SEARCH · Engineering Papers

Results for “data base for model validation”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Virtual sensing of wind turbine hub loads and drivetrain fatigue damage, Virtuelle Sensoren für die Messung von Hauptwellenlasten und Ermüdungsschäden im Antriebstrang von Windenergieanlagen

Abstract: This paper presents a Digital Twin for virtual sensing of wind turbine aerodynamic hub loads, as well as monitoring the accumulated fatigue damage and remaining useful life in drivetrain bearings based on measurements of the Supervisory Control and Data Acquisition (SCADA) and the drivetrain condition monitoring system (CMS). The aerodynamic load estimation is realized with data-driven regression models, while the estimation of local bearing loads and damage is conducted with physics-based, analytical models. Field measurements of the DOE 1.5 research turbine are used for model training and validation. The results show low errors of 6.4% and 1.1% in the predicted damage at the main and the generator side high-speed bearing respectively. Zusammenfassung: In diesem Aufsatz wird ein digitaler Zwilling für Windenergieanlagen vorgestellt, welcher die virtuelle Erfassung der Hauptwellenlasten und die Zustandsüberwachung von Ermüdungschäden und der verbleibende Nutzungsdauer der Antriebsstranglager ermöglicht. Der digital Zwilling nutzt Messdaten des Supervisory Control and Data Acquisition (SCADA) Systems und des Zustandsüberwachungssystems des Antriebsstranges (CMS). Die Berechnung der Hauptwellenlasten ist mit datenbasierten Regressionsmodellen umgesetzt, während die Berechnung der Lagerkräfte und der Ermüdungsschaden mit physikbasierten Modelle durchgeführt wird. Für die Modellentwicklung und -validierung werden Feldmessdaten der DOE 1.5MW Turbine eingesetzt. Die Abweichungen in den Ermüdungsschäden am Hauptwellenlager und am Generatorwellenlager betragen lediglich 6,4% beziehungsweise 1,1%.

17 WIND ENERGY↗

DOE OSTI2025

Development of a conduction-based model for analyzing frozen startup of alkali-metal heat pipes

One key area of interest in heat pipe modeling/simulation is to analyze the startup behavior of the liquid-metal heat pipes (LMHPs) from a frozen state. This so-called ‘frozen startup’ process involves a complex set of nonlinear mass and heat transport phenomena, including phase transitions from solid to liquid and vapor, multiphase interactions, microporous wick flow, and compressible vapor dynamics. The complexity of these processes makes it challenging to simulate LMHP’s frozen startup using conventional numerical methods or commercial computational fluid dynamics (CFD) software. This paper presents a simplified conduction-based modeling approach that can provide practical insights into the entire LMHP frozen startup process, while alleviating the challenges of modeling its complex physics. The theoretical foundation and physical assumptions of the proposed model are based solely on heat-conduction equation, allowing for a more tractable simulation without sacrificing essential physical accuracy. The proposed model was implemented in a commercial CFD software, and its prediction was compared with the experimental data obtained from sodium heat-pipe startup experiments. The comparison highlights the proposed model's ability to capture the transient thermal behavior of LMHP during frozen startup. This study not only validates the conduction-based frozen startup modeling method but also shows its potential as a practical and efficient tool for understanding the startup performance of the LMHP systems.

Microreactor↗

DOE OSTI2021

Development of a Turbulent Liquid Spray Atomization Model for Diesel Engine Simulations (Final Technical Report)

This project addresses the systematic lack of predictive capabilities by spray models within engine CFD codes. We develop a new modeling approach to predict the breakup of diesel sprays based on recent literature showing that liquid turbulence plays a fundamental role in spray atomization. A new body of quantitative validation data is also developed as a critical element of the project, leveraging the joint capabilities of Georgia Tech’s high-pressure continuous-flow spray chamber and Argonne National Lab’s near-nozzle x-ray diagnostics at the Advanced Photon Source. This project contributes spatially-resolved measurements of drop size distribution within well-characterized diesel injectors, Spray A and D, from the Engine Combustion Network (ECN) to the engine combustion community for the first time. Utilizing this new body of measurements, we validate and demonstrate a new spray model for diesel sprays, termed the KH-Faeth model, that predicts global and local spray characteristic more accurately than the widely adopted and employed KH model. Predicted drop size distributions are seen to predict measured drops sizes both quantitatively and predictively, with accurate response in droplet size distributions over a wide range of ambient density, injection pressure, and injector nozzle size (Spray A and D) without model tuning. The KH-Faeth model can reduce error in the predicted centerline droplet size profile by up to 80% for ECN Spray D simulations when compared to use of the widely employed KH model.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

