Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model benchmark”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Benchmarking and Improving Microbial-explicit Soil Biogeochemistry Models

Soils represent the largest terrestrial carbon pool on Earth. Yet emerging theories regarding stabilization of soil organic matter remain poorly represented in global-scale models; thus, underestimating the true uncertainty associated with potential terrestrial carbon cycle – climate feedbacks. With this project we created a testbed to compare and evaluate soil biogeochemical models (W. Wieder at the Univ. of CO, Boulder), data synthesis (R. Phillips, Indiana Univ.) and parameter estimation (S Allison, Univ. CA Irvine) to quantify uncertainty associated with potential soil C changes. This project resulted in 14 Presentations, 14 Publications and helped support the training of three graduate students. A significant accomplishment with this work was the creation of a soil biogeochemical testbed, which forces three soil carbon models (CASA, MIMICS, and CORPSE) with common environmental drivers.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Generating Models of the Flattop Critical Assembly for Benchmark Experiments with Python

Los Alamos National Laboratory has been performing nuclear criticality experiments since 1946 at the Pajarito site, starting the Los Alamos Critical Experiments Facility in 1948. A transition period occurred between 2004 and 2011 as operations moved to the National Criticality Experiments Research Center (NCERC), where criticality experiments are now performed. Criticality experiments are essential for determination and verification of nuclear data used in calculations and modeling—such as radiation transport codes—throughout the industry, enhancing nuclear criticality safety. In addition to nuclear data validation and benchmarking, the remotely operated critical assemblies at NCERC are used for a variety of experiments and training classes supporting criticality safety.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Combining Observations and Models: A Review of the CARDAMOM Framework for Data‐Constrained Terrestrial Ecosystem Modeling

The rapid increase in the volume and variety of terrestrial biosphere observations (i.e., remote sensing data and in situ measurements) offers a unique opportunity to derive ecological insights, refine process‐based models, and improve forecasting for decision support. However, despite their potential, ecological observations have primarily been used to benchmark process‐based models, as many past and current models lack the capability to directly integrate observations and their associated uncertainties for parameterization. In contrast, data assimilation frameworks such as the CARbon DAta MOdel fraMework (CARDAMOM) and its suite of process‐based models, known as the Data Assimilation Linked Ecosystem Carbon Model (DALEC), are specifically designed for model‐data fusion. This review, motivated by a recent CARDAMOM community workshop, examines the development and applications of CARDAMOM, with an emphasis on its role in advancing ecosystem process understanding. CARDAMOM employs a Bayesian approach, using a Markov Chain Monte Carlo algorithm to enable data‐driven calibration of DALEC parameters and initial states (i.e., carbon pool sizes) through observation operators. CARDAMOM's unique ability to retrieve localized model process parameters from diverse datasets—ranging from in situ measurements to global satellite observations—makes it a highly flexible tool for analyzing spatially variable ecosystem responses to environmental change. However, assimilating these data also presents challenges, including data quality issues that propagate into model skill, as well as trade‐offs between model complexity, parameter equifinality, and predictive performance. We discuss potential solutions to these challenges, such as reducing parameter equifinality by incorporating new observations. This review also offers community recommendations for incorporating emerging datasets, integrating machine learning techniques, strengthening collaboration with remote sensing, field, and modeling communities, and expanding CARDAMOM's relevance for localized ecosystem monitoring and decision‐making. CARDAMOM enables a deep, mechanistic understanding of terrestrial ecosystem dynamics that cannot be achieved through empirical analyses of observational datasets or weakly constrained models alone.

