Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “cost model”

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.

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

At least 631 records · Page 35
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Shedding light on the economic costs of long-duration power outages: A review of resilience assessment methods and strategies

Here this paper provides a literature review of methods and modeling techniques to estimate the cost of power system outages, along with the value of outage mitigation or system resilience. Regulators, policymakers, and infrastructure owners have a growing need to understand the methods for estimating the benefits of resilience improvements of electric infrastructure against natural and man-made disasters. There is a broad literature that estimates the cost of short-duration outages and a small but developing literature on estimating the cost of long-duration outages. This article reviews the models used to estimate the cost of outages and discusses their relative strengths. Additionally, this paper identifies key questions from stakeholders regarding resilience investment and maps them to the relevant models that would help answer them. We include recommendations for future work to include recent advances in regional economic modeling that can estimate region and demographic-specific costs and the distributional consequences of potential resilience projects.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Active learning with multifidelity modeling for efficient rare event simulation

Here, while multifidelity modeling provides a cost-effective way to conduct uncertainty quantification with computationally expensive models, much greater efficiency can be achieved by adaptively deciding the number of required high-fidelity (HF) simulations, depending on the type and complexity of the problem and the desired accuracy in the results. We propose a framework for active learning with multifidelity modeling emphasizing the efficient estimation of rare events. Our framework works by fusing a low-fidelity (LF) prediction with an HF-inferred correction, filtering the corrected LF prediction to decide whether to call the high-fidelity model, and for enhanced subsequent accuracy, adapting the correction for the LF prediction after every HF model call. The framework does not make any assumptions as to the LF model type or its correlations with the HF model. In addition, for improved robustness when estimating smaller failure probabilities, we propose using dynamic active learning functions that decide when to call the HF model. We demonstrate our framework using several academic case studies (including some high-dimensional problems) and two finite element model case studies: estimating Navier-Stokes velocities using the Stokes approximation and estimating stresses in a transversely isotropic model subjected to displacements via a coarsely meshed isotropic model. Across these case studies, not only did the proposed framework estimate the failure probabilities accurately, but compared with either Monte Carlo or a standard variance reduction method, it also required only a small fraction of the calls to the HF model.

42 ENGINEERING↗
DOE OSTI2020

STOCHASTIC OPTIMIZATION FOR LONG TERM CAPITAL STRUCTURES, SYSTEMS, AND COMPONENTS REFURBISHMENT AND REPLACEMENT

As commercial nuclear power plants (NPPs) pursue extended plant operations in the form of Second License Renewals (SLRs), opportunities exist for these plants to provide capital investments to ensure long-term, safe, and economic performance. Several utilities have already announced their intention to pursue extended operations for one or more of their NPPs via SLR2. The goal of this research is to develop a riskinformed approach to evaluate and prioritize plant capital investments made in preparation for, and during the period of, extended plant operations to support decisions in NPP operations. In order to prioritize project selection via a riskinformed approach we developed a single decision-making tool that integrates safety/reliability, cost, and stochastic optimization models to provide users with data analysis capabilities to more cost effectively manage plant assets. Both stochastic analysis methods—such as Monte Carlo-based sampling strategies—and multi-stage stochastic optimization strategies are employed to provide priority lists to decisionmakers in support of risk-informed decisions. We applied the proposed method to a trial application of projected replacement/refurbishment expenditures for plant capital assets (i.e., Structures, Systems, and Components [SSCs]). The objective is to optimize the SSC replacement/refurbishment schedule in terms of economic constraints, data uncertainties, and SSC reliability data, as well to generate a priority list for maximizing returns on investment.

42 ENGINEERING↗
DOE OSTI2023

Model Predictive Control-Based Dual-Mode Operation of an Energy-Stored Quasi-Z-Source Photovoltaic Power System

The energy-stored quasi-Z-source inverter (ES-qZSI) has attracted much attention for photovoltaic (PV) power generations, due to its capability to stabilize the PV power fluctuations with simple structure and other advantages of Z-source inverter. The improved dual-mode (DM) ES-qZSI is able to support all-weather operation even at night or cloudy days when PV power is extremely low. However, the traditional proportional–integral (PI) based control suffers from complicated controller design and poor dynamic response during mode transition, due to two sets of PI control required for the daytime and night operation modes. In order to overcome that, here in this article, we propose a model predictive control strategy for the DM-ES-qZSI PV power system. The system predictive models in both day and night operating modes are derived. The control strategy is disclosed to ensure high performance of the system, through calling the predictive models and defined cost functions of the two modes within a single control loop. Simulation and experiment are carried out to verify the effectiveness of the proposed control strategy.