Automated bubble analysis of high-speed subcooled flow boiling images using U-net transfer learning and global optical flow

Capturing and analyzing the bubble dynamics is crucial to improving the understanding of boiling heat transfer mechanisms and predicting boiling heat transfer coefficient and boiling crisis. High speed video (HSV) imaging has been used for decades towards this end. Still, there is no universal approach to quantitatively analyze bubble dynamics from HSV images. In this study, we propose a data-driven post-processing approach to segment, track, and identify wall-attached vapor bubbles from HSV images of the boiling process in subcooled flow conditions. Firstly, we employ a transfer learning framework with a U-Net-based convolution neural network (CNN) architecture to detect and segment bubbles in HSV images of diverse contrast and surface texture using very little data (e.g., 10 images) for training. Then, we evaluate the trained CNN model with 100 ground-truth images, and the validation results show that the model accuracy and precision in detecting the optical footprint of bubbles are higher than 90%. Finally, we suggest a criterion to identify a condensing bubble based on the divergence of the bubble displacement, which is calculated from sequential segmented bubble images using a global optical flow code. Using this combination of machine learning and optical flow, we can identify nucleation sites and track the growth of bubbles nucleating at each site to quantify nucleation site density, nucleation frequency, and other fundamental boiling parameters. The proposed system is validated using results obtained on a special heater, which enables both infrared (IR) thermometry and HSV imaging on a metallic surface. We compare the fundamental boiling parameters obtained by the two different diagnostics. The results show good agreement. In conclusion, the difference between the measurements of nucleation site density, averaged nucleation frequency, and averaged growth time performed with the two techniques is always within ± 20% and mostly ± 10% of the values measured with IR thermometry.

42 ENGINEERING↗

DOE OSTI2021

AGGREGATE: dAta-driven modelinG preservinG contRollable dEr for outaGe mAnagemenT and rEsiliency (Final Report)

The AGGREGATE project team successfully developed and validated various modules for outage management. Brief summaries of each module are provided to showcase their strength for outage management and restoration for a distribution system with a high penetration of connected distribution energy resources (DERs). In recent years, inverter-based DERs have been widely deployed in distribution system. A most of behind-the-meter (BTM) solar power generation is not visible to the utility. The data-driven DER and load estimation modules are using machine learning (ML) and artificial intelligence (AI) to manage this issue, which provides an opportunity for distribution system operators (DSOs) to operate systems and make decisions in real-time for a distribution system with a high penetration of DERs deployed. Also, the estimated DER and true load can be further leveraged in network aggregation and cold-load pick up estimation for reducing the computing complexity and providing for fast restoration. After load demand and DER power generations have been estimated, the information will support topology and state estimation (SE). The topology estimation module demonstrated the viability of mixed integer linear programming (MILP) formulation to estimate the most likely operational radial topology and outage sections using power flow measurements, historical/estimated load and DERs data and smart meter ping measurements. Formulation includes continuous (power flow, load and DERs data) and binary measurements (smart meter ping measurements) in a single formulation. Errors in continuous data and binary data are modeled as normal distribution and Bernoulli distribution, respectively. In the future distribution grid, the power injection from controllable DERs will be essential for efficient and resilient grid operation. However, determining the optimal DER injections and restoration actions is dependent on knowledge of the system states. State estimation (SE), already the cornerstone of transmission energy management systems, will become commonplace in distribution management systems as more measurements become available from deployment of automated metering infrastructure (AMI). Observability analysis is the first step in SE, as it determines the sufficiency of the available measurements for accurately estimating the current system states. A new type of pseudo-measurement called a Correlational Measurement (CM) is introduced in this module, to enhance the observability of the system to enable more accurate SE. CMs encapsulate knowledge of correlation between demand patterns for similar classes of loads as well as injection patterns for same-technology renewable DERs. During grid contingency scenarios, DERs have been traditionally disconnected, without any fault ride-through capabilities. However, with new regulations and better technology, it is feasible for these resources to contribute to the grid’s restoration after an adverse event and hence enhance resilience. The controllability module proposes a two-step restoration scheme for the power system restoration process by leveraging additional degrees of freedom in power electronics interfaced DERs for mitigating voltage problems. In a resilience mode without the utility system, the distribution grid relies on DERs to serve critical load. In such a severe event with multiple faults on the distribution feeders, actuation of various protective devices (PDs) divides the distribution system into electrical islands. The undetected actuated PDs due to fault current contributions from DERs can delay the restoration process, thereby reducing the system resilience. The Advanced Outage Management (AOM) and the Advanced Feeder Restoration (AFR) modules developed in this project provide improved system resilience with multiple DERs. AOM identifies the faulted sections and actuated PDs in a distribution system with DERs by incorporating smart meter data. The most credible outage scenario including fault locations, PD actuations, and fault indicator (FI) failures is identified by a set of binary integer linear programming incorporating hypotheses. The AFR module serves to restore a distribution system with available energy resources taking into consideration the availability of utility sources and DERs. By partitioning the system into islands, critical load will be served with the available generation resources within islands based on the solution of a MILP. When the utility systems become available, the optimal path will be determined by a spanning tree search algorithm that reconnects these islands back to substations and restores the remaining load. The transmission and distribution (T&D) co-simulation module was used to validate the effect of a control action performed on the distribution side assets as it propagates to the transmission side. This ensures that the control action performed results in a feasible operating point on both the transmission and the distribution system. In addition to validation, the team used the T&D co-simulation module to demonstrate how distribution system assets can be used to mitigate issues on the transmission system. Specifically, the team demonstrated that appropriate switching operations on the distribution side can alleviate the line overload condition on the transmission side without causing new operational constraint violations.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2024

