skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, November 14 until 2:00 AM ET on Saturday, November 15 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • An Attention‐Based Explainable Deep Learning Approach to Spatially Distributed Hydrologic Modeling of a Snow Dominated Mountainous Karst Watershed
Title: An Attention‐Based Explainable Deep Learning Approach to Spatially Distributed Hydrologic Modeling of a Snow Dominated Mountainous Karst Watershed
Abstract In many regions globally, snowmelt‐recharged mountainous karst aquifers serve as crucial sources for municipal and agricultural water supplies. In these watersheds, complex interplay of meteorological, topographical, and hydrogeological factors leads to intricate recharge‐discharge pathways. This study introduces a spatially distributed deep learning precipitation‐runoff model that combines Convolutional Long Short‐Term Memory (ConvLSTM) with a spatial attention mechanism. The effectiveness of the deep learning model was evaluated using data from the Logan River watershed and subwatersheds, a characteristically karst‐dominated hydrological system in northern Utah. Compared to the ConvLSTM baseline, the inclusion of a spatial attention mechanism improved performance for simulating discharge at the watershed outlet. Analysis of attention weights in the trained model unveiled distinct areas contributing the most to discharge under snowmelt and recession conditions. Furthermore, fine‐tuning the model at subwatershed scales provided insights into cross‐subwatershed subsurface connectivity. These findings align with results obtained from detailed hydrogeochemical tracer studies. Results highlight the potential of the proposed deep learning approach to unravel the complexities of karst aquifer systems, offering valuable insights for water resource management under future climate conditions. Furthermore, results suggest that the proposed explainable, spatially distributed, deep learning approach to hydrologic modeling holds promise for non‐karstic watersheds.  more » « less
Award ID(s):
2044051
PAR ID:
10556738
Author(s) / Creator(s):
 ;  ;  ;  ;  ;  ;  ;  ;  
Publisher / Repository:
DOI PREFIX: 10.1029
Date Published:
Journal Name:
Water Resources Research
Volume:
60
Issue:
11
ISSN:
0043-1397
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Water Resources Research)
    Abstract Snow dominated mountainous karst watersheds are the primary source of water supply in many areas in the western U.S. and worldwide. These watersheds are typically characterized by complex terrain, spatiotemporally varying snow accumulation and melt processes, and duality of flow and storage dynamics because of the juxtaposition of matrix (micropores and small fissures) and karst conduits. As a result, predicting streamflow from meteorological inputs has been challenging due to the inability of physically based or conceptual hydrologic models to represent these unique characteristics. We present a hybrid modeling approach that integrates a physically based, spatially distributed, snow model with a deep learning karst model. More specifically, the high‐resolution snow model captures spatiotemporal variability in snowmelt, and the deep learning model simulates the corresponding response of streamflow as influenced by complex surface and subsurface properties. The deep learning model is based on the Convolutional Long Short‐Term Memory (ConvLSTM) architecture capable of handling spatiotemporal recharge patterns and watershed storage dynamics. The hybrid modeling approach is tested on a watershed in northern Utah with seasonal snow cover and variably karstified carbonate bedrock. The hybrid models were able to simulate streamflow at the watershed outlet with high accuracy. The spatial and temporal recharge and discharge patterns learned by the ConvLSTM model were then examined and compared with known hydrogeologic information. Results suggest that ConvLSTM simulates streamflow with higher accuracy than reference models for the study area and provides insight into spatially influenced hydrologic responses that are unavailable within lumped modeling approaches. 
    more » « less
  2. ; ; ; (, Hydrological Processes)
    Abstract Streamflow generation in mountain watersheds is strongly influenced by snow accumulation and melt as well as groundwater connectivity. In mountainous regions with limestone and dolomite geology, bedrock formations can host karst aquifers, which play a significant role in snowmelt–discharge dynamics. However, mapping complex karst features and the resulting surface‐groundwater exchanges at large scales remains infeasible. In this study, timeseries analysis of continuous discharge and specific conductance measurements were combined with gridded snowmelt predictions to characterize seasonal streamflow response and evaluate dominant watershed controls across 12 monitoring sites in a karstified 554 km2watershed in northern Utah, USA. Immense surface water hydrologic variability across subcatchments, years and seasons was linked to geologic controls on groundwater dynamics. Unlike many mountain watersheds, the variability between subcatchments could not be well described by typical watershed properties, including elevation or surficial geology. To fill this gap, a conceptual framework was proposed to characterize subsurface controls on snowmelt–discharge dynamics in karst mountain watersheds in terms of conduit flow direction, aquifer storage capacity and connectivity. This framework requires only readily measured surface water and climatic data from nested monitoring sites and was applied to the study watershed to demonstrate its applicability for evaluating dominant controls and climate sensitivity. 