14 SOLAR ENERGY↗
DOE OSTI2022

Additional Degree of Freedom for WEC Model

'Additional Degree of Freedom for WEC' - WEC-Sim numerical model from RFTS 1 TEAMER project. An increase in wave energy converter (WEC) efficiency requires not only consideration of the nonlinear effects in the WEC dynamics and the power take-off (PTO) mechanisms, but also more integrated treatment of the whole system, i.e., the buoy dynamics, the PTO system, and the control strategy. It results in an optimization formulation that has a nonquadratic and nonstandard cost functional. This model presents the application of real-time nonlinear model predictive controller (NMPC) to two degrees of freedom point absorber type WEC with highly nonlinear PTO characteristics. The nonlinear effects, such as the fluid viscous drag, are also included in the plant dynamics. The controller may be implemented on a real-time target machine, and the WEC device is emulated in real-time using the WECSIM toolbox. Please see the ‘ReadMe’ within the root directory for an explanation of how to set-up and run the model. An article covering the development of this model is attached as "Real-Time Nonlinear Model Predictive Controller for Multiple Degrees of Freedom Wave Energy Converters with Non-Ideal Power Take-Off"

16 TIDAL AND WAVE POWER↗
DOE OSTI2022

Adaptive experimental design for multi-fidelity surrogate modeling of multi-disciplinary systems

We present an adaptive algorithm for constructing surrogate models of multi-disciplinary systems composed of a set of coupled components. With this goal we introduce “coupling” variables with a priori unknown distributions that allow surrogates of each component to be built independently. Once built, the surrogates of the components are combined to form an integrated-surrogate that can be used to predict system-level quantities of interest at a fraction of the cost of the original model. The error in the integrated-surrogate is greedily minimized using an experimental design procedure that allocates the amount of training data, used to construct each component-surrogate, based on the contribution of those surrogates to the error of the integrated-surrogate. Here, the multi-fidelity procedure presented is a generalization of multi-index stochastic collocation that can leverage ensembles of models of varying cost and accuracy, for one or more components, to reduce the computational cost of constructing the integrated-surrogate. Extensive numerical results demonstrate that, for a fixed computational budget, our algorithm is able to produce surrogates that are orders of magnitude more accurate than methods that treat the integrated system as a black-box.

42 ENGINEERING↗
DOE OSTI2024

Modeling prebiotic chemistries with quantum accuracy at classical costs

Molecular Dynamics (MD) simulations using classical force-fields are commonly employed in numerous scientific investigations. However, many natural processes involve bond breaking and quantum forces. This complexity is compounded by the presence of multiple competing length and timescales. For example, accurately modeling the thermodynamics and dynamics of a chemical reaction requires accounting for the concerted movements of numerous solvent molecules and ions with their own fast or slow timescales. While widely used static Density Functional Theory (DFT) calculations at 0 temperature can be beneficial for such investigations, they do not account for dynamics, and lack precision in describing the molecular environments. They particularly fail at correct, rigorous treatments of finite-temperature fluctuations, and thus generalization to experimentally relevant conditions. In PNAS Benayad et al develop a scalable, generalizable approach for designing Neural Network Potentials (NNPs) that can handle chemical reactivity in solvated systems with quantum accuracy at classical costs. Specifically, they study phosphoester bond formation and rupture, which is fundamentally relevant to the Phosphorus-Oxygen bond formation central to life, and especially for the RNA world hypothesis. The framework developed here has the potential to generalize to different chemical reactions of energy and biological relevance.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Representing Carbon Dioxide Transport and Storage Network Investments within Power System Planning Models

