Rapid, Reproducible, and Robust Environmental Modeling for Decision Support: Worked Examples and Open-Source Software Tools

65.2K
views
73
authors
19
articles
Cover image for research topic "Rapid, Reproducible, and Robust Environmental Modeling for Decision Support: Worked Examples and Open-Source Software Tools"
Editors
4
Impact
Loading...
2,883 views
6 citations
Original Research
24 November 2022
Scalable deep learning for watershed model calibration
Maruti K. Mudunuru
3 more and 
Xingyuan Chen
Proposed scalable deep learning workflow for the SWAT model calibration: A pictorial description of the proposed DL methodology to estimate parameters and calibrate the SWAT model using observational discharge. Ensemble simulations generated by the SWAT model are used to train, validate, and test the CNN-enabled inverse models, as shown in the top figure (A). The observed streamflow is then provided as an input to the developed DL models to estimate site-specific parameters. These parameters are then used by the SWAT model to simulate discharge for comparison with observational data. The bottom figure (B) shows a scalable hyperparameter tuning approach to identify optimal CNN architectures using high-performance computing resources at NERSC. Each explored CNN architecture is trained on one/two CPU physical cores and its performance is estimated using validation loss and streamflow prediction metrics (e.g., R2-score, NSE, logNSE, KGE and its variants). From the explored space, top 50 CNNs are chosen for inverse modeling and analysis.

Watershed models such as the Soil and Water Assessment Tool (SWAT) consist of high-dimensional physical and empirical parameters. These parameters often need to be estimated/calibrated through inverse modeling to produce reliable predictions on hydrological fluxes and states. Existing parameter estimation methods can be time consuming, inefficient, and computationally expensive for high-dimensional problems. In this paper, we present an accurate and robust method to calibrate the SWAT model (i.e., 20 parameters) using scalable deep learning (DL). We developed inverse models based on convolutional neural networks (CNN) to assimilate observed streamflow data and estimate the SWAT model parameters. Scalable hyperparameter tuning is performed using high-performance computing resources to identify the top 50 optimal neural network architectures. We used ensemble SWAT simulations to train, validate, and test the CNN models. We estimated the parameters of the SWAT model using observed streamflow data and assessed the impact of measurement errors on SWAT model calibration. We tested and validated the proposed scalable DL methodology on the American River Watershed, located in the Pacific Northwest-based Yakima River basin. Our results show that the CNN-based calibration is better than two popular parameter estimation methods (i.e., the generalized likelihood uncertainty estimation [GLUE] and the dynamically dimensioned search [DDS], which is a global optimization algorithm). For the set of parameters that are sensitive to the observations, our proposed method yields narrower ranges than the GLUE method but broader ranges than values produced using the DDS method within the sampling range even under high relative observational errors. The SWAT model calibration performance using the CNNs, GLUE, and DDS methods are compared using R2 and a set of efficiency metrics, including Nash-Sutcliffe, logarithmic Nash-Sutcliffe, Kling-Gupta, modified Kling-Gupta, and non-parametric Kling-Gupta scores, computed on the observed and simulated watershed responses. The best CNN-based calibrated set has scores of 0.71, 0.75, 0.85, 0.85, 0.86, and 0.91. The best DDS-based calibrated set has scores of 0.62, 0.69, 0.8, 0.77, 0.79, and 0.82. The best GLUE-based calibrated set has scores of 0.56, 0.58, 0.71, 0.7, 0.71, and 0.8. The scores above show that the CNN-based calibration leads to more accurate low and high streamflow predictions than the GLUE and DDS sets. Our research demonstrates that the proposed method has high potential to improve our current practice in calibrating large-scale integrated hydrologic models.

3,734 views
8 citations
Technology and Code
30 September 2022

In an age of both big data and increasing strain on water resources, sound management decisions often rely on numerical models. Numerical models provide a physics-based framework for assimilating and making sense of information that by itself only provides a limited description of the hydrologic system. Often, numerical models are the best option for quantifying even intuitively obvious connections between human activities and water resource impacts. However, despite many recent advances in model data assimilation and uncertainty quantification, the process of constructing numerical models remains laborious, expensive, and opaque, often precluding their use in decision making. Modflow-setup aims to provide rapid and consistent construction of MODFLOW groundwater models through robust and repeatable automation. Common model construction tasks are distilled in an open-source, online code base that is tested and extensible through collaborative version control. Input to Modflow-setup consists of a single configuration file that summarizes the workflow for building a model, including source data, construction options, and output packages. Source data providing model structure and parameter information including shapefiles, rasters, NetCDF files, tables, and other (geolocated) sources to MODFLOW models are read in and mapped to the model discretization, using Flopy and other general open-source scientific Python libraries. In a few minutes, an external array-based MODFLOW model amenable to parameter estimation and uncertainty quantification is produced. This paper describes the core functionality of Modflow-setup, including a worked example of a MODFLOW 6 model for evaluating pumping impacts to a lake in central Wisconsin, United States.

