mechanism combinational measurements is established, under which can achieve almost surely, respectively. With help adaptive strategy, designed schemes do not rely on minimal nonzero eigenvalue La...

Packet routing is one of the fundamental problems in computer networks which a router determines next-hop each packet queue to get it as quickly possible its destination. Reinforcement learning (RL) has been introduced design autonomous policies with local information stochastic arrival and service. However, curse dimensionality RL prohibits more comprehensive representation dynamic network sta...