Simulation of Particulate Transport for Delivery of Solid Amendments into the Subsurface: FY24 Status Report

For particulate-based amendments to be viable for field-scale remediation at the Hanford Site (e.g., 200 DV-1 Operable Unit), particles need to be delivered a sufficient radial distance from an injection well and retained at concentrations high enough for effective treatment. An accurate description of the particle radius of influence (ROI) is critical for developing an overall remediation strategy. However, field-scale particle simulations are currently limited due to insufficient simulation capabilities and a lack of experimental data to validate and parameterize particle transport models. To help build toward field-scale deployment, this fiscal year (FY) we have (1) developed a pre screening tool to estimate particle transport, (2) implemented particle transport models within PFLOTRAN, and (3) conducted preliminary estimations of particle ROI. While field-scale numerical simulations will ultimately be necessary before remedy design and field implementation, we have developed a pre-screening tool that offers valuable estimations of expected particle injectability and ROI in a 1-D system. The advantage of the tool is that it does not require extensive laboratory experiments and instead makes predictions based solely on routine laboratory measurements. This tool can assist in down-selection and decision-making by identifying which particle amendment systems are worth pursuing in future laboratory experiments, such as 1-D column tests and beyond. With any system, scaling up from the lab to the field presents challenges. Currently, there is no field data available for model calibration or validation. However, the theoretical particle models being developed herein are the best tools available to guide progress toward field deployment. To help bridge this gap and verify model predictions, larger-scale lab experiments are being proposed. To advance simulation capabilities, six particle transport models are being integrated into the reactive transport simulator PFLOTRAN. These include colloid filtration theory (CFT) and five additional particle transport models (M1-M5). Each model, from M1 to M5, progressively incorporates additional particle transport and retention processes. Ultimately, the simplest model capable of accurately describing 1-D column data will be selected and parameterized. During FY24, the CFT and M1 model have been fully implemented within PFLOTRAN. Using an existing 1 D column experiment, the two currently implemented particle transport models (CFT and M1), and associated parameters, were fit to this experiment. While simpler model formulations are helpful for estimations, these formulations could not fully describe particle transport and retention behavior in the previous 1-D column experiment. Thus, additional complexities will need to be considered, which will be accounted for in the M2-M5 model formulations. Additionally, because a viscous, shear thinning fluid was required to keep particles in suspension, considerations for flow will also need to also be accounted for. Therefore, a new immiscible two-phase flow mode is currently being implemented in PFLOTRAN. With some modifications, this new flow module could also support simulation of non-Newtonian liquid amendments, foams, and emulsions. We also estimated the expected ROI of solid amendments using 1-D simulations. The average predicted ROI was approximately 15 ft for micron-sized zero valent iron (mZVI) suspended in xanthan gum (XG). Using the pre screening tool and ROI estimates, additional amendment-delivery laboratory characterization and experiments are proposed. The results from additional experiments can be used to validate and parametrize particulate transport model formulations, which will ultimately provide predictive capabilities for field amendment-delivery systems.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2024