6,915 views
10 citations
Technology and Code
30 September 2022
HydroBench: Jupyter supported reproducible hydrological model benchmarking and diagnostic tool
Edom Moges
5 more and 
Laurel G. Larsen
Article Cover Image

Evaluating whether hydrological models are right for the right reasons demands reproducible model benchmarking and diagnostics that evaluate not just statistical predictive model performance but also internal processes. Such model benchmarking and diagnostic efforts will benefit from standardized methods and ready-to-use toolkits. Using the Jupyter platform, this work presents HydroBench, a model-agnostic benchmarking tool consisting of three sets of metrics: 1) common statistical predictive measures, 2) hydrological signature-based process metrics, including a new time-linked flow duration curve and 3) information-theoretic diagnostics that measure the flow of information among model variables. As a test case, HydroBench was applied to compare two model products (calibrated and uncalibrated) of the National Hydrologic Model - Precipitation Runoff Modeling System (NHM-PRMS) at the Cedar River watershed, WA, United States. Although the uncalibrated model has the highest predictive performance, particularly for high flows, the signature-based diagnostics showed that the model overestimates low flows and poorly represents the recession processes. Elucidating why low flows may have been overestimated, the information-theoretic diagnostics indicated a higher flow of information from precipitation to snowmelt to streamflow in the uncalibrated model compared to the calibrated model, where information flowed more directly from precipitation to streamflow. This test case demonstrated the capability of HydroBench in process diagnostics and model predictive and functional performance evaluations, along with their tradeoffs. Having such a model benchmarking tool not only provides modelers with a comprehensive model evaluation system but also provides an open-source tool that can further be developed by the hydrological community.

3,880 views
5 citations
4,187 views
8 citations
Stresses included in the time series model for observation well B39F0579 (Filter 5).
4,325 views
11 citations
Schematic representation of an ArchPy stratigraphic pile (B) given a geological concept (A); interp. method, interpolation method; GRF, Gaussian random functions; DEM, digital elevation model; Prop method, property simulation method; MPS, multiple-points statistics; SIS, sequential indicator simulation; TPG, truncated pluri-Gaussians; HO, homogeneous; K, hydraulic conductivity; FFT, fast Fourier transform; SGS, sequential Gaussian simulation.
4,505 views
13 citations
Location and main hydrogeological features of the Vale do Lobo aquifer system. The locations of groundwater abstraction wells, piezometers, and contoured average measured hydraulic heads during 2020 are also depicted.
4,464 views
9 citations
Open for submission
Frontiers Logo

Frontiers in Environmental Science

Innovative Support of Remote Sensing Data for Monitoring Peatlands and Wetlands and Their Condition
Edited by Christian Bignami, Susan Page, Gerardo López Saldaña
Deadline
30 September 2025
Submit a paper
Recommended Research Topics
Frontiers Logo

Frontiers in Earth Science

Stochastic Modeling in Hydrogeology
Edited by J. Jaime Gómez-Hernández, Liangping Li, Teng Xu, Andrés Alcolea
39.4K
views
51
authors
11
articles
Frontiers Logo

Frontiers in Environmental Science

Future Climate Scenarios: Regional Climate Modelling and Data Analysis
Edited by Xander Wang, Yurui Fan, Shan Zhao, Yulei Xie, Hans Von Storch
87.8K
views
114
authors
23
articles
Frontiers Logo

Frontiers in Earth Science

High-Performance Computing in Solid Earth Geohazards: Progresses, Achievements and Challenges for a Safer World
Edited by Alice-Agnes Gabriel, Marta Pienkowska, Manuela Volpe, Sara Barsotti
27.7K
views
52
authors
10
articles
Frontiers Logo

Frontiers in Environmental Science

Application of Bayesian Modeling in Environmental Management
Edited by Marie Anne Eurie Forio, Peter Goethals, Elena Moltchanova
18.5K
views
24
authors
6
articles
Frontiers Logo

Frontiers in Environmental Science

Climate Change Information for Regional Impact and Risk Assessment
Edited by Benjamin Lamptey, Rupakumar Kolli, Mark Amo-Boateng
61.9K
views
39
authors
10
articles