Carbon dioxide (CO 2 ) capture and storage (CCS) is frequently identified as a potential component to achieving a decarbonized power system at least cost; however, power system models frequently lack detailed representation of CO 2 transportation, injection, and storage (CTS) infrastructure. In this paper, we present a novel approach to explicitly represent CO 2 storage potential and CTS infrastructure costs and constraints within a continental-scale power system capacity expansion model. In addition, we evaluate the sensitivity of the results to assumptions about the future costs and performance of CTS components and carbon capture technologies. We find that the quantity of CO 2 captured within the power sector is relatively insensitive to the range of CTS costs explored, suggesting that the cost of CO 2 capture retrofits is a more important driver of CCS implementation than the costs of transportation and storage. Finally, we demonstrate that storage and injection costs account for the predominant share of total costs associated with CTS investment and operation, suggesting that pipeline infrastructure costs have limited influence on the competitiveness of CCS.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

A deformation-dependent coupled Lagrangian/semi-Lagrangian meshfree hydromechanical formulation for landslide modeling

Abstract The numerical modelling of natural disasters such as landslides presents several challenges for conventional mesh-based methods such as the finite element method (FEM) due to the presence of numerically challenging phenomena such as severe material deformation and fragmentation. In contrast, meshfree methods such as the reproducing kernel particle method (RKPM) possess unique features conducive to modelling extreme events such as the absence of a structured mesh and the ease of adaptive refinement, among others. While the semi-Lagrangian reproducing kernel (SL-RK) shape functions of RKPM defined in the current configuration have proven to be effective in extreme event modelling, the computational cost for the re-evaluation of the shape functions at every time step is costly. In this work, a deformation-dependent coupling of the Lagrangian reproducing kernel (L-RK) and SL-RK approximations is proposed for the solution of a hydro-mechanical formulation for effective simulations of landslides. The ramp function is constructed based on an equivalent plastic strain as a deformation-dependent transition from L-RK shape functions to SL-RK ones as the deformation progresses. The particular focus of the paper will be on modelling seepage-induced landslides with a mixed $$u$$ u – $$p$$ p formulation to couple the solid and fluid phases. Examples are presented to examine the effectiveness of this coupled Lagrangian/semi-Lagrangian reproducing kernel (L–SL RK) formulation and to highlight its performance in landslide modelling.

Baek, Jonghyuk↗
DOE OSTI2020

CRADA Number NFE-17-06866 with Active Energy Systems, Inc. (CRADA Final Report)

Cooperative Research and Development Agreement (CRADA) NFE-17-06866 between Oak Ridge National Laboratory (ORNL) and Active Energy Systems Inc. (AES) focused on studying and modeling a low cost, high efficiency energy storage technology. The successful development of low-cost, high-efficiency energy storage is a significant bottleneck in the implementation of intermittent renewable energy sources such as wind and solar. AES is a startup company developing a heat exchange technology to utilize a low-temperature phase change material (PCM). The work done under this CRADA explored this technology’s ability to augment a heat pump/heat engine device to convert electricity into thermal energy and vice versa, operating to complement the needs of the electric grid. Modeling, design and development of a prototype to prove the technology was successful, but current production economics and market demand make further exploration undesirable.

25 ENERGY STORAGE↗
DOE OSTI2024

Artificial ground reflector size and position effects on energy yield and economics of single‐axis‐tracked bifacial photovoltaics

Abstract Artificial ground reflectors improve bifacial energy yield by increasing both front and rear‐incident irradiance. Studies have demonstrated an increase in energy yield due to the addition of artificial reflectors; however, they have not addressed the effect of varying reflector dimensions and placement on system performance and the impact of these parameters on the reflectors' financial viability. We studied the effect of high albedo (70% reflective) artificial reflectors on single‐axis‐tracked bifacial photovoltaic systems through ray‐trace modeling and field measurements. In the field, we tested a range of reflector configurations by varying reflector size and placement and demonstrated that reflectors increased daily energy yield up to 6.2% relative to natural albedo for PERC modules. To confirm the accuracy of our model, we compared modeled and measured power and found a root mean square error (RMSE) of 5.4% on an hourly basis. We modeled a typical meteorological year in Golden, Colorado, to demonstrate the effects of artificial reflectors under a wide range of operating conditions. Seventy percent reflective material can increase total incident irradiance by 1.9%–8.6% and total energy yield by 0.9%–4.5% annually after clipping is considered with a DC–AC ratio of 1.2. Clipping has a significant effect on reflector impact and must be included when assessing reflector viability because it reduces reflector energy gain. We calculated a maximum viable cost for these improvements of up to $2.50–4.60/m 2 , including both material and installation, in Golden. We expanded our analysis to cover a latitude range of 32–48°N and demonstrated that higher‐latitude installations with lower energy yield and higher diffuse irradiance content can support higher reflector costs. In both modeling and field tests, and for all locations, the ideal placement of the reflectors was found to be directly underneath the module due to the optimized rear irradiance increase.

