Search NASA⌕ Search

SEARCH · Search NASA

Results for “Scalable 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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Design of Controller Hardware-In-the-Loop Model of Microgrid with Modular Building Blocks and Automated Design Script

The scalability of controller hardware-in-the-loop (CHIL) simulation is critical for validating control coordination and energy management in microgrids with distributed energy resources, especially as these modern systems become more complex and decentralized. This paper presents a CHIL modeling methodology that combines modular building blocks with an automated design script to streamline the development of high-fidelity microgrid models. Standardized subsystem templates for resources, converters, and buses are integrated with a Python-based script that compiles structured JSON configuration files into simulation-ready initialization code. The proposed approach reduces development time, improves model consistency, and enhances simulation fidelity. The methodology is validated on a Typhoon HIL604 platform and is broadly applicable to real-time simulation of complex, networked microgrid systems. This framework establishes a foundation for automated, scalable CHIL validation and accelerates the design of next-generation distributed energy systems.

Kim, Namwon [ORNL] (ORCID:0000000200438489)↗
DOE OSTI2026

Xanthos-Lake Model Source Code

This repository contains the source code for Xanthos-Lake, a lake-modeling extension of the Xanthos framework that introduces a coupled lake component comprising the Xanthos-Lake Snow and Ice Model (xLSIM) and the Xanthos-Lake Water Balance Model (xLWBM). xLSIM is a basin-aware machine-learning model for lake snow, ice, and thermal conditions. It predicts monthly lake ice thickness, snow depth, snow-cover fraction, mixing-layer temperature, and lake ice fraction from meteorological forcing and lake surface-area information. It uses sequence-based deep-learning architectures, including Transformer and hybrid Long Short-Term Memory–Transformer (LSTM–Transformer) models, together with seasonal encoding, multi-lake learning, physical masking, and basin-level cryospheric and non-cryospheric classification. The training workflow uses Ray for scalable execution and includes optional Ray Tune hyperparameter optimization. Model predictions, observations, diagnostics, and feature-importance outputs are written in NetCDF. xLWBM is the water-balance component of the new lake framework. It simulates monthly lake storage, surface area, evaporation, inflow, outflow, and lake–groundwater exchange. It combines physical water-balance equations with calibrated bathymetric relationships, weir-based outlet flow, modified Penman open-water evaporation, groundwater head relaxation, Penman–Monteith snow and ice sublimation, and snow, ice, and thermal conditions supplied by xLSIM. The model calibrates lake parameters against satellite-derived surface-area data, using evaporation-based calibration where surface-area data are unavailable, and supports small, medium, and large lake classes. For large lakes, xLWBM is integrated with the managed-routing workflow so that lake storage and outflow interact directly with downstream river routing and reservoir operations. Together, xLSIM and xLWBM provide Xanthos with a coupled lake-modeling capability. xLSIM supplies the snow, ice, and thermal conditions that affect lake evaporation and snow- and ice-related water exchanges, while xLWBM translates those conditions into dynamic lake storage, surface area, evaporation, and discharge. In return, xLWBM supplies evolving lake surface area to xLSIM. This coupling enables Xanthos to represent lakes as active hydrologic components within basin-scale water-availability and routing simulations.

Machine Learning↗
NASA NTRS2022

Coevolution of Machine Learning and Process-Based Modelling to Revolutionize Earth and Environmental Sciences: A Perspective

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in EES, (1) nowcasting and prediction, (2) scenario analysis, and (3) diagnostic learning. The paper ponders over a ‘coevolutionary’ approach to model building, shifting away from a borrowing to a co-creation culture, to develop a generation of models that leverage the unique strengths of ML such as scalability to big data and high-dimensional mapping, while remaining faithful to process-based knowledge base and principles of model explainability and interpretability, and therefore, falsifiability.

