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 253 records · Page 14

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Enabling Load Following Capability in the Transatomic Power MSR

This project is dedicated towards designing a fuel processing system that enables liquid-fueled molten salt reactors (MSR) to load follow by removing the dissolved xenon in the fuel salt. As one of the Gen-IV nuclear reactor concepts, the molten salt reactor receives increasing development interests in the recent years. One distinguishing feature of the liquid-fueled molten salt reactor is its improved ability to operate in a load-following mode by including the unique online fission product removal system. Load-following means that the reactor changes its power output based on the demand on the grid. Most of the current operating nuclear reactors have limited load-following ability and operate as the base load on the grid. Due to the rapid increase of solar energy, the requirement on load-following capacity is significantly increased because of the varying power output of the solar panels, yet the traditional load-following capacity is expected to decrease as the decarbonization of the grid continues. Therefore, the ability to perform load-following operation for the nuclear reactors will greatly enhance the resilience of the grid and make nuclear energy more economically competitive. This load-following feature is included in many commercial molten salt reactor designs, such as the designs by Transatomic Power, Terrestrial Energy, and Flibe Energy. Unfortunately, detailed analysis of the fuel processing system for commercial scale MSRs is still lacking, as well as how the fuel processing quantitively impacts the load-following operation. Moreover, experimental data for many of the underlying physics of fuel processing is limited. This project aims to pave the way for the fuel processing technology to advance to the commercial stage by performing combined experimental and simulation research. During the project period, four interconnected aspects of the development of the fuel processing system in liquid-fueled molten salt reactors are investigated. These aspects are the simulation and analysis of the fission product removal system, the fuel cycle simulation, the coupled reactor neutronics and thermal hydraulics transient simulation, and the gaseous fission product removal experiment. Multiphase CFD simulations are performed for components of the processing systems, and simplified air-water experiments are carried out to provide validation data. It is concluded that the CFD simulation can satisfactorily predict the system level performance of the components, and engineering models are constructed based on this success. Fuel cycle analysis is performed for two representative MSR design, the MSBR and the Transatomic Power MSR. Open-source code SaltProc is developed to incorporate the unique fuel processing system of the MSRs. It is concluded that the removal of xenon is essential for load-following operation in thermal spectrum MSR and Molten Salt Breeder Reactor. For the Transatomic Power MSR, the xenon poisoning effect is negligible due to its relatively fast neutron spectrum, though the overall fuel cycle economics still benefits from the removal of xenon. Coupled reactor neutronics and thermal hydraulics transient simulation is performed specifically for the Transatomic Power MSR. It is concluded that the reactor core design could perform power ramping fast enough to satisfy load-following operation. Combining the findings from each aspect, it is concluded that the load-following operation of a thermal neutron MSR is dependent upon the removal of xenon, which could be achieved for a commercial sized reactor using continuous inert gas sparging in a separate system with reasonable dimensions.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2024

Transitioning from Simulation to Reality: Applying Chatter Detection Models to Real-World Machining Data

Chatter, a self-excited vibration phenomenon, is a critical challenge in high-speed machining operations, affecting tool life, product surface quality, and overall process efficiency. While machine learning models trained on simulated data have shown promise in detecting chatter, their real-world applicability remains uncertain due to discrepancies between simulated and actual machining environments. The primary goal of this study is to bridge the gap between simulation-based machine learning models and real-world applications by developing and validating a Random Forest-based chatter detection system. This research focuses on improving manufacturing efficiency through reliable chatter detection by integrating Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL). The study applies a Random Forest classification model trained on over 140,000 simulated machining datasets, incorporating techniques like Operational Modal Analysis (OMA), Receptance Coupling Substructure Analysis (RCSA), and Transfer Learning (TL) to adapt the model for real-world operational data. The model is validated against 1600 real-world machining datasets, achieving an accuracy of 86.1%, with strong precision and recall scores. The results demonstrate the model’s robustness and potential for practical implementation in industrial settings, highlighting challenges such as sensor noise and variability in machining conditions. This work advances the use of predictive analytics in machining processes, offering a data-driven solution to improve manufacturing efficiency through more reliable chatter detection.