Estimates of Southern Hemispheric Gravity Wave Momentum Fluxes across Observations, Reanalyses, and Kilometer-Scale Numerical Weather Prediction Model

Abstract Gravity waves (GWs) are among the key drivers of the meridional overturning circulation in the mesosphere and upper stratosphere. Their representation in climate models suffers from insufficient resolution and limited observational constraints on their parameterizations. This obscures assessments of middle atmospheric circulation changes in a changing climate. This study presents a comprehensive analysis of stratospheric GW activity above and downstream of the Andes from 1 to 15 August 2019, with special focus on GW representation ranging from an unprecedented kilometer-scale global forecast model (1.4 km ECMWF IFS), ground-based Rayleigh lidar (CORAL) observations, modern reanalysis (ERA5), to a coarse-resolution climate model (EMAC). Resolved vertical flux of zonal GW momentum (GWMF) is found to be stronger by a factor of at least 2–2.5 in IFS compared to ERA5. Compared to resolved GWMF in IFS, parameterizations in ERA5 and EMAC continue to inaccurately generate excessive GWMF poleward of 60°S, yielding prominent differences between resolved and parameterized GWMFs. A like-to-like validation of GW profiles in IFS and ERA5 reveals similar wave structures. Still, even at ∼1 km resolution, the resolved waves in IFS are weaker than those observed by lidar. Further, GWMF estimates across datasets reveal that temperature-based proxies, based on midfrequency approximations for linear GWs, overestimate GWMF due to simplifications and uncertainties in GW wavelength estimation from data. Overall, the analysis provides GWMF benchmarks for parameterization validation and calls for three-dimensional GW parameterizations, better upper-boundary treatment, and vertical resolution increases commensurate with increases in horizontal resolution in models, for a more realistic GW analysis. Significance Statement Gravity wave–induced momentum forcing forms a key component of the middle atmospheric circulation. However, complete knowledge of gravity waves, their atmospheric effects, and their long-term trends are obscured due to limited global observations, and the inability of current climate models to fully resolve them. This study combines a kilometer-scale forecast model, modern reanalysis, and a coarse-resolution climate model to first compare the resolved and parameterized momentum fluxes by gravity waves generated over the Andes, and then evaluate the fluxes using a state-of-the-art ground-based Rayleigh lidar. Our analysis reveals shortcomings in current model parameterizations of gravity waves in the middle atmosphere and highlights the sensitivity of the estimated flux to the formulation used.

Meteorology & Atmospheric Sciences↗

DOE OSTI2024

Dark Energy Survey Year 3 results: Simulation-based cosmological inference with wavelet harmonics, scattering transforms, and moments of weak lensing mass maps. Validation on simulations

Beyond-two-point statistics contain additional information on cosmological as well as astrophysical and observational (systematics) parameters. In this methodology paper we provide an end-to-end simulationbased analysis of a set of Gaussian and non-Gaussian weak lensing statistics using detailed mock catalogs of the Dark Energy Survey (DES). Here, we implement: 1) second and third moments; 2) wavelet phase harmonics (WPH); 3) the scattering transform (ST). Our analysis is fully based on simulations, it spans a space of seven $νw$CDM cosmological parameters, and it forward models the most relevant sources of systematics of the data (masks, noise variations, clustering of the sources, intrinsic alignments, and shear and redshift calibration). We implement a neural network compression of the summary statistics, and we estimate the parameter posteriors using a likelihood-free-inference approach. We validate the pipeline extensively, and we find that WPH exhibits the strongest performance when combined with second moments, followed by ST, and then by third moments. The combination of all the different statistics further enhances constraints with respect to second moments, up to 25 percent, 15 percent, and 90 percent for S 8 , Ω m , and the figure-of-merit FoM S8;Ωm , respectively. We further find that non-Gaussian statistics improve constraints on w and on the amplitude of intrinsic alignment with respect to second moments constraints. The methodological advances presented here are suitable for application to Stage IV surveys from Euclid, Rubin-LSST, and Roman with additional validation on mock catalogs for each survey. In a companion paper we present an application to DES Year 3 data.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2023