14 SOLAR ENERGY↗
DOE OSTI2022

Decarbonization Scenarios in the United States: Comparing Biofuels Growth in Two Models - GCAM and BSM

Scenarios for deep decarbonization rely on biomass for biofuels, biopower, and bioproducts, often including negative emissions via carbon capture and storage or utilization. Despite the prominence of biomass in many deep decarbonization pathways, critical questions remain about biomass allocation, effects of transportation electrification, the pace of growth, and implications for agriculture and land use. We address these questions through a unique comparison of carbon pricing effects on the growth of biomass utilization and its effects on land use in the United States by comparing results from a multisectoral integrated assessment model, the Global Change Analysis Model [GCAM], with results from a biomass-to-biofuels system dynamics model, the Biomass Scenario Model [BSM]. We contribute to model comparison efforts by analyzing the biomass deployment needed for a scenario consistent with a "Middle of the Road" Shared Socioeconomic Pathway [SSP2] and a representative concentration pathway of 2.6 W/m2. The GCAM scenarios solve for global equilibrium conditions that are consistent with this pathway, including demands for biomass across all economic sectors and representing bioenergy with carbon capture and storage as a technology option. The BSM scenarios assess those biomass and biofuel results for the United States and identify challenges associated with that pace and amount of expansion. In the scenario analysis, we harmonize key factors such as carbon price trajectory, domestic ethanol fuel demand, ethanol blending, and arable land availability, and vary them in both models. In GCAM, we vary the carbon price, transportation electrification, ethanol blending constraints, and arable land availability inputs and the value of the carbon in land; in BSM, in addition to directly inputting certain GCAM results, we vary the maximum rate of biorefinery construction, flexibility of feedstock types across conversion processes, and policy incentives such as tax credits and renewable identification number payments. The selected carbon price trajectory results in a rapid increase in biofuel production in the United States, reaching about 9.4 EJ/year in 2060 in the highest scenario analyzed in GCAM. Results differ between the two models in timing and ultimate quantity of biomass and biofuel production. GCAM biofuel quantities generally exceed BSM amounts because CCS is applied to biofuel pathways in GCAM, and because of differences in capacity expansion and related dynamics of land allocation, biomass production, and price dynamics. These dynamics include rapid biorefinery capacity expansion in high demand cases. To satisfy this biomass demand, GCAM rapidly equilibrates land allocation, but the BSM limits the rate at which this re-allocation can occur. A further contrast with the equilibrium approach in GCAM is that the BSM represents a delay between planting and harvesting woody biomass resources. As a result of these model contrasts, feedstock costs in BSM increase more than in GCAM, and the absence of CCS in the BSM also reduces the relative economic attractiveness of biofuels production. The bottlenecks, lags, and price increases also lead to potential for volatility in feedstock price and land allocation to biomass in the BSM. GCAM has more biomass production than BSM in all scenarios, partly because of the broader, economy-wide coverage of GCAM, in contrast to BSM's exclusive focus on biofuels. In both models, trends like those of biofuels production were observed for biomass production: minimal growth without a carbon price and policy incentives, and increases with a carbon price, particularly with carbon capture and storage, because the inputs assume that biopower and biofuels decrease greenhouse gas emissions. In high policy scenarios, biomass demand is high, and the consequent high biomass prices due to the land re-allocation bottleneck in the BSM limit biofuel production even if the biorefinery capacity is expanded. However, because biomass prices do not increase as much in the low policy scenario, growth is slower and the land-reallocation bottleneck no longer dominates, such that the effect of increased capacity can be seen. Across both the models, a change in assumptions from less to more land availability increases biofuel production in both GCAM and BSM, as the upward pressure on feedstock price and volatility are both reduced.