    more » « less
  3. (, Journal of Hydrology)
    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
  4. ; ; ; ; ; ; ; ; (, Geoscientific Model Development)
    Abstract. Watersheds are the fundamental Earth surface functioning units that connect the land to aquatic systems. Many watershed-scale models represent hydrological processes but not biogeochemical reactive transport processes. This has limited our capability to understand and predict solute export, water chemistry and quality, and Earth system response to changing climate and anthropogenic conditions. Here we present a recently developed BioRT-Flux-PIHM (BioRT hereafter) v1.0, a watershed-scale biogeochemical reactive transport model. The model augments the previously developed RT-Flux-PIHM that integrates land-surface interactions, surface hydrology, and abiotic geochemical reactions. It enables the simulation of (1) shallow and deep-water partitioning to represent surface runoff, shallow soil water, and deeper groundwater and of (2) biotic processes including plant uptake, soil respiration, and nutrient transformation. The reactive transport part of the code has been verified against the widely used reactive transport code CrunchTope. BioRT-Flux-PIHM v1.0 has recently been applied in multiple watersheds under diverse climate, vegetation, and geological conditions. This paper briefly introduces the governing equations and model structure with a focus on new aspects of the model. It also showcases one hydrology example that simulates shallow and deep-water interactions and two biogeochemical examples relevant to nitrate and dissolved organic carbon (DOC). These examples are illustrated in two simulation modes of complexity. One is the spatially lumped mode (i.e., two land cells connected by one river segment) that focuses on processes and average behavior of a watershed. Another is the spatially distributed mode (i.e., hundreds of cells) that includes details of topography, land cover, and soil properties. Whereas the spatially lumped mode represents averaged properties and processes and temporal variations, the spatially distributed mode can be used to understand the impacts of spatial structure and identify hot spots of biogeochemical reactions. The model can be used to mechanistically understand coupled hydrological and biogeochemical processes under gradients of climate, vegetation, geology, and land use conditions. 
    more » « less
  5. ; ; ; ; (, Journal of Hydrology)
    Karst groundwater is a critical freshwater resource for numerous regions worldwide. Monitoring and predicting karst spring discharge is essential for effective groundwater management and the preservation of karst ecosystems. However, the high heterogeneity and karstification pose significant challenges to physics-based models in providing robust predictions of karst spring discharge. In this study, an interpretable multi-step hybrid deep learning model called selective EEMD-TFT is proposed, which adaptively integrates temporal fusion transformers (TFT) with ensemble empirical mode decomposition (EEMD) for predicting karst spring discharge. The selective EEMD-TFT hybrid model leverages the strengths of both EEMD and TFT techniques to learn inherent patterns and temporal dynamics from nonlinear and nonstationary signals, eliminate redundant components, and emphasize useful characteristics of input variables, leading to the improvement of prediction performance and efficiency. It consists of two stages: in the first stage, the daily precipitation data is decomposed into multiple intrinsic mode functions using EEMD to extract valuable information from nonlinear and nonstationary signals. All decomposed components, temperature and categorical date features are then fed into the TFT model, which is an attention- based deep learning model that combines high-performance multi-horizon prediction and interpretable insights into temporal dynamics. The importance of input variables will be quantified and ranked. In the second stage, the decomposed precipitation components with high importance are selected to serve as the TFT model’s input features along with temperature and categorical date variables for the final prediction. Results indicate that the selective EEMD-TFT model outperforms other sequence-to-sequence deep learning models, such as LSTM and single TFT models, delivering reliable and robust prediction performance. Notably, it maintains more consistent prediction performance at longer forecast horizons compared to other sequence-to-sequence models, highlighting its capacity to learn complex patterns from the input data and efficiently extract valuable information for karst spring prediction. An interpretable analysis of the selective EEMD-TFT model is conducted to gain insights into relationships among various hydrological processes and analyze temporal patterns. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email