Bayesian inference↗
NASA NTRS2005

Terrestrial Microgravity Model and Threshold Gravity Simulation sing Magnetic Levitation

What is the threshold gravity (minimum gravity level) required for the nominal functioning of the human system? What dosage is required? Do human cell lines behave differently in microgravity in response to an external stimulus? The critical need for such a gravity simulator is emphasized by recent experiments on human epithelial cells and lymphocytes on the Space Shuttle clearly showing that cell growth and function are markedly different from those observed terrestrially. Those differences are also dramatic between cells grown in space and those in Rotating Wall Vessels (RWV), or NASA bioreactor often used to simulate microgravity, indicating that although morphological growth patterns (three dimensional growth) can be successiblly simulated using RWVs, cell function performance is not reproduced - a critical difference. If cell function is dramatically affected by gravity off-loading, then cell response to stimuli such as radiation, stress, etc. can be very different from terrestrial cell lines. Yet, we have no good gravity simulator for use in study of these phenomena. This represents a profound shortcoming for countermeasures research. We postulate that we can use magnetic levitation of cells and tissue, through the use of strong magnetic fields and field gradients, as a terrestrial microgravity model to study human cells. Specific objectives of the research are: 1. To develop a tried, tested and benchmarked terrestrial microgravity model for cell culture studies; 2. Gravity threshold determination; 3. Dosage (magnitude and duration) of g-level required for nominal functioning of cells; 4. Comparisons of magnetic levitation model to other models such as RWV, hind limb suspension, etc. and 5. Cellular response to reduced gravity levels of Moon and Mars.

Ramachandran, N.↗
NASA NTRS2005

Terrestrial Microgravity Model and Threshold Gravity Simulation using Magnetic Levitation

What is the threshold gravity (minimum gravity level) required for the nominal functioning of the human system? What dosage is required? Do human cell lines behave differently in microgravity in response to an external stimulus? The critical need for such a gravity simulator is emphasized by recent experiments on human epithelial cells and lymphocytes on the Space Shuttle clearly showing that cell growth and function are markedly different from those observed terrestrially. Those differences are also dramatic between cells grown in space and those in Rotating Wall Vessels (RWV), or NASA bioreactor often used to simulate microgravity, indicating that although morphological growth patterns (three dimensional growth) can be successfully simulated using RWVs, cell function performance is not reproduced - a critical difference. If cell function is dramatically affected by gravity off-loading, then cell response to stimuli such as radiation, stress, etc. can be very different from terrestrial cell lines. Yet, we have no good gravity simulator for use in study of these phenomena. This represents a profound shortcoming for countermeasures research. We postulate that we can use magnetic levitation of cells and tissue, through the use of strong magnetic fields and field gradients, as a terrestrial microgravity model to study human cells. Specific objectives of the research are: 1. To develop a tried, tested and benchmarked terrestrial microgravity model for cell culture studies; 2. Gravity threshold determination; 3. Dosage (magnitude and duration) of g-level required for nominal functioning of cells; 4. Comparisons of magnetic levitation model to other models such as RWV, hind limb suspension, etc. and 5. Cellular response to reduced gravity levels of Moon and Mars. The paper will discuss experiments md modeling work to date in support of this project.

Ramachandran, N.↗
NASA NTRS2005

Threshold Gravity Determination and Artificial Gravity Studies Using Magnetic Levitation

What is the threshold gravity (minimum gravity level) required for the nominal functioning of the human system? What dosage is required (magnitude and duration)? Do human cell lines behave differently in microgravity in response to an external stimulus? The critical need for a variable gravity simulator is emphasized by recent experiments on human epithelial cells and lymphocytes on the Space Shuttle clearly showing that cell growth and function are markedly different from those observed terrestrially. Those differences are also dramatic between cells grown in space and those in Rotating Wall Vessels (RWV), or NASA bioreactor often used to simulate microgravity, indicating that although morphological growth patterns (three dimensional growth) can be successfully simulated using RWVs, cell function performance is not reproduced - a critical difference. If cell function is dramatically affected by gravity off-loading, then cell response to stimuli such as radiation, stress, etc. can be very different from terrestrial cell lines. Yet, we have no good gravity simulator for use in study of these phenomena. This represents a profound shortcoming for countermeasures research. We postulate that we can use magnetic levitation of cells and tissue, through the use of strong magnetic fields and field gradients, as a terrestrial microgravity model to study human cells. Specific objectives of the research are: 1. To develop a tried, tested and benchmarked terrestrial microgravity model for cell culture studies; 2. Gravity threshold determination; 3. Dosage (magnitude and duration) of g-level required for nominal functioning of cells; 4. Comparisons of magnetic levitation model to other models such as RWV, hind limb suspension, etc. and 5. Cellular response to reduced gravity levels of Moon and Mars.

