Towards Interpretable Physical-Conceptual Catchment-Scale Hydrological Modeling using the Mass-Conserving-Perceptron
- URL: http://arxiv.org/abs/2401.14521v3
- Date: Wed, 22 May 2024 17:58:41 GMT
- Title: Towards Interpretable Physical-Conceptual Catchment-Scale Hydrological Modeling using the Mass-Conserving-Perceptron
- Authors: Yuan-Heng Wang, Hoshin V. Gupta,
- Abstract summary: We investigate the applicability of machine learning technologies to the development of catchment-scale hydrologic models.
The goal is to discover a minimal representation that represents the dominant processes that can explain the input-state-output behaviors of a given catchment.
We find that a HyMod-like architecture with three cell-states and two major flow pathways achieves such a representation at our study location.
- Score: 1.1510009152620668
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We investigate the applicability of machine learning technologies to the development of parsimonious, interpretable, catchment-scale hydrologic models using directed-graph architectures based on the mass-conserving perceptron (MCP) as the fundamental computational unit. Here, we focus on architectural complexity (depth) at a single location, rather than universal applicability (breadth) across large samples of catchments. The goal is to discover a minimal representation (numbers of cell-states and flow paths) that represents the dominant processes that can explain the input-state-output behaviors of a given catchment, with particular emphasis given to simulating the full range (high, medium, and low) of flow dynamics. We find that a HyMod-like architecture with three cell-states and two major flow pathways achieves such a representation at our study location, but that the additional incorporation of an input-bypass mechanism significantly improves the timing and shape of the hydrograph, while the inclusion of bi-directional groundwater mass exchanges significantly enhances the simulation of baseflow. Overall, our results demonstrate the importance of using multiple diagnostic metrics for model evaluation, while highlighting the need for designing training metrics that are better suited to extracting information across the full range of flow dynamics. Further, they set the stage for interpretable regional-scale MCP-based hydrological modeling (using large sample data) by using neural architecture search to determine appropriate minimal representations for catchments in different hydroclimatic regimes.
Related papers
- SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics [20.706469085872516]
Generalization is a key requirement for a general-purpose fluid simulator, which should adapt to different topologies, resolutions, or thermodynamic ranges.
We propose SURF, a benchmark designed to test the $textitgeneralization$ of learned graph-based fluid simulators.
We empirically demonstrate the applicability of SURF by thoroughly investigating the two state-of-the-art graph-based models.
arXiv Detail & Related papers (2023-10-30T22:12:35Z) - Optimization of a Hydrodynamic Computational Reservoir through Evolution [58.720142291102135]
We interface with a model of a hydrodynamic system, under development by a startup, as a computational reservoir.
We optimized the readout times and how inputs are mapped to the wave amplitude or frequency using an evolutionary search algorithm.
Applying evolutionary methods to this reservoir system substantially improved separability on an XNOR task, in comparison to implementations with hand-selected parameters.
arXiv Detail & Related papers (2023-04-20T19:15:02Z) - Machine Learning model for gas-liquid interface reconstruction in CFD
numerical simulations [59.84561168501493]
The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids.
A major bottleneck of the VoF method is the interface reconstruction step due to its high computational cost and low accuracy on unstructured grids.
We propose a machine learning enhanced VoF method based on Graph Neural Networks (GNN) to accelerate the interface reconstruction on general unstructured meshes.
arXiv Detail & Related papers (2022-07-12T17:07:46Z) - Learning Large-scale Subsurface Simulations with a Hybrid Graph Network
Simulator [57.57321628587564]
We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows.
HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure.
Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
arXiv Detail & Related papers (2022-06-15T17:29:57Z) - Extending Process Discovery with Model Complexity Optimization and
Cyclic States Identification: Application to Healthcare Processes [62.997667081978825]
The paper presents an approach to process mining providing semi-automatic support to model optimization.
A model simplification approach is proposed, which essentially abstracts the raw model at the desired granularity.
We aim to demonstrate the capabilities of the technological solution using three datasets from different applications in the healthcare domain.
arXiv Detail & Related papers (2022-06-10T16:20:59Z) - Attention U-Net as a surrogate model for groundwater prediction [13.029731605492252]
This study proposes a physics-based convolutional encoder-decoder neural network as a surrogate model to calculate the response of the groundwater system.
Holding strong promise in cross-domain mappings, encoder-decoder networks are applicable for learning complex input-output mappings of physical systems.
arXiv Detail & Related papers (2022-04-09T17:46:24Z) - Differentiable, learnable, regionalized process-based models with
physical outputs can approach state-of-the-art hydrologic prediction accuracy [1.181206257787103]
We show that differentiable, learnable, process-based models (called delta models here) can approach the performance level of LSTM for the intensively-observed variable (streamflow) with regionalized parameterization.
We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework.
arXiv Detail & Related papers (2022-03-28T15:06:53Z) - Transfer learning to improve streamflow forecasts in data sparse regions [0.0]
We study the methodology behind Transfer Learning (TL) through fine-tuning and parameter transferring for better generalization performance of streamflow prediction in data-sparse regions.
We propose a standard recurrent neural network in the form of Long Short-Term Memory (LSTM) to fit on a sufficiently large source domain dataset.
We present a methodology to implement transfer learning approaches for hydrologic applications by separating the spatial and temporal components of the model and training the model to generalize.
arXiv Detail & Related papers (2021-12-06T14:52:53Z) - Machine learning for rapid discovery of laminar flow channel wall
modifications that enhance heat transfer [56.34005280792013]
We present a combination of accurate numerical simulations of arbitrary, flat, and non-flat channels and machine learning models predicting drag coefficient and Stanton number.
We show that convolutional neural networks (CNN) can accurately predict the target properties at a fraction of the time of numerical simulations.
arXiv Detail & Related papers (2021-01-19T16:14:02Z) - Physics Guided Machine Learning Methods for Hydrology [21.410993515618895]
We propose an LSTM based deep learning architecture that is coupled with SWAT (Soil and Water Assessment Tool)
The efficacy of the approach is being analyzed on several small catchments located in the South Branch of the Root River Watershed in southeast Minnesota.
arXiv Detail & Related papers (2020-12-02T19:17:19Z) - Towards an Automatic Analysis of CHO-K1 Suspension Growth in
Microfluidic Single-cell Cultivation [63.94623495501023]
We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data.
Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
arXiv Detail & Related papers (2020-10-20T08:36:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.