42 ENGINEERING↗

DOE OSTI2024

RELAP5-3D HTGR Validation Work at Idaho National Laboratory

Prismatic block-type high-temperature gas-cooled reactors (HTGRs) were built in the United States decades ago, and now advanced reactor vendors are seeking to deploy them again for a variety of applications. Deploying these reactors requires modelling and simulation tools that have been validated against conditions representative of the HTGR application. Idaho National Laboratory (INL) is leading the execution an of HTGR thermal hydraulics benchmark to accelerate the validation of thermal hydraulics modelling and simulation tools for these applications. That benchmark is based on a facility called the High Temperature Test Facility (HTTF). This work provides an overview of work conducted at INL over the last 2 years to validate RELAP5-3D against data from HTTF. This presentation shows results from multiple RELAP5-3D models and an HTTF experiment to assess the impact of certain modelling assumptions on results. The contents of this talk sit on the cutting edge of RELAP5-3D validation for HTGR analysis.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2023

Reaction mechanism for atmospheric pressure plasma treatment of cysteine in solution

Mechanisms for the cold atmospheric plasma (CAP) treatment of cells in solution are needed for more optimum design of plasma devices for wound healing, cancer treatment, and bacterial inactivation. However, the complexity of organic molecules on cell membranes makes understanding mechanisms that result in modifications (i.e. oxidation) of such compounds difficult. As a surrogate to these systems, a reaction mechanism for the oxidation of cysteine in CAP activated water was developed and implemented in a 0-dimensional (plug-flow) global plasma chemistry model with the capability of addressing plasma-liquid interactions. Reaction rate coefficients for organic reactions in water were estimated based on available data in the literature or by analogy to gas-phase reactions. The mechanism was validated by comparison to experimental mass-spectrometry data for COST-jets sustained in He/O 2 , He/H 2 O and He/N 2 /O 2 mixtures treating cysteine in water. Results from the model were used to determine the consequences of changing COST-jet operating parameters, such as distance from the substrate and inlet gas composition, on cysteine oxidation product formation. Results indicate that operating parameters can be adjusted to select for desired cysteine oxidation products, including nitrosylated products.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2026

Atomistic Simulation of Glasses and Amorphous Materials: Challenges and Opportunities for the Next Decade

Atomistic simulations have become indispensable tools for understanding glass structure, dynamics, and properties, yet persistent challenges limit their predictive power. This perspective examines three interconnected issues, namely glass formation procedures, interatomic potential development, and machine learning applications, which emerged from the 5th International Workshop on Challenges of Atomistic Simulations of Glasses and Amorphous Materials. We identify convergent community priorities for (i) standardized validation protocols, (ii) curated benchmark datasets with complete metadata, and (iii) open repositories for glasses. A systematic was forward is provided by a hierarchical validation framework for assessing the structural fidelity, property prediction, and behavioral realism of simulation techniques. Looking ahead, transformative advances are promised by the fusion of classical techniques with machine learning based approaches, for instance, by integrating swap Monte Carlo with machine-learning (ML) potentials, leveraging foundation models through transfer learning, and finetuning ML potentials with experimental data. Progress depends on the community committing to validated models, reproducible protocols, and sustained data sharing.

Krishnan, N. M. Anoop↗

DOE OSTI2025

Physics-informed machine learning for building performance simulation-A review of a nascent field

Building performance simulation (BPS) is critical for understanding building dynamics and behavior, analyzing the performance of the built environment, optimizing energy efficiency, improving demand flexibility, and enhancing building resilience. However, conducting BPS is not trivial. Traditional BPS relies on accurate building energy models, which are primarily physics-based and heavily dependent on detailed building information, expert knowledge, and case-by-case model calibrations, significantly limiting their scalability. With the development of sensing technology and the increased availability of data, there is growing attention and interest in data-driven BPS. However, purely data-driven models often suffer from limited generalization ability and a lack of physical consistency, resulting in poor performance in real-world applications. To address these limitations, recent studies have begun integrating physics priors into data-driven models, a methodology known as physics-informed machine learning (PIML). PIML is an emerging field where its definitions, methodologies, evaluation criteria, application scenarios, and future directions remain open. To bridge those gaps, this study systematically reviews the state-of-the-art PIML for BPS, offering a comprehensive definition of PIML and comparing it to traditional BPS approaches regarding data requirements, modeling effort, performance, and computational cost. We also summarize the commonly used methodologies, validation approaches, application domains, available data sources, open-source packages, and testbeds. In addition, this study provides a general guideline for selecting appropriate PIML models based on BPS applications. Finally, this study identifies key challenges and outlines future research directions, providing a solid foundation and valuable insights to advance R&D of PIML in BPS.