Ramachandran, N.↗
NASA NTRS2015

Revisiting Turbulence Model Validation for High-Mach Number Axisymmetric Compression Corner Flows

Two axisymmetric shock-wave/boundary-layer interaction (SWBLI) cases are used to benchmark one- and two-equation Reynolds-averaged Navier-Stokes (RANS) turbulence models. This validation exercise was executed in the philosophy of the NASA Turbulence Modeling Resource and the AIAA Turbulence Model Benchmarking Working Group. Both SWBLI cases are from the experiments of Kussoy and Horstman for axisymmetric compression corner geometries with SWBLI inducing flares of 20 and 30 degrees, respectively. The freestream Mach number was approximately 7. The RANS closures examined are the Spalart-Allmaras one-equation model and the Menter family of kappa − omega two equation models including the Baseline and Shear Stress Transport formulations. The Wind-US and CFL3D RANS solvers are employed to simulate the SWBLI cases. Comparisons of RANS solutions to experimental data are made for a boundary layer survey plane just upstream of the SWBLI region. In the SWBLI region, comparisons of surface pressure and heat transfer are made. The effects of inflow modeling strategy, grid resolution, grid orthogonality, turbulent Prandtl number, and code-to-code variations are also addressed.

Shock Wave↗
DOE OSTI2025

A High-Fidelity Model of the Peach Bottom 2 Turbine-Trip Benchmark Using VERA

This work presents a high-fidelity simulation of the Peach Bottom turbine trip (PBTT) benchmark using the Virtual Environment for Reactor Applications (VERA), a multiphysics reactor modeling tool developed by the U.S. Department of Energy’s Consortium for Advanced Simulation of Light Water Reactors energy innovation hub. The PBTT benchmark, based on a 1977 transient event at the end of cycle 2 in a General Electric Type-4 boiling water reactor (BWR), is a critical test case for validating core physics models with thermal feedback during rapid reactivity events. VERA was employed to perform end-to-end, pin-resolved simulations from conditions at the beginning of cycle 1 through the turbine-trip transient, incorporating detailed neutron transport, fuel depletion, and subchannel thermal hydraulics. The simulation reproduced key benchmark observables with high accuracy: the peak power excursion occurred at 0.75 s, matching the scram time and closely aligning with the benchmark average of 0.742 s; the simulated maximum power spike was approximately 7600 MW, which is within 3% of the benchmark average of 7400 MW; and void-collapse dynamics were consistent with benchmark expectations. Reactivity predictions during cycles 1 and 2 remained within 1500 pcm and 400 pcm of criticality, respectively. These results confirm VERA’s ability to model complex coupled neutronic and thermal hydraulic behavior in a BWR turbine-trip transient, which will support its use in future studies of modeling dryout, fuel performance, and uncertainty quantification for transients of this type.

BWR↗
DOE OSTI2026

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗
NASA NTRS2003

Particle Engulfment and Pushing By Solidifying Interfaces - Recent Theoretical and Experimental Developments

The objective of the work on Particle Engulfment and Pushing by Solidifying Interfaces (PEP) include: 1) to obtain fundamental understanding of the physics of particle pushing and engulfment, 2) to develop mathematical models to describe the phenomenon, and 3) to perform critical experiments in the microgravity environment of space to provide benchmark data for model validation. Successful completion of this project will yield vital information relevant to a diverse area of terrestrial applications. With PEP being a long term research effort, this report will focus on advances in the theoretical treatment of the solid/liquid interface interaction with an approaching particle, experimental validation of some aspects of the developed models, and the experimental design aspects of future experiments to be performed on board the International Space Station.