Residuals-based distributionally robust optimization with covariate information

We consider data-driven approaches that integrate a machine learning prediction model within distributionally robust optimization (DRO) given limited joint observations of uncertain parameters and covariates. Our framework is flexible in the sense that it can accommodate a variety of regression setups and DRO ambiguity sets. We investigate asymptotic and finite sample properties of solutions obtained using Wasserstein, sample robust optimization, and phi-divergence-based ambiguity sets within our DRO formulations, and explore cross-validation approaches for sizing these ambiguity sets. Through numerical experiments, we validate our theoretical results, study the effectiveness of our approaches for sizing ambiguity sets, and illustrate the benefits of our DRO formulations in the limited data regime even when the prediction model is misspecified.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Residuals-based distributionally robust optimization with covariate information

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Crowdsourcing biocuration: The Community Assessment of Community Annotation with Ontologies (CACAO)

Experimental data about gene functions curated from the primary literature have enormous value for research scientists in understanding biology. Using the Gene Ontology (GO), manual curation by experts has provided an important resource for studying gene function, especially within model organisms. Unprecedented expansion of the scientific literature and validation of the predicted proteins have increased both data value and the challenges of keeping pace. Capturing literature-based functional annotations is limited by the ability of biocurators to handle the massive and rapidly growing scientific literature. Within the community-oriented wiki framework for GO annotation called the Gene Ontology Normal Usage Tracking System (GONUTS), we describe an approach to expand biocuration through crowdsourcing with undergraduates. This multiplies the number of high-quality annotations in international databases, enriches our coverage of the literature on normal gene function, and pushes the field in new directions. From an intercollegiate competition judged by experienced biocurators, Community Assessment of Community Annotation with Ontologies (CACAO), we have contributed nearly 5,000 literature-based annotations. Many of those annotations are to organisms not currently well-represented within GO. Over a 10-year history, our community contributors have spurred changes to the ontology not traditionally covered by professional biocurators. The CACAO principle of relying on community members to participate in and shape the future of biocuration in GO is a powerful and scalable model used to promote the scientific enterprise. It also provides undergraduate students with a unique and enriching introduction to critical reading of primary literature and acquisition of marketable skills.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2020

Battery Equivalent Model for Residential HVAC

Flexible loads, especially heating, ventilation, and air-conditioning (HVAC) systems can be used to provide a battery-like service to the power grid by varying their demand up and down over a baseline. Recent work has reported that the round-trip efficiency for providing grid services with HVAC systems can be close to 1. Inspired by this promising result, in this work, we rigorously develop a battery equivalent model (BEM) for residential HVAC systems. Relying only on typically available data, the proposed BEM will bridge the observability and controllability gaps between utility companies and customers. The proposed BEM will enable the utility companies to manage the flexible HVAC devices as easy as charging/discharging the conventional energy storage devices. Validated physics-based models are used to train the BEM, whose prediction accuracy is illustrated through a simulation study.

Dong, Jin↗

DOE OSTI2024

Design by analysis rules for ASME Section III, Division 5, Class B components

The current rules for elevated temperature ASME Section III, Division 5, Class B components, other than piping, were basically adapted from the Design-by-Rule approach for Section VIII, Division 1 vessels. A goal of the proposed new rules is to explicitly account for the design life and cyclic service while recognizing the less-rigorous requirements commensurate with lesser safety consideration. Further goals are to maximize the use of modern computational technology, for example finite element analysis in conjunction with reference stress concepts, and to avoid the need for stress classification. This paper summarizes the work done to address these issues. A summary of the design-by-analysis for primary loads, strain limit evaluation, and creep-fatigue damage assessment is presented. The proposed design-by-analysis creep-fatigue damage calculation approach uses a new elastic follow-up-based Isochronous Stress Strain Curve stress relaxation procedure. A set of sample problems are selected to validate the proposed design-by-analysis rules for creep-fatigue damage assessment. The proposed Class B rules are evaluated against the Class A elastic design rules and the experimental data obtained from a family of a simplified model test-based key-feature test results. The proposed Class B creep-fatigue damage assessment methodology yields conservative design cycles estimates compared to the experimental results.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Computational Experiment Design for Operations Model Simulation

Computer simulations that demonstrate the value of novel approaches are crucial to developing more flexible and robust power systems operations with high penetrations of renewable energy at multiple geographic and temporal scales. However, optimization-based simulations that depend on forecast data often face challenges in evaluating performance, reproducing results, and testing under realistic simulation scenarios. In this paper, we develop scientific computing best-practices for the validation and reproduction of power systems operational models. We then employ two case studies to demonstrate the proposed validation and reproduction framework.