Jiang, Zixin↗

DOE OSTI2025

MOOSE-based Tritium Migration Analysis Program, Version 8 (TMAP8) for advanced open-source tritium transport and fuel cycle modeling

Tritium management is critical for the safety, sustainability, and economics of fusion energy systems, and advanced and reliable modeling tools help accelerate the development of tritium technologies. This paper presents the Tritium Migration Analysis Program, Version 8 (TMAP8), an open-source, MOOSE-based application developed to provide state-of-the-art tritium transport and fuel cycle modeling capabilities. TMAP8 aims to expand the capabilities of previous versions (i.e., TMAP4 and TMAP7) by leveraging modern computational techniques, ensuring high software quality assurance standards (key to building trust), and enabling multispecies, multiscale, and multiphysics simulations for integrated tritium transport modeling in complex geometries. This paper outlines TMAP8’s scope and rigorous development practices, emphasizing its transparency, accessibility, modularity, and reliability. We present the current suite of verification and validation cases based on those from TMAP4, demonstrating TMAP8’s accuracy and reliability against analytical solutions and experimental data. Additionally, the paper showcases TMAP8’s integrated fuel cycle modeling capabilities, highlighting its applicability at various scales and levels. The TMAP8 code and documentation are openly available, promoting collaborative development and widespread adoption within the fusion community. Future work will soon expand TMAP8’s verification and validation suite to include those from TMAP7 and other recent experimental studies for validation.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

Intelligent Experiments Through Real-time AI: Fast Data Processing and Autonomous Detector Control for sPHENIX and Future EIC Detectors (Final Report)

The overall vision of this project was to integrate real-time artificial intelligence (AI) directly into the data acquisition and detector-control systems of nuclear physics experiments, including both fast online event selection and an autonomous detector-control feedback loop. The work carried out under the award focused on the fast online event-selection half of that vision: the efficient recording of low-momentum heavy-flavor (HF) hadron decays in proton-proton collisions at the sPHENIX experiment at the Relativistic Heavy Ion Collider (RHIC)—an observable that requires fast tracking and topological trigger selection not previously demonstrated at RHIC, and that is essential for QCD studies at future facilities such as the Electron-Ion Collider (EIC). The autonomous detector-control (GPU-based feedback) component named in the project title remained a design concept and was not implemented under this award. The Massachusetts Institute of Technology (MIT) group led the offline simulation and data processing needed to train the machine-learning (ML) models, the translation of trained models to Field-Programmable Gate Array (FPGA) firmware using the hls4ml framework, and the physics validation of heavy-flavor reconstruction. Over the award period, the team developed and hardware-tested the principal components of an AI-based heavy-flavor trigger on simulated and recorded sPHENIX tracker data: a software Bipartite Graph Attention Network (BiGAT) trigger model reaching > 95% signal efficiency at 99% background rejection; an FPGA-native hit clusterizer matching the offline clustering; smaller networks synthesized to FPGA within the required sub-10 µs latency; and an assembled decoder–clusterizer–inference firmware chain exercised on the FELIX readout board. A complete, fully integrated hardware demonstrator was not finished within the award period. This report documents the project goals, the MIT group’s contributions, the technical accomplishments, and the outlook toward applications at the future EIC ePIC detector.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2021

Effect of Soil Properties and Input Motion on Site Amplification Using Validated Nonlinear Soil Model

Here, three-dimensional (3-D) nonlinear site response analyses are conducted using finite element models of actual soil profiles from ten nuclear power plant (NPP) sites in the United States to investigate the effects of soil properties and input motions on site amplification. The modeling approach developed in this study combines several novel elements, such as 3-D analysis (including vertical motions), nonlinear inelastic behavior of soil (strain-dependent shear modulus reduction and hysteretic damping), formulation of nonreflecting boundary conditions at the base, and generation of realistic outcrop ground motions for specific sites. All these elements of the modeling approach are first validated using actual data from five earthquakes at three downhole array stations recorded in the Kiban-Kyoshin network (KiK-net), Japan. The same approach is then used to develop site models of ten NPP sites in the United States and corresponding ground motions that are spectrally matched to the site hazard spectra. Eight sets of three-component input motions are used in the study and are categorized on the basis of presence or absence of a near-field pulse in the seed ground motions used for spectral matching. It is found that all sites retain a definite site amplification function regardless of the input motion, provided that the seed motion is spectrally matched to the site hazard spectra. The magnitude of site amplification and frequencies at which they occur depend upon soil properties, particularly the shear wave velocity profile and the constitutive relationship (strain-dependent shear modulus reduction and hysteretic damping) of soil. Amplification of spectral acceleration in the vertical direction (up-down motion) is found to be just as much as, if not more than, the amplification in the horizontal direction. Peak shear strain is found to be about 20% larger for near-field motions compared to far-field motions whereas maximum horizontal site amplification for far-field motions is found to be consistently larger than that of near-field motions, even though the differences between the two remain within the scatter resulting from individual ground motions.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2024

