An official website of the United States government
Karst aquifers are important groundwater resources that supply drinking water for approximately 25 % of the world’s population. Their complex hydrogeological structures, dual-flow regimes, and highly heterogeneous flow pose significant challenges for accurate hydrodynamic modeling and sustainable management. Traditional modeling approaches often struggle to capture the intricate spatial dependencies and multi-scale temporal patterns inherent in karst systems, particularly the interactions between rapid conduit flow and slower matrix flow. This study proposes a novel multi-scale dynamic graph attention network integrated with long short-term memory model (GAT-LSTM) to innovatively learn and integrate spatial and temporal dependencies in karst systems for forecasting spring discharge. The model introduces several innovative components: (1) graph-based neural networks with dynamic edge-weighting mechanism are proposed to learn and update spatial dependencies based on both geographic distances and learned hydrological relationships, (2) a multi-head attention mechanism is adopted to capture different aspects of spatial relationships simultaneously, and (3) a hierarchical temporal architecture is incorporated to process hydrological temporal patterns at both monthly and seasonal scales with an adaptive fusion mechanism for final results. These features enable the proposed model to effectively account for the dual-flow dynamics in karst systems, where rapid conduit flow and slower matrix flow coexist. The newly proposed model is applied to the Barton Springs of the Edwards Aquifer in Texas. The results demonstrate that it can obtain more accurate and robust prediction performance across various time steps compared to traditional temporal and spatial deep learning approaches. Based on the multi-scale GAT-LSTM model, a comprehensive ablation analysis and permutation feature important are conducted to analyze the relative contribution of various input variables on the final prediction. These findings highlight the intricate nature of karst systems and demonstrate that effective spring discharge prediction requires comprehensive monitoring networks encompassing both primary recharge contributors and supplementary hydrological features that may serve as valuable indicators of system-wide conditions.
more »
« less
Deciphering the connection between upstream obstacles, wake structures, and root signals in seal whisker array sensing using interpretable neural networks
This study presents a novel method that combines a computational fluid-structure interaction model with an interpretable deep-learning model to explore the fundamental mechanisms of seal whisker sensing. By establishing connections between crucial signal patterns, flow characteristics, and attributes of upstream obstacles, the method has the potential to enhance our understanding of the intricate sensing mechanisms. The effectiveness of the method is demonstrated through its accurate prediction of the location and orientation of a circular plate placed in front of seal whisker arrays. The model also generates temporal and spatial importance values of the signals, enabling the identification of significant temporal-spatial signal patterns crucial for the network’s predictions. These signal patterns are further correlated with flow structures, allowing for the identification of important flow features relevant for accurate prediction. The study provides insights into seal whiskers’ perception of complex underwater environments, inspiring advancements in underwater sensing technologies.
more »
« less
- Award ID(s):
- 2327204
- PAR ID:
- 10488904
- Editor(s):
- Zheng, X.
- Publisher / Repository:
- Frontiers
- Date Published:
- Journal Name:
- Frontiers in Robotics and AI
- Volume:
- 10
- ISSN:
- 2296-9144
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This work investigates the response of forces from fluid flow around seal whisker inspired cylinder geometry at swept back angles. The unique, undulated surface of seal whiskers has been shown to reduce drag and oscillating lift in comparison to smooth cylinders of equivalent dimensions. As seals swim through the water, their whisker orientation with respect to the freestream is constantly changing due to body position, but also the ability to manipulate the position of their whiskers while sensing. Though the effects of orientation and geometry parameters such as varied angle of attack, changes to undulation wavelength, amplitude, and aspect ratio have been investigated in previous literature, there is little research dedicated to characterizing the response of undulated cylinder geometry at sweep angles. In this paper, direct numerical simulation of incompressible flow over a highly resolved whisker surface is used to simulate flow structures and forces over whisker-inspired cylinders at a range of sweep angles from 0 to 60 degrees. It is observed that the decrease in forces in comparison to circular cylinders is still present at all swept angles tested. Root-mean-squared lift coefficient displays a 51.9 to 93.8% reduction, whereas drag displays a 12.9 to 39.1% reduction. When compared to forces on a streamlined elliptical cylinder, sweep angles of 0 to 30 degrees result in a force reduction advantage for the undulated cylinder geometry. Beyond this range at sweep angles of 45 and 60, drag and lift coefficients closely mirror those of the streamlined ellipse and undulated geometry offers no improvement.more » « less