biofuels↗
DOE OSTI2026

Benchtop Autonomous Electrochemical Characterization System for Combinatorial Thin-Film Solid Oxide Electrodes

The design of materials for electrochemical energy conversion is complicated by a vast search space of candidate materials and multifaceted property requirements: multicarrier conductivity, stability, and catalytic activity are all necessary but rarely intersect. Although self-driving laboratories are rapidly rising to address such material optimization problems, the required infrastructure for integrated, large-scale robotic facilities can be cost-prohibitive. Here we develop and evaluate a closed-loop measurement system for efficient screening of proton-conducting oxide electrodes for ceramic fuel cells and electrolyzers, building on top of an existing benchtop instrument and integrating techniques for rapid impedance measurement and automated analysis. This system exemplifies a “minimum viable” self-driving implementation that can deliver substantial benefits with relatively simple infrastructure. Combinatorial thin-film microelectrode libraries are characterized with a recently developed joint time-domain and frequency-domain impedance measurement technique, which provides an order-of-magnitude acceleration relative to conventional impedance spectroscopy. The distribution of relaxation times is extracted from impedance data and analyzed without human intervention. These results feed an active learning and Bayesian optimization process that learns to predict electrochemical impedance as a function of material composition, measurement temperature, oxygen partial pressure, and electrical bias, which further reduces the screening time by tenfold with optimized experimental sequences. We apply this system to Ba⁡(Co,Fe,Zr,Y)⁢O 3−𝛿 combinatorial libraries and evaluate its effectiveness for learning material property trends and optimizing expensive-to-evaluate properties such as activation energy. This offers insights into key methodological aspects of practical autonomous experimentation, including surrogate model validation, cost-aware acquisition functions, and high-throughput data interpretation. Our results demonstrate the efficacy of the system for rapidly gathering information, but also highlight real-world experimental challenges of thin-film degradation and numerical instability in surrogate models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

A data-driven framework for permeability prediction of natural porous rocks via microstructural characterization and pore-scale simulation

Understanding the microstructure–property relationships of porous media is of great practical significance, based on which macroscopic physical properties can be directly derived from measurable microstructural informatics. However, establishing reliable microstructure–property mappings in an explicit manner is difficult, due to the intricacy, stochasticity, and heterogeneity of porous microstructures. In this paper, a data-driven computational framework is presented to investigate the inherent microstructure–permeability linkage for natural porous rocks, where multiple techniques are integrated together, including microscopy imaging, stochastic reconstruction, microstructural characterization, pore-scale simulation, feature selection, and data-driven modeling. A large number of 3D digital rocks with a wide porosity range are acquired from microscopy imaging and stochastic reconstruction techniques. A broad variety of morphological descriptors are used to quantitatively characterize pore microstructures from different perspectives, and they compose the raw feature pool for feature selection. Here high-fidelity lattice Boltzmann simulations are conducted to resolve fluid flow passing through porous media, from which reliable permeability references are obtained. The optimal feature set that best represents permeability is identified through a performance-oriented feature selection process, upon which a cost-effective surrogate model is rapidly fitted to approximate the microstructure-permeability mapping via data-driven modeling. This surrogate model exhibits great advantages over empirical/analytical formulas in terms of prediction accuracy and generalization capacity, which can predict reliable permeability values spanning four orders of magnitude. Besides, feature selection also greatly enhances the interpretability of the data-driven prediction model, from which new insights into the mechanism of how microstructural characteristics determine intrinsic permeability are obtained.

58 GEOSCIENCES↗
DOE OSTI2025

Floating Wind Array Ontology and Modeling Framework

While there are many tools for designing and modeling a single floating turbine, array level design and modeling has much more to consider. Designing floating wind arrays requires a coupled approach considering many variables, from bathymetry to installation and maintenance to failure and risk analysis. With all of these considerations, an array-level modeling tool is needed to quickly evaluate array designs. The Floating Array Model (FAModel) tool developed at the National Renewable Energy Laboratory was created to fill this gap in low-fidelity array modeling. FAModel is a python framework created to streamline holistic low-fidelity floating wind modeling for array-level analysis. FAModel integrates site data and models with a variety of open-source modeling tools developed by NREL, including FLORIS, RAFT, MoorPy, and anchor capacity models. The integration of these tools allows users to quickly and holistically design an array by considering forces, area analysis, visualization, annual energy production, failure modeling, and component costs.