Cosmological constraints from density-split clustering in the BOSS CMASS galaxy sample

We present a clustering analysis of the BOSS DR12 CMASS galaxy sample, combining measurements of the galaxy two-point correlation function and density-split clustering down to a scale of $1 \, h^{-1}\, \text{Mpc}$. Our theoretical framework is based on emulators trained on high-fidelity mock galaxy catalogues that forward model the cosmological dependence of the clustering statistics within an extended-ΛCDM framework, including redshift-space and Alcock–Paczynski distortions. Our base-ΛCDM analysis finds ω cdm = 0.1201 ± 0.0022, σ 8 = 0.792 ± 0.034, and n s = 0.970 ± 0.018, corresponding to fσ 8 = 0.462 ± 0.020 at z ≈ 0.525, which is in agreement with Planck 2018 predictions and various clustering studies in the literature. We test single-parameter extensions to base-ΛCDM, varying the running of the spectral index, the dark energy equation of state, and the density of mass-less relic neutrinos, finding no compelling evidence for deviations from the base model. We model the galaxy–halo connection using a halo occupation distribution framework, finding signatures of environment-based assembly bias in the data. We validate our pipeline against mock catalogues that match the clustering and selection properties of CMASS, showing that we can recover unbiased cosmological constraints even with a volume 84 times larger than the one used in this study.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Dark energy survey: Modeling strategy for multiprobe cluster cosmology and validation for the full six-year dataset

Here, we introduce an updated To&Krause2021 model for joint analyses of cluster abundances and large-scale two-point correlations of weak lensing and galaxy and cluster clustering (termed CL+3×2 pt analysis) and validate that this model meets the systematic accuracy requirements of analyses with the statistical precision of the final Dark Energy Survey (DES) Year 6 (Y6) dataset. The validation program consists of two distinct approaches, (i) identification of modeling and parametrization choices and impact studies using simulated analyses with each possible model misspecification and (ii) end-to-end validation using mock catalogs from customized Cardinal simulations that incorporate realistic galaxy populations and DES-Y6-specific galaxy and cluster selection and photometric redshift modeling, which are the key observational systematics. In combination, these validation tests indicate that the model presented here meets the accuracy requirements of DES-Y6 for CL+3×2 pt based on a large list of tests for known systematics. In addition, we also validate that the model is sufficient for several other data combinations: the CL+GC subset of this data vector (excluding galaxy–galaxy lensing and cosmic shear two-point statistics) and the CL+3×2 pt+BAO+SN (combination of CL+3×2 pt with the previously published Y6 DES baryonic acoustic oscillation and Y5 supernovae data).

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2025

Dark Energy Survey: Modeling strategy for multiprobe cluster cosmology and validation for the Full Six-year Dataset

We introduce an updated To&Krause2021 model for joint analyses of cluster abundances and large-scale two-point correlations of weak lensing and galaxy and cluster clustering (termed CL+3x2pt analysis) and validate that this model meets the systematic accuracy requirements of analyses with the statistical precision of the final Dark Energy Survey (DES) Year 6 (Y6) dataset. The validation program consists of two distinct approaches, (1) identification of modeling and parameterization choices and impact studies using simulated analyses with each possible model misspecification (2) end-to-end validation using mock catalogs from customized Cardinal simulations that incorporate realistic galaxy populations and DES-Y6-specific galaxy and cluster selection and photometric redshift modeling, which are the key observational systematics. In combination, these validation tests indicate that the model presented here meets the accuracy requirements of DES-Y6 for CL+3x2pt based on a large list of tests for known systematics. In addition, we also validate that the model is sufficient for several other data combinations: the CL+GC subset of this data vector (excluding galaxy--galaxy lensing and cosmic shear two-point statistics) and the CL+3x2pt+BAO+SN (combination of CL+3x2pt with the previously published Y6 DES baryonic acoustic oscillation and Y5 supernovae data).