Stefanescu, D. M.↗
DOE OSTI2025

A comparison of probabilistic generative frameworks for molecular simulations

Generative artificial intelligence is now a widely used tool in molecular science. Despite the popularity of probabilistic generative models, numerical experiments benchmarking their performance on molecular data are lacking. Here, in this work, we introduce and explain several classes of generative models, broadly sorted into two categories: flow-based models and diffusion models. We select three representative models: neural spline flows, conditional flow matching, and denoising diffusion probabilistic models, and examine their accuracy, computational cost, and generation speed across datasets with tunable dimensionality, complexity, and modal asymmetry. Our findings are varied, with no one framework being the best for all purposes. In a nutshell, (i) neural spline flows do best at capturing mode asymmetry present in low-dimensional data, (ii) conditional flow matching outperforms other models for high-dimensional data with low complexity, and (iii) denoising diffusion probabilistic models appear the best for low-dimensional data with high complexity. Our datasets include a Gaussian mixture model and the dihedral torsion angle distribution of the Aib9 peptide, generated via a molecular dynamics simulation. We hope our taxonomy of probabilistic generative frameworks and numerical results may guide model selection for a wide range of molecular tasks.

Artificial intelligence↗
DOE OSTI2026

Analysis and modeling of tungsten emission and net erosion in the DIII-D divertor using updated atomic data

Tungsten (W) is one of the leading candidate materials for plasma-facing components. However, its main drawback is its high radiative efficiency; if W penetrates the plasma, it can lead to core degradation or even collapse. Since eroded tungsten tends to ionize in the sheath and redeposit promptly, the net erosion flux that escapes prompt redeposition can differ significantly from the gross erosion. This work presents a modeling framework to estimate net erosion and photon emission from W coatings exposed to the lower divertor of DIII-D using the DiMES material exposure probe. The approach couples RustBCA for sputtering yields with a Monte Carlo transport code (LPTMC) that models redeposition and W emission. Computation is carried out with new atomic data, based on R-matrix and Mons calculations, leading to lower ionization probabilities and a twofold increase in net erosion estimates compared to calculations done with OPEN-ADAS atomic data. The model results are benchmarked against experimental measurements, showing quantitative agreement for erosion, although the trends in W emission are reproduced only qualitatively. The model is also used to assess whether W II emission can serve as a direct measurement of the net erosion of W in the lower divertor of DIII-D. Simulations show that this is not valid if the electron pressure is above ~120 Pa or if the toroidal length of the eroded material is smaller than the parallel-to-B distance traveled by impurity ions before steady-state conditions are reached. Finally, simulations suggest that when W is sputtered by carbon ions with high impact energies (≳300 eV) in DIII-D, W net erosion scales with W gross erosion and can be numerically approximated using W I flux alone as input.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Temporal sequence transformer to advance long-term streamflow prediction

Accurate streamflow prediction is crucial for understanding climate change impacts on water resources and for effective management of extreme hydrological events. While Long Short-Term Memory (LSTM) networks have been the dominant data-driven approach for streamflow forecasting, recent advancements in transformer architectures for time series tasks have shown promise in outperforming traditional LSTM models. This study introduces a transformer-based model that integrates historical streamflow data with climatic variables to enhance streamflow prediction accuracy. We evaluated our transformer model against a benchmark LSTM across five diverse basins in the United States. Results demonstrate that the transformer architecture consistently outperforms the LSTM model across all evaluation metrics, highlighting its potential as a more effective tool for hydrological forecasting. This research contributes to the ongoing development of advanced AI techniques for improved water resource management and climate change adaptation strategies.

