Use of one-dimensional CNN for input data size reduction in LSTM for improved computational efficiency and accuracy in hourly rainfall-runoff modeling.

A deep learning architecture, denoted as CNNsLSTM, is proposed for hourly rainfall-runoff modeling in this study. The architecture involves a serial coupling of the one-dimensional convolutional neural network (1D-CNN) and the long short-term memory (LSTM) network. In the proposed framework, multiple layers of the CNN component process long-term hourly meteorological time series data, while the LSTM component handles short-term meteorological time series data and utilizes the extracted features from the 1D-CNN.

Generalizations of incompressible and compressible Navier-Stokes equations to fractional time and multi-fractional space.

This study develops the governing equations of unsteady multi-dimensional incompressible and compressible flow in fractional time and multi-fractional space. When their fractional powers in time and in multi-fractional space are specified to unit integer values, the developed fractional equations of continuity and momentum for incompressible and compressible fluid flow reduce to the classical Navier-Stokes equations. As such, these fractional governing equations for fluid flow may be interpreted as generalizations of the classical Navier-Stokes equations.

Capabilities of deep learning models on learning physical relationships: Case of rainfall-runoff modeling with LSTM.

This study investigates the relationships which deep learning methods can identify between the input and output data. As a case study, rainfall-runoff modeling in a snow-dominated watershed by means of a long short-term memory (LSTM) network is selected. Daily precipitation and mean air temperature were used as model input to estimate daily flow discharge.

Coupling hydroclimate-hydraulic-sedimentation models to estimate flood inundation and sediment transport during extreme flood events under a changing climate.

Extreme flood events are disastrous and can cause serious damages to society. Flood frequency obtained based on historical flow records may also be changing under future climate conditions. The associated flood inundation and environmental transport processes will also be affected.

Hourly-scale coastal sea level modeling in a changing climate using long short-term memory neural network.

In this study, a coastal sea level estimation model was developed at an hourly temporal scale using the long short-term memory (LSTM) network, which is a type of recurrent neural networks. The model incorporates the effects of various phenomena on the coastal sea level such as the gravitational attractions of the sun and the moon, seasonality, storm surges, and changing climate. The relative positions of the moon and the sun from the target location at each hour were utilized to reflect the gravitational attractions of the sun and the moon in the model simulation.

Self-similarity in fate and transport of contaminants in groundwater.

Similarity within non-linear geophysical processes under different space and time has been investigated in literature to understand and model the sophisticated nature of these processes. This study deals with the self-similarity of the governing processes of fate and transport of contaminants in groundwater, which include advection, dispersion, sorption, and degradation, either by chemical reaction or microbiological interaction. As such, self-similarity conditions of three-dimensional advective-dispersive-reactive transport (ADR) equation with various initial and boundary conditions are obtained by employing one-parameter Lie group of point scaling transformations.

Scaling Relations and Self-Similarity of 3-Dimensional Reynolds-Averaged Navier-Stokes Equations.

Scaling conditions to achieve self-similar solutions of 3-Dimensional (3D) Reynolds-Averaged Navier-Stokes Equations, as an initial and boundary value problem, are obtained by utilizing Lie Group of Point Scaling Transformations. By means of an open-source Navier-Stokes solver and the derived self-similarity conditions, we demonstrated self-similarity within the time variation of flow dynamics for a rigid-lid cavity problem under both up-scaled and down-scaled domains. The strength of the proposed approach lies in its ability to consider the underlying flow dynamics through not only from the governing equations under consideration but also from the initial and boundary conditions, hence allowing to obtain perfect self-similarity in different time and space scales.

Assessment of the effects of multiple extreme floods on flow and transport processes under competing flood protection and environmental management strategies.

Extreme floods are regarded as one of the most catastrophic natural hazards and can result in significant morphological changes induced by pronounced sediment erosion and deposition processes over the landscape. However, the effects of extreme floods of different return intervals on the floodplain and river channel morphological evolution with the associated sediment transport processes are not well explored. Furthermore, different basin management action plans, such as engineering structure modifications, may also greatly affect the flood inundation, sediment transport, solute transport and morphological processes within extreme flood events.

Self-similarity in incompressible Navier-Stokes equations.

The self-similarity conditions of the 3-dimensional (3D) incompressible Navier-Stokes equations are obtained by utilizing one-parameter Lie group of point scaling transformations. It is found that the scaling exponents of length dimensions in i = 1, 2, 3 coordinates in 3-dimensions are not arbitrary but equal for the self-similarity of 3D incompressible Navier-Stokes equations. It is also shown that the self-similarity in this particular flow process can be achieved in different time and space scales when the viscosity of the fluid is also scaled in addition to other flow variables.

Scaling and self-similarity in two-dimensional hydrodynamics.

The conditions under which depth-averaged two-dimensional (2D) hydrodynamic equations system as an initial-boundary value problem (IBVP) becomes self-similar are investigated by utilizing one-parameter Lie group of point scaling transformations. Self-similarity conditions due to the 2D k-ε turbulence model are also investigated. The self-similarity conditions for the depth-averaged 2D hydrodynamics are found for the flow variables including the time, the longitudinal length, the transverse length, the water depth, the flow velocities in x- and y-directions, the bed shear stresses in x- and y-directions, the bed shear velocity, the Manning's roughness coefficient, the kinematic viscosity of the fluid, the eddy viscosity, the turbulent kinetic energy, the turbulent dissipation, and the production and the source terms in the k-ε model.

Fish-protection devices at unscreened water diversions can reduce entrainment: evidence from behavioural laboratory investigations.

Diversion (i.e. extraction) of water from rivers and estuaries can potentially affect native wildlife populations if operation is not carefully managed.

Fusing inertial sensor data in an extended Kalman filter for 3D camera tracking.

In a setup where camera measurements are used to estimate 3D egomotion in an extended Kalman filter (EKF) framework, it is well-known that inertial sensors (i.e., accelerometers and gyroscopes) are especially useful when the camera undergoes fast motion.

Unscreened water-diversion pipes pose an entrainment risk to the threatened green sturgeon, Acipenser medirostris.

Over 3,300 unscreened agricultural water diversion pipes line the levees and riverbanks of the Sacramento River (California) watershed, where the threatened Southern Distinct Population Segment of green sturgeon, Acipenser medirostris, spawn. The number of sturgeon drawn into (entrained) and killed by these pipes is greatly unknown. We examined avoidance behaviors and entrainment susceptibility of juvenile green sturgeon (35±0.

Efficacy of a sensory deterrent and pipe modifications in decreasing entrainment of juvenile green sturgeon (Acipenser medirostris) at unscreened water diversions.

Water projects designed to extract fresh water for local urban, industrial and agricultural use throughout rivers and estuaries worldwide have contributed to the fragmentation and degradation of suitable habitat for native fishes. The number of water diversions located throughout the Sacramento-San Joaquin watershed in California's Central Valley exceeds 3300, and the majority of these are unscreened. Many anadromous fish species are susceptible to entrainment into these diversions, potentially impacting population numbers.