MATHEMATICS AND COMPUTING,POWER TRANSMISSION AND D↗

DOE OSTI2021

A Modeling Tool to Analyze the Performance of Industrial Cooling Towers

Energy efficiency and energy savings have become an important factor as industries look for ways to save energy and minimize their energy consumption while reducing their carbon footprint. Cooling towers are utilized significantly in industries for either serving chillers or process cooling. Depending on the size of the cooling tower, it can use a surprising amount of energy and water, which is why it is crucial to make sure that the facility has optimized their cooling tower.A modeling tool has been developed to perform a thorough analysis of a cooling tower and its various operations to ensure that the facility has optimized its cooling tower. This model analyzes an annual base case in comparison with the revised case of a cooling tower operation. This modeling tool simulates 8,760 hourly calculations for fan power for various fan controls, water consumption, and pumping energy consumption and demand based on the user’s location and its corresponding Typical Meteorological Year 3 (TMY3) weather data. This model is capable to simulate up to five cooling tower cells as one large tower utilizing one pump or parallel pumping. The successful validated cooling tower model should assist industry to save energy at their facility through their cooling tower, whether they use it for process cooling or heating, ventilation and air conditioning (HVAC) applications. The entering/leaving water temperatures based on a monthly operating schedule or a wet-bulb temperature schedule will be used as inputs, and the model can calculate savings in energy for various conditions including variable-frequency drive (VFD) on the fan/pump, drift eliminators, number of cycles of concentration, reduced water flow rate, etc.

Hooper, Josh↗

DOE OSTI2026

HDSense: An efficient method for ranking observable sensitivity

Identifying which observables most effectively constrain model parameters can be computationally prohibitive when considering full likelihoods of many correlated observables. This is especially important for, e.g., hadronization models, where high precision is required to interpret the results of collider experiments. We introduce the High-Dimensional Sensitivity (HDSense) score, a computationally efficient metric for ranking observable sets using only one-dimensional histograms. Derived by profiling over unknown correlations in the Fisher information framework, the score balances total information content against redundancy between observables. We apply HDSense to rank a set observables in terms of their constraining power with respect to five parameters of the Lund string model of hadronization implemented in Pythia using simulated leptonic collider events at the $Z$ pole. Validation against machine-learning--based full-likelihood approximations demonstrates that HDSense successfully identifies near-optimal observable subsets. The framework naturally handles data from multiple experiments with different acceptances and incorporates detector effects. While demonstrated on hadronization models, the methodology applies broadly to generic parameter estimation problems where correlations are unknown or difficult to model.

Assi, Benoît [Cincinnati U.] (ORCID:00000003092433↗

DOE OSTI2022

Scalable deep learning for watershed model calibration

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 R 2 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.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

PyOECP: A flexible open-source software library for estimating and modeling the complex permittivity based on the open-ended coaxial probe (OECP) technique

Here, we present PyOECP, a Python-based flexible open-source software for estimating and modeling the complex permittivity obtained from the open-ended coaxial probe (OECP) technique. The transformation of the measured reflection coefficient to complex permittivity is performed based on three different methods. The software library contains the dielectric spectra of common reference liquids, which can be used to transform the reflection coefficient into the dielectric spectra. Several Python routines that are commonly employed (e.g., SciPy and NumPy) in the field of science and engineering are required only so that the users can alter the software structure depending on their needs. The modeling algorithm exploits the Markov Chain Monte Carlo method for the data regression. The discrete relaxation models can be built by a proper combination of well-known relaxation models. In addition to these models, electrode polarization, a typical measurement artifact for interpreting dielectric spectra, can be incorporated into the modeling algorithm. A continuous relaxation model, which solves the Fredholm integral equation of the first kind (a mathematically ill-posed problem), is also included. This open-source software enables users to freely adjust the physical parameters to obtain physical insight into their materials under test and will be consistently updated for more accurate measurement and interpretation of dielectric spectra in an automated manner. This work describes the theoretical and mathematical background of the software, lays out the workflow, and validates the software functionality based on both synthetic and empirical data included in the software.

97 MATHEMATICS AND COMPUTING↗