Singh, Ruhaan [Farragut High School]↗
DOE OSTI2020

Neutronic Consideration of TREAT Facility Fuel SiC Recladding

The Transient Reactor Test (TREAT) Facility is an air-cooled reactor composed of graphite-urania fuel encapsulated in zirconium alloy canisters and surrounded by ~2 ft (~61 cm) of nuclear grade graphite. The primary role of TREAT is to provide in-pile nuclear-heated safety research via transient testing [1]. Benchmark efforts have demonstrated sensitivity of TREAT neutronics models to graphite cross section data and key neutron poisons found in the fuel assemblies [2]. During fabrication of TREAT fuel assemblies, a small concentration of boron was inadvertently introduced with variable concentration into the aggregate of fuel blocks prepared for TREAT use. The concentration of boron, and its respective uncertainty, represent the most sensitive component in a neutronics study; unfortunately, nothing can be done to reduce or otherwise mitigate its impact. Hydrogen in the fuel blocks reduces the mean free path of the core and its true quantity and uncertainty is approximated. The hydrogen remains from pitch binder used in the fuel fabrication process and was not completely released due to incomplete fuel graphitization. Destructive fuel testing is necessary to quantify the actual hydrogen content and to improve benchmark model quality. A third neutron poison of some significance is the hafnium impurity in the Zircaloy-3 (Zry-3) assembly cladding. The quantity of hafnium is expected to be within nominal manufacturing limits for nuclear grade zircaloy. Recladding the fuel assemblies with material that is less neutron absorbing is expected to benefit reactor neutron economy. Moreover, TREAT’s total transient energy is restricted based on the rate of Zry-3 oxidation in TREAT’s air coolant environment. Hence, cladding with more benign air reaction kinetics could dramatically uprate the facility’s experimental capability. Silicon carbide (SiC) has been proposed as a candidate material for recladding TREAT assemblies, as SiC/SiC demonstrate favorable properties within nuclear environments [3]. The current operational limits of TREAT are restricted by the oxidation of Zry-3. Change of the cladding to SiC could feasibly double the current temperature limitation. Recladding opportunities allow for previously damaged fuel assemblies to be returned to service, as Zry-3 is not commercially available. The initial effort required to consider proceeding with any recladding effort is to neutronically characterize key reactor parameters while replacing Zry-3 with SiC. A characterization summary, with respective results, is provided herein.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
NASA NTRS1982

Turbofan forced mixer-nozzle internal flowfield. Volume 1: A benchmark experimental study

An experimental investigation of the flow field within a model turbofan forced mixer nozzle is described. Velocity and thermodynamic state variable data for use in assessing the accuracy and assisting the further development of computational procedures for predicting the flow field within mixer nozzles are provided. Velocity and temperature data suggested that the nozzle mixing process was dominated by circulations (secondary flows) of a length scale on the order the lobe dimensions which were associated with strong radial velocities observed near the lobe exit plane. The 'benchmark' model mixer experiment conducted for code assessment purposes is discussed.

Paterson, R. W.↗
DOE OSTI2022

gdess: A framework for evaluating simulated atmospheric CO 2 in Earth System Models

Atmospheric carbon dioxide (CO 2 ) plays a key role in the global carbon cycle and global warming. Climate-carbon feedbacks are often studied and estimated using Earth System Models (ESMs), which couple together multiple model components—including the atmosphere, ocean, terrestrial biosphere, and cryosphere—to jointly simulate mass and energy exchanges within and between these components. Despite tremendous advances, model intercomparisons and benchmarking are aspects of ESMs that warrant further improvement (Fer et al., 2021; Smith et al., 2014). Such benchmarking is critical because comparing the value of state variables in these simulations against observed values provides evidence for appropriately refining model components; moreover, researchers can learn much about Earth system dynamics in the process (Randall et al., 2019). We introduce `gdess` (a.k.a., Greenhouse gas Diagnostics for Earth System Simulations), which parses observational datasets and ESM simulation output, combines them to be in a consistent structure, computes statistical metrics, and generates diagnostic visualizations. In its current incarnation, `gdess` facilitates evaluating a model's ability to reproduce observed temporal and spatial variations of atmospheric CO 2 . The diagnostics implemented modularly in `gdess` support more rapid assessment and improvement of model-simulated global CO 2 sources and sinks associated with land and ocean ecosystem processes. We intend for this set of automated diagnostics to form an extensible, open source framework for future comparisons of simulated and observed concentrations of various greenhouse gases across Earth system models.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2021