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2023

Fusion of Multiple Models for Improving Gross Primary Production Estimation With Eddy Covariance Data Based on Machine Learning

Abstract Terrestrial gross primary production (GPP) represents the magnitude of CO 2 uptake through vegetation photosynthesis, and is a key variable for carbon cycles between the biosphere and atmosphere. Light use efficiency (LUE) models have been widely used to estimate GPP for its physiological mechanisms and availability of data acquisition and implementation, yet each individual GPP model has exhibited large uncertainties due to input errors and model structure, and further studies of systematic validation, comparison, and fusion of those models with eddy covariance (EC) site data across diverse ecosystem types are still needed in order to further improve GPP estimation. We here compared and fused five GPP models (VPM, EC‐LUE, GOL‐PEM, CHJ, and C‐Fix) across eight ecosystems based on FLUXNET2015 data set using the ensemble methods of Bayesian Model Averaging (BMA), Support Vector Machine (SVM), and Random Forest (RF) separately. Our results showed that for individual models, EC‐LUE gave a better performance to capture interannual variability of GPP than other models, followed by VPM and GLO‐PEM, while CHJ and C‐Fix were more limited in their estimation performance. We found RF and SVM were superior to BMA on merging individual models at various plant functional types (PFTs) and at the scale of individual sites. On the basis of individual models, the fusion methods of BMA, SVM, and RF were examined by a five‐fold cross validation for each ecosystem type, and each method successfully improved the average accuracy of estimation by 8%, 18%, and 19%, respectively.

Environmental Sciences & Ecology↗

DOE OSTI2022

Development of QSAR models to predict blood-brain barrier permeability

Assessing drug permeability across the blood-brain barrier (BBB) is important when evaluating the abuse potential of new pharmaceuticals as well as developing novel therapeutics that target central nervous system disorders. One of the gold-standard in vivo methods for determining BBB permeability is rodent log BB; however, like most in vivo methods, it is time-consuming and expensive. In the present study, two statistical-based quantitative structure-activity relationship (QSAR) models were developed to predict BBB permeability of drugs based on their chemical structure. The in vivo BBB permeability data were harvested for 921 compounds from publicly available literature, non-proprietary drug approval packages, and University of Washington’s Drug Interaction Database. The cross-validation performance statistics for the BBB models ranged from 82 to 85% in sensitivity and 80–83% in negative predictivity. Additionally, the performance of newly developed models was assessed using an external validation set comprised of 83 chemicals. Overall, performance of individual models ranged from 70 to 75% in sensitivity, 70–72% in negative predictivity, and 78–86% in coverage. The predictive performance was further improved to 93% in coverage by combining predictions across the two software programs. These new models can be rapidly deployed to predict blood brain barrier permeability of pharmaceutical candidates and reduce the use of experimental animals.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

A Semi-Detailed Pyrolytic Gas-Phase Kinetic Model for the Volatiles of Polyethylene Thermal Degradation

This work presents a semi-detailed kinetic model to address the pyrolytic gas-phase reactivity of volatiles formed during thermal degradation of polyethylene (PE). The model builds on a validated multi-step condensed-phase model and employs validated lumping approaches. Short-chain compounds are modelled with high detail, while long-chain ones are described by surrogate species representative of diesel-cuts (NC16H32) and waxes (NC30H60). The reactivity of short chains is described through the comprehensive CRECK kinetic model, updated to align C5-C7 olefins based on recent literature experimental data. Due to the lack of experimental data for longer olefins, their reactivity is modeled by analogy to the shorter ones, ensuring an asymptotic behavior with increasing carbon numbers. The semi-detailed model is validated through experimental data on PE pyrolysis, assuming an instantaneous mixing of the inert inlet flow with released volatiles, followed by a segregated plug-flow behavior. Validation across different reactor setups confirms the model’s capability to predict detailed product distributions. Despite minor discrepancies, the proposed model effectively captures experimental trends. Further work will address modelling the reactivity in oxygen-containing environments.

kinetics↗

DOE OSTI2025

A Semi-Detailed Pyrolytic Gas-Phase Kinetic Model for the Volatiles of Polyethylene Thermal Degradation

kinetics↗

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↗