Saman Razavi↗
NASA NTRS2011

Graphics Processing Unit (GPU) Acceleration of the Goddard Earth Observing System Atmospheric Model

The Goddard Earth Observing System 5 (GEOS-5) is the atmospheric model used by the Global Modeling and Assimilation Office (GMAO) for a variety of applications, from long-term climate prediction at relatively coarse resolution, to data assimilation and numerical weather prediction, to very high-resolution cloud-resolving simulations. GEOS-5 is being ported to a graphics processing unit (GPU) cluster at the NASA Center for Climate Simulation (NCCS). By utilizing GPU co-processor technology, we expect to increase the throughput of GEOS-5 by at least an order of magnitude, and accelerate the process of scientific exploration across all scales of global modeling, including: The large-scale, high-end application of non-hydrostatic, global, cloud-resolving modeling at 10- to I-kilometer (km) global resolutions Intermediate-resolution seasonal climate and weather prediction at 50- to 25-km on small clusters of GPUs Long-range, coarse-resolution climate modeling, enabled on a small box of GPUs for the individual researcher After being ported to the GPU cluster, the primary physics components and the dynamical core of GEOS-5 have demonstrated a potential speedup of 15-40 times over conventional processor cores. Performance improvements of this magnitude reduce the required scalability of 1-km, global, cloud-resolving models from an unfathomable 6 million cores to an attainable 200,000 GPU-enabled cores.

Putnam, Williama↗
DOE OSTI2024

Enhanced power density in zero-vacuum-gap thermophotovoltaic devices

Thermophotovoltaic (TPV) devices, which convert infrared thermal radiation from a hot emitter into electricity, hold great promise for applications in energy storage and waste heat recovery. While recent advancements have developed TPV devices with high efficiency, much less attention has been focused on improving the power density. Current TPV methods face challenges in significantly boosting the power density using emitters at very high temperatures (>2000 °C) or using complex, costly architectures such as near-field TPV. Here, we present the first experimental demonstration of a novel far-field TPV concept called “zero-vacuum-gap TPV” that eliminates the vacuum or gas-filled gap in conventional designs. By incorporating a high-index, infrared-transparent, and thermally insulating fused quartz spacer, we achieved a two-fold increase in power density compared to the far-field counterpart under identical conditions. Notably, in our experiment, the zero-vacuum-gap far-field design transforms a less-optimized, low-power-density far-field device into one with one of the highest power densities reported at moderate temperatures (700–1100 °C). Moreover, our measurements using a graphite emitter surpass the blackbody limit for gap-integrated far-field devices and match the performance of near-field TPV devices with an ultrathin 200-nm gap. Our findings suggest that zero-vacuum-gap TPV offers potential for cost-effective, scalable manufacturing using current technologies. Additionally, our modelling predicts that further power enhancements over one order of magnitude are possible with other spacer materials.

14 SOLAR ENERGY↗
DOE OSTI2025

Poster Abstract: Leveraging Large Language Models to Reveal Interpretable Cooling Behaviors from Smart Thermostat Data

Frequent heatwaves and hot summers increasingly challenge occupant comfort, health, and energy grid stability. Addressing these challenges requires a detailed understanding of household cooling behaviors, such as thermostat adjustments and adaptive responses to extreme conditions. Traditional analyses often rely on aggregated numerical metrics that overlook subtle but important household-specific variations. In this study, we introduce a generalizable methodology that integrates large language models (LLMs) with vision capabilities to enable scalable and detailed analysis of residential thermostat data. Using Ecobee's Donate Your Data (DYD) dataset—which provides five-minute records of indoor temperatures, thermostat setpoints, and HVAC runtimes—we focus on two U.S. cities with contrasting summer climates : Austin (TX) and Phoenix (AZ). Because raw time-series data are not well suited for direct LLM analysis, we transform them into visual representations, such as daily indoor temperature trajectories and weekly runtime histograms, to better capture behavioral variations. Leveraging LLMs' visual interpretation, we extract descriptive behavioral features, including temperature preferences, time-of-day cooling orientation, anticipatory versus reactive heatwave responses, and behavioral consistency. These semantic features support unsupervised clustering to identify distinct occupant archetypes at scale, revealing differences—such as morning-centric anticipatory coolers versus households that shift toward warmer setpoints during heatwaves—that can inform demand response, resilience planning, and health-aware interventions. By converting raw numerical data into interpretable behavioral patterns, this methodology enables scalable and practical analysis of occupant behavior, supporting actionable insights for comfort, resilience, and energy management.