Hybrid phenology matching model for robust crop phenological retrieval

Crop phenology regulates seasonal agroecosystem carbon, water, and energy exchanges, and is a key component in empirical and process-based crop models for simulating biogeochemical cycles of farmlands, assessing gross and net primary production, and forecasting the crop yield. The advances in phenology matching models provide a feasible means to monitor crop phenological progress using remote sensing observations, with a priori information of reference shapes and reference phenological transition dates. Yet the underlying geometrical scaling assumption of models, together with the challenge in defining phenological references, hinders the applicability of phenology matching in crop phenological studies. The objective of this study is to develop a novel hybrid phenology matching model to robustly retrieve a diverse spectrum of crop phenological stages using satellite time series. The devised hybrid model leverages the complementary strengths of phenometric extraction methods and phenology matching models. It relaxes the geometrical scaling assumption and can characterize key phenological stages of crop cycles, ranging from farming practice-relevant stages (e.g., planted and harvested) to crop development stages (e.g., emerged and mature). To systematically evaluate the influence of phenological references on phenology matching, four representative phenological reference scenarios under varying levels of phenological calibrations in terms of time and space are further designed with publicly accessible phenological information. The results indicate that the hybrid phenology matching model can achieve high accuracies for estimating corn and soybean phenological growth stages in Illinois, particularly with the year- and region-adjusted phenological reference (R-squared higher than 0.9 and RMSE less than 5 days for most phenological stages). The inter-annual and regional phenological patterns characterized by the hybrid model correspond well with those in the crop progress reports (CPRs) from the USDA National Agricultural Statistics Service (NASS). Compared to the benchmark phenology matching model, the hybrid model is more robust to the decreasing levels of phenological reference calibrations, and is particularly advantageous in retrieving crop early phenological stages (e.g., planted and emerged stages) when the phenological reference information is limited. This innovative hybrid phenology matching model, together with CPR-enabled phenological reference calibrations, holds 3 considerable promise in revealing spatio-temporal patterns of crop phenology over extended geographical regions.

Phenology↗
DOE OSTI2025

AI Benchmark Democratization and Carpentry

Benchmarks are a cornerstone of modern machine learning, enabling reproducibility, comparison, and scientific progress. However, AI benchmarks are increasingly complex, requiring dynamic, AI-focused workflows. Rapid evolution in model architectures, scale, datasets, and deployment contexts makes evaluation a moving target. Large language models often memorize static benchmarks, causing a gap between benchmark results and real-world performance. Beyond traditional static benchmarks, continuous adaptive benchmarking frameworks are needed to align scientific assessment with deployment risks. This calls for skills and education in AI Benchmark Carpentry. From our experience with MLCommons, educational initiatives, and programs like the DOE's Trillion Parameter Consortium, key barriers include high resource demands, limited access to specialized hardware, lack of benchmark design expertise, and uncertainty in relating results to application domains. Current benchmarks often emphasize peak performance on top-tier hardware, offering limited guidance for diverse, real-world scenarios. Benchmarking must become dynamic, incorporating evolving models, updated data, and heterogeneous platforms while maintaining transparency, reproducibility, and interpretability. Democratization requires both technical innovation and systematic education across levels, building sustained expertise in benchmark design and use. Benchmarks should support application-relevant comparisons, enabling informed, context-sensitive decisions. Dynamic, inclusive benchmarking will ensure evaluation keeps pace with AI evolution and supports responsible, reproducible, and accessible AI deployment. Community efforts can provide a foundation for AI Benchmark Carpentry.

von Laszewski, Gregor [Virginia U.]↗