-
Abstract The spanwise undulated cylinder geometry inspired by seal whiskers has been shown to alter shedding frequency and reduce fluid forces significantly compared to smooth cylindrical geometry. Prior research has parameterized the whisker-inspired geometry and demonstrated the relevance of geometric variations on force reduction properties. Among the geometric parameters, undulation wavelength was identified as a significant contributor to forcing changes. To analyze the effect of undulation wavelength, a thorough investigation isolating changes in wavelength is performed to expand upon previous research that parameterized whisker-inspired geometry and the relevance of geometric variations on the force reduction properties. A set of five whisker-inspired models of varying wavelength are computationally simulated at a Reynolds number of 250 and compared with an equivalent aspect ratio smooth elliptical cylinder. Above a critical non-dimensional value, the undulation wavelength reduces the amplitude and frequency of vortex shedding accompanied by a reduction in oscillating lift force. Frequency shedding is tied to the creation of wavelength-dependent vortex structures which vary across the whisker span. These vortices produce distinct shedding modes in which the frequency and phase of downstream structures interact to decrease the oscillating lift forces on the whisker model with particular effectiveness around the wavelength values typically found in nature. The culmination of these location-based modes produces a complex and spanwise-dependent lift frequency spectra at those wavelengths exhibiting maximum force reduction. Understanding the mechanisms of unsteady force reduction and the relationship between undulation wavelength and frequency spectra is critical for the application of this geometry to vibration tuning and passive flow control for vortex-induced vibration (VIV) reduction.more » « less
-
null (Ed.)Ocean ecosystems have spatiotemporal variability and dynamic complexity that require a long-term deployment of an autonomous underwater vehicle for data collection. A new generation of long-range autonomous underwater vehicles (LRAUVs), such as the Slocum glider and Tethys-class AUV, has emerged with high endurance, long-range, and energy-aware capabilities. These new vehicles provide an effective solution to study different oceanic phenomena across multiple spatial and temporal scales. For these vehicles, the ocean environment has forces and moments from changing water currents which are generally on the order of magnitude of the operational vehicle velocity. Therefore, it is not practical to generate a simple trajectory from an initial location to a goal location in an uncertain ocean, as the vehicle can deviate significantly from the prescribed trajectory due to disturbances resulted from water currents. Since state estimation remains challenging in underwater conditions, feedback planning must incorporate state uncertainty that can be framed into a stochastic energy-aware path planning problem. This article presents an energy-aware feedback planning method for an LRAUV utilizing its kinematic model in an underwater environment under motion and sensor uncertainties. Our method uses ocean dynamics from a predictive ocean model to understand the water flow pattern and introduces a goal-constrained belief space to make the feedback plan synthesis computationally tractable. Energy-aware feedback plans for different water current layers are synthesized through sampling and ocean dynamics. The synthesized feedback plans provide strategies for the vehicle that drive it from an environment’s initial location toward the goal location. We validate our method through extensive simulations involving the Tethys vehicle’s kinematic model and incorporating actual ocean model prediction data.more » « less
-
In this paper, we present a Long Short-Term Memory (LSTM)-based Kalman Filter for data assimilation of a 2D spatio-temporally varying depth-averaged ocean flow field for underwater glider path planning. The data source to the filter combines both the Eulerian flow map with the Lagrangian mobile sensor data stream. The depth-averaged flow is modeled as two components, the tidal and the non-tidal flow component. The tidal flow is modeled with ADCIRC (Advanced Three-Dimensional Circulation Model), while the non-tidal flow field is modeled by a set of spatial basis functions and their time series coefficients. The spatial basis functions are the principal modes derived by performing EOF (Empirical Orthogonal Functions) analysis on the historical surface flow field measured by high frequency radar (HFR), and the temporal coefficients of the spatial basis function are modeled by an LSTM neural network. The Kalman Filter is performed to combine the dynamics derived from the LSTM network, and the observations from the glider flow estimation data. Simulation results demonstrate that the proposed data assimilation method can give flow field prediction of reasonable accuracy.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3389/frobt.2023.1231715