Nihar, Kopal↗
DOE OSTI2025

Scalable multilevel Monte Carlo methods exploiting parallel redistribution on coarse levels

Here, we study an element agglomeration coarsening strategy that requires data redistribution at coarse levels when the number of coarse elements becomes smaller than the number of MPI processes used on the finest level. The overall procedure generates coarse elements (general unstructured unions of fine grid elements) within the framework of element-based algebraic multigrid methods (or AMGe) studied previously. The AMGe-generated coarse spaces have the ability to exhibit approximation properties of the same order as the fine-level spaces since by construction they contain the piecewise polynomials of the same order as on the fine level. These approximation properties are key for the successful use of AMGe in multilevel solvers for nonlinear partial differential equations as well as for multilevel Monte Carlo (MLMC) simulations. The ability to coarsen without being constrained by the number of MPI processes, as described in the present paper, allows to improve the scalability of these solvers as well as the overall MLMC method. The paper illustrates this latter fact with detailed scalability study of MLMC simulations applied to model Darcy equations with a stochastic log-normal permeability field.

AMGe↗
NASA NTRS1994

An avionics scenario and command model description for Space Generic Open Avionics Architecture (SGOAA)

This paper presents a description of a model for a space vehicle operational scenario and the commands for avionics. This model will be used in developing a dynamic architecture simulation model using the Statemate CASE tool for validation of the Space Generic Open Avionics Architecture (SGOAA). The SGOAA has been proposed as an avionics architecture standard to NASA through its Strategic Avionics Technology Working Group (SATWG) and has been accepted by the Society of Automotive Engineers (SAE) for conversion into an SAE Avionics Standard. This architecture was developed for the Flight Data Systems Division (FDSD) of the NASA Johnson Space Center (JSC) by the Lockheed Engineering and Sciences Company (LESC), Houston, Texas. This SGOAA includes a generic system architecture for the entities in spacecraft avionics, a generic processing external and internal hardware architecture, and a nine class model of interfaces. The SGOAA is both scalable and recursive and can be applied to any hierarchical level of hardware/software processing systems.

Stovall, John R.↗
NASA NTRS2012

Foundational Performance Analyses of Pressure Gain Combustion Thermodynamic Benefits for Gas Turbines

A methodology is described whereby the work extracted by a turbine exposed to the fundamentally nonuniform flowfield from a representative pressure gain combustor (PGC) may be assessed. The method uses an idealized constant volume cycle, often referred to as an Atkinson or Humphrey cycle, to model the PGC. Output from this model is used as input to a scalable turbine efficiency function (i.e., a map), which in turn allows for the calculation of useful work throughout the cycle. Integration over the entire cycle yields mass-averaged work extraction. The unsteady turbine work extraction is compared to steady work extraction calculations based on various averaging techniques for characterizing the combustor exit pressure and temperature. It is found that averages associated with momentum flux (as opposed to entropy or kinetic energy) provide the best match. This result suggests that momentum-based averaging is the most appropriate figure-of-merit to use as a PGC performance metric. Using the mass-averaged work extraction methodology, it is also found that the design turbine pressure ratio for maximum work extraction is significantly higher than that for a turbine fed by a constant pressure combustor with similar inlet conditions and equivalence ratio. Limited results are presented whereby the constant volume cycle is replaced by output from a detonation-based PGC simulation. The results in terms of averaging techniques and design pressure ratio are similar.

Paxson, Daniel E.↗
NASA NTRS2022

A Scalable Framework for Post Fire Debris Flow Hazard Assessment Using Satellite Precipitation Data

Wildfire is a global phenomenon that has dramatic effects on erosion and flood potential. On steep slopes, burned areas are more likely to experience significant overland flow during heavy rainfall leading to post fire debris flows (PFDFs). Previous work establishes methods for PFDF hazard assessment, often relying on regional-scale parameterizations with in-situ rainfall measurements to categorize hazard as a function of meteorological and surface properties. We present a globally scalable approach to extend the benefit these models provide to new areas. Our new model relies on publicly available satellite-based inputs with a global extent to provide first order hazard assessments of recently burned areas. Our results show it is possible to identify the conditions relevant for PFDF-initiation processes across a variety of physiographic settings. Improvements to satellite borne rainfall intensity data and increased availability of PFDF occurrence data worldwide are expected to enhance model skill and applicability further.