17 WIND ENERGY↗
DOE OSTI2023

Predicting wind farm operations with machine learning and the P2D‐RANS model: A case study for an AWAKEN site

Abstract The power performance and the wind velocity field of an onshore wind farm are predicted with machine learning models and the pseudo‐2D RANS model, then assessed against SCADA data. The wind farm under investigation is one of the sites involved with the American WAKE experimeNt (AWAKEN). The performed simulations enable predictions of the power capture at the farm and turbine levels while providing insights into the effects on power capture associated with wake interactions that operating upstream turbines induce, as well as the variability caused by atmospheric stability. The machine learning models show improved accuracy compared to the pseudo‐2D RANS model in the predictions of turbine power capture and farm power capture with roughly half the normalized error. The machine learning models also entail lower computational costs upon training. Further, the machine learning models provide predictions of the wind turbulence intensity at the turbine level for different wind and atmospheric conditions with very good accuracy, which is difficult to achieve through RANS modeling. Additionally, farm‐to‐farm interactions are noted, with adverse impacts on power predictions from both models.

17 WIND ENERGY↗
DOE OSTI2024

Autonomous hybrid optimization of a SiO 2 plasma etching mechanism

Computational modeling of plasma etching processes at the feature scale relevant to the fabrication of nanometer semiconductor devices is critically dependent on the reaction mechanism representing the physical processes occurring between plasma produced reactant fluxes and the surface, reaction probabilities, yields, rate coefficients, and threshold energies that characterize these processes. The increasing complexity of the structures being fabricated, new materials, and novel gas mixtures increase the complexity of the reaction mechanism used in feature scale models and increase the difficulty in developing the fundamental data required for the mechanism. This challenge is further exacerbated by the fact that acquiring these fundamental data through more complex computational models or experiments is often limited by cost, technical complexity, or inadequate models. In this paper, we discuss a method to automate the selection of fundamental data in a reduced reaction mechanism for feature scale plasma etching of SiO 2 using a fluorocarbon gas mixture by matching predictions of etch profiles to experimental data using a gradient descent (GD)/Nelder–Mead (NM) method hybrid optimization scheme. These methods produce a reaction mechanism that replicates the experimental training data as well as experimental data using related but different etch processes.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Two-Step Hyperparameter Optimization Method: Accelerating Hyperparameter Search by Using a Fraction of a Training Dataset

Abstract Hyperparameter optimization (HPO) is an important step in machine learning (ML) model development, but common practices are archaic—primarily relying on manual or grid searches. This is partly because adopting advanced HPO algorithms introduces added complexity to the workflow, leading to longer computation times. This poses a notable challenge to ML applications, as suboptimal hyperparameter selections curtail the potential of ML model performance, ultimately obstructing the full exploitation of ML techniques. In this article, we present a two-step HPO method as a strategic solution to curbing computational demands and wait times, gleaned from practical experiences in applied ML parameterization work. The initial phase involves a preliminary evaluation of hyperparameters on a small subset of the training dataset, followed by a reevaluation of the top-performing candidate models postretraining with the entire training dataset. This two-step HPO method is universally applicable across HPO search algorithms, and we argue it has attractive efficiency gains. As a case study, we present our recent application of the two-step HPO method to the development of neural network emulators for aerosol activation. Although our primary use case is a data-rich limit with many millions of samples, we also find that using up to 0.0025% of the data—a few thousand samples—in the initial step is sufficient to find optimal hyperparameter configurations from much more extensive sampling, achieving up to 135× speedup. The benefits of this method materialize through an assessment of hyperparameters and model performance, revealing the minimal model complexity required to achieve the best performance. The assortment of top-performing models harvested from the HPO process allows us to choose a high-performing model with a low inference cost for efficient use in global climate models (GCMs).

97 MATHEMATICS AND COMPUTING↗