Wildfire↗
DOE OSTI2025

A Machine Learning Approach for Hourly Traffic Prediction Used in EV-Charging Sites

Reliable forecasting of hourly traffic volumes on highways is critical for planning and operating electric-vehicle charging infrastructure without overloading the grid. In this work, we develop and evaluate a station-specific machine-learning approach based on NeuralProphet, enhanced with conditional seasonality to better distinguish weekday, weekend, and holiday patterns. For each station, the model automatically retrieves the same calendar day from the prior years as an AR-Net initialization, fits trend and Fourier-based seasonality components, and then applies short-term auto-regressive corrections. We train and test on 2021 and 2022 TMAS data, respectively, and validate performance over the whole year. We chose to demonstrate how the model performs on a typical weekday (3/15/2022), weekend (3/27/2022), and a special holiday (12/25/2022). Our results yield MAPE of 7.4%, 23.6%, and 32.0%, respectively. Over the entire year 2022, the overall MAPE was 17%. This demonstrates that station-specific models with conditional seasonality can achieve accurate, scalable hourly forecasts for EV-charging load planning.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRS2014

Using SpF to Achieve Petascale for Legacy Pseudospectral Applications

Pseudospectral (PS) methods possess a number of characteristics (e.g., efficiency, accuracy, natural boundary conditions) that are extremely desirable for dynamo models. Unfortunately, dynamo models based upon PS methods face a number of daunting challenges, which include exposing additional parallelism, leveraging hardware accelerators, exploiting hybrid parallelism, and improving the scalability of global memory transposes. Although these issues are a concern for most models, solutions for PS methods tend to require far more pervasive changes to underlying data and control structures. Further, improvements in performance in one model are difficult to transfer to other models, resulting in significant duplication of effort across the research community. We have developed an extensible software framework for pseudospectral methods called SpF that is intended to enable extreme scalability and optimal performance. Highlevel abstractions provided by SpF unburden applications of the responsibility of managing domain decomposition and load balance while reducing the changes in code required to adapt to new computing architectures. The key design concept in SpF is that each phase of the numerical calculation is partitioned into disjoint numerical kernels that can be performed entirely inprocessor. The granularity of domain decomposition provided by SpF is only constrained by the datalocality requirements of these kernels. SpF builds on top of optimized vendor libraries for common numerical operations such as transforms, matrix solvers, etc., but can also be configured to use open source alternatives for portability. SpF includes several alternative schemes for global data redistribution and is expected to serve as an ideal testbed for further research into optimal approaches for different network architectures. In this presentation, we will describe our experience in porting legacy pseudospectral models, MoSST and DYNAMO, to use SpF as well as present preliminary performance results provided by the improved scalability.

DYNAMO↗
NASA NTRS2004

Transformations in Air Transportation Systems For the 21st Century

Globally, our transportation systems face increasingly discomforting realities: certain of the legacy air and ground infrastructures of the 20th century will not satisfy our 21st century mobility needs. The consequence of inaction is diminished quality of life and economic opportunity for those nations unable to transform from the 20th to 21st century systems. Clearly, new thinking is required regarding business models that cater to consumers value of time, airspace architectures that enable those new business models, and technology strategies for innovating at the system-of-networks level. This lecture proposes a structured way of thinking about transformation from the legacy systems of the 20th century toward new systems for the 21st century. The comparison and contrast between the legacy systems of the 20th century and the transformed systems of the 21st century provides insights into the structure of transformation of air transportation. Where the legacy systems tend to be analog (versus digital), centralized (versus distributed), and scheduled (versus on-demand) for example, transformed 21st century systems become capable of scalability through technological, business, and policy innovations. Where air mobility in our legacy systems of the 20th century brought economic opportunity and quality of life to large service markets, transformed air mobility of the 21st century becomes more equitable available to ever-thinner and widely distributed populations. Several technological developments in the traditional aircraft disciplines as well as in communication, navigation, surveillance and information systems create new foundations for 21st thinking about air transportation. One of the technological developments of importance arises from complexity science and modern network theory. Scale-free (i.e., scalable) networks represent a promising concept space for modeling airspace system architectures, and for assessing network performance in terms of robustness, resilience, and other metrics. The lecture offers an air transportation system topology and a scale-free network linkage graphic as framework for transportation system innovation. Successful outcomes of innovation in air transportation could lay the foundations for new paradigms for aircraft and their operating capabilities, air transportation system topologies, and airspace architectures and procedural concepts. These new paradigms could support scalable alternatives for the expansion of future air mobility to more consumers in more parts of the world.

Holmes, Bruce J.↗
DOE OSTI2024

Synthesis of Correct Digital Controller Models from Specifications by Model Transformation (21-0320)

The design of high consequence controllers (in weapons systems, autonomy, etc.) that do what they are supposed to do is a significant challenge. Testing simply does not come close to meeting the requirements for assurance. Today circuit designers at Sandia (and elsewhere) typically capture the core behavior of their components using state models in tools such as STATEFLOW. They then check that their models meet certain requirements (e.g. “The system bus must not deadlock” or “both traffic lights at an intersection must not be green at the same time”) using tools called model checkers. If the model checker returns “yes” then the property is guaranteed to be satisfied by the model. However, there are several drawbacks to this industry practice: (1) there is a lot of detail to get right, this is particularly challenging when there are multiple components requiring complex coordination (2) any errors returned by the model checker have to be traced back through the design and fixed, necessitating rework, (3) there are severe scalability problems with this approach, particularly when dealing with concurrency. All this places high demands on the designers who now face not only an accelerated schedule but also controllers of increasing complexity. This report describes a new and fundamentally different approach to the construction of safety-critical digital controllers. Instead of directly constructing a complete model and then trying to verify it, the designer can start with an initial abstract (think “sketch”) model plus the requirements, from which a correct concrete model is automatically synthesized. There is no need for post-hoc verification of required functional properties. Having tool to carry this out will significantly impact the nation’s ability to ensure the safety of high-consequence digital systems. The approach has been implemented in a prototype tool, along with a suite of examples, including ones that reflect actual problems faced by designers. Our approach operates on a variant of Statecharts developed at Sandia called Qspecs. Statecharts are a widely used formalism for developing concurrent reactive systems, supporting scalability through allowing state models containing composite states, which are the serial or parallel composition of substates which can themselves contain statecharts. Statecharts enable an incremental style of development, in which states are progressively refined to incorporate greater detail in an incremental model of software development. Our approach formulates a set of constraints from the structure of the models and the requirements and propagates these constraints to a fixpoint. The solution to the constraints is an inductive invariant along with guards on the transitions. We also show how our approach extends to implementation refinement, decomposition, composition, and elaboration. We currently handle safety requirements written in LTL (Linear Temporal Logic)

42 ENGINEERING↗
NASA NTRS1991

High-performance multiprocessor architecture for a 3-D lattice gas model

The lattice gas method has recently emerged as a promising discrete particle simulation method in areas such as fluid dynamics. We present a very high-performance scalable multiprocessor architecture, called ALGE, proposed for the simulation of a realistic 3-D lattice gas model, Henon's 24-bit FCHC isometric model. Each of these VLSI processors is as powerful as a CRAY-2 for this application. ALGE is scalable in the sense that it achieves linear speedup for both fixed and increasing problem sizes with more processors. The core computation of a lattice gas model consists of many repetitions of two alternating phases: particle collision and propagation. Functional decomposition by symmetry group and virtual move are the respective keys to efficient implementation of collision and propagation.

Lee, F.↗
DOE OSTI2026

Emerging Flexible Designs for Geospatial Multimodal Foundation Models

Foundation models are rapidly transforming Earth observation by enabling scalable pretraining across diverse unlabeled geospatial modalities. However, their architectural diversity—ranging from encoder-only to encoder-decoder and masked autoencoding paradigms—makes it challenging to assess performance trade-offs in a consistent manner. In this work, we present an apples-to-apples comparison of leading FM architectures designed for geospatial multimodal reasoning, with a particular focus on flexibility across varied spectral band configurations. We standardize pretraining using identical self-supervised learning objectives and training datasets, and evaluate all models under consistent parameterization on the GEOBench benchmark across classification and segmentation tasks. Our results offer new insights into the design trade-offs between model flexibility, modality alignment, and downstream task performance. By highlighting architectural strengths and limitations under controlled conditions, this study provides practical guidance for building next-generation geospatial foundation models capable of robust multimodal reasoning.

Ambrozio Dias, Philipe [ORNL] (ORCID:0000000194277↗
NASA NTRSDate not supplied

Sheaf Theoretic Models for Routing in Delay Tolerant Networks

One key to communications scalability is routing; as such the goal of this paper is to build upon successful efforts towards general routing for space-based networks. With the ever-increasing accessibility of space, the number of assets is increasing, which becomes a critical communications burden in terms of scheduling, spectrum allocation, and resource allocation. In order to mitigate these concerns, a true networking approach is necessary; a standard approach for space systems is Delay Tolerant Networking (DTN). For DTN to be a meaningful answer to the Solar System Internet (SSI) question, DTN must offer meaningful routing solutions that span the heterogeneous collection of links and nodes. This, in turn, depends on the general structure of these disconnected networks -- a structure that remains largely unknown. In ground communications networks, routing decisions are made based on several pathfinding algorithms working in tandem. In previous work, we modeled Dijkstra's pathfinding algorithm using sheaves and provided a more general framework for determining paths using sheaves over graphs. Continuing our sheaf-theoretic approach, we introduce here an expansion of our pathfinding sheaf to handle more general information, and we expand on additional pathfinding algorithms that can be represented using sheaves. Moreover, we demonstrate means of combining multiple algorithms into a single sheaf structure so that changes of scale can be presented in the language of sheaves. In addition, space communications networks rely upon radio transmitter antennas which can establish broadcast and multicast communications options, rather than the primarily unicast options available to wired networks. Last year, we also introduced a multicast routing sheaf for presenting broadcast, unicast, and multicast communications over a graph. Extending that work, we also introduce queuing sheaves so that we can blend these communications options together to simulate a variety of routing options across space networks. In addition, we include examples to illustrate the applicability of this abstract theory to routing in disconnected networks.

Robert Short↗
NASA NTRSDate not supplied

Validation of Cryogenic Propellant Tank Self-Pressurization

NASA’s near-future long-term space missions necessitate advancements in cryogenic fluid management (CFM), which includes safe and reliable long-term propellant storage. Consequently, NASA STMD (Space Technology Mission Directorate) has established the CFM Portfolio Project to improve CFM technologies for upcoming missions. As a part of CFM Modeling Portfolio, NASA Marshall Space Flight Center’s (MSFC) Fluid Dynamics branch within the Propulsion Systems Department is tasked with assessing and improving computational tools used to support flight projects such as Human Lander System and Commercial Lunar Payload Services. One of the challenging modeling problems is that of self-pressurization of propellant tank due to heat leakage over long time periods. Reduced order and nodal tools find it extremely difficult to accurately predict self-pressurization under transient conditions or where complex flow patterns or thermal gradients exist, and application of 3-D CFD (computational fluid dynamics) simulations is necessary to characterize these problems. Until recently, CFD simulations for these long-term processes (order of hours or days) have been too impractical to conduct due to prohibitive wall time and computational resource requirements. The requisite CFD tool need to be efficient, computationally scalable, modular with ability to incorporate various physics models, and robust enough to not accumulate conservation errors over several hours of simulated time. NASA MSFC’s Loci-Stream CFD tool along with the VOF module is a great candidate to fit this mold. In this paper, we validate Loci-Stream for predicting self-pressurization of a flight scale propellant tank so it can serve as a reliable design and analysis tool for NASA’s CFM application needs. Liquid hydrogen tank pressurization tests carried out at the K-site testing facility provide a reliable data set for this purpose. These tests were simulated using Loci-Stream solver with VOF module as well as a hybrid approach which uses a lumped model for the ullage gas domain and CFD simulation of the liquid propellant. Both are shown to have very good predictive capabilities over multiple K-site experiments.

Hong Q. Yang↗