Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning models”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Learning to Branch with Interpretable Machine Learning Models

Machine learning is being increasingly used in improving decisions made within branch-and-bound algorithms for solving mixed-integer programs (MIPs). Branching is a key component in branch-and-bound algorithms, this work presents IDAES-core project update on building simple and interpretable machine learning models for branching and improving decision-making tools applied for the optimization of advanced energy systems.

Bayramoglu, Selin↗
DOE OSTI2024

Towards provably efficient quantum algorithms for large-scale machine-learning models

Large machine learning models are revolutionary technologies of artificial intelligence whose bottlenecks include huge computational expenses, power, and time used both in the pre-training and fine-tuning process. In this work, we show that fault-tolerant quantum computing could possibly provide provably efficient resolutions for generic (stochastic) gradient descent algorithms, scaling as $\mathcal{O}$(T 2 x polylog($n$)), where n is the size of the models and T is the number of iterations in the training, as long as the models are both sufficiently dissipative and sparse, with small learning rates. Based on earlier efficient quantum algorithms for dissipative differential equations, we find and prove that similar algorithms work for (stochastic) gradient descent, the primary algorithm for machine learning. In practice, we benchmark instances of large machine learning models from 7 million to 103 million parameters. We find that, in the context of sparse training, a quantum enhancement is possible at the early stage of learning after model pruning, motivating a sparse parameter download and re-upload scheme. Our work shows solidly that fault-tolerant quantum algorithms could potentially contribute to most state-of-the-art, large-scale machine-learning problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

An Open Combinatorial Diffraction Dataset Including Consensus Human and Machine Learning Labels with Quantified Uncertainty for Training New Machine Learning Models

Modern machine learning and autonomous experimentation schemes in materials science rely on accurate analysis of the data ingested by these models. Unfortunately, accurate analysis of the underlying data can be difficult, even for domain experts, complicating the training of the models intended to drive experiments. This is especially true when the goal is to identify the presence of weak signatures in diffraction or spectroscopic datasets. In this work, we examine a set of as-obtained diffraction data that track the phase transition from monoclinic to tetragonal in a Nb-doped VO2 film as a function of temperature and dopant concentration. We then task a set of domain experts and a set of machine learning experts with identifying which phase is present in each diffraction pattern manually and algorithmically, respectively; in both cases, the labels can vary dramatically, especially at the phase boundaries. We use the mode of the labels and the Shannon entropy as a method to capture, preserve and propagate consensus labels and their variance. Further we use the expert labels as a benchmark and demonstrate the use of Shannon entropy weighted scoring to test the performance of machine learning generated labels. Finally, we propose a material data challenge centered around generating improved labeling algorithms. This real-world dataset curated with expert labels can act as test bed for new algorithms. The raw data, annotations and code used in this study are all available online at data.gov and the interested reader is encouraged to replicate and improve the existing models

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

QUBO formulations for training machine learning models

Abstract Training machine learning models on classical computers is usually a time and compute intensive process. With Moore’s law nearing its inevitable end and an ever-increasing demand for large-scale data analysis using machine learning, we must leverage non-conventional computing paradigms like quantum computing to train machine learning models efficiently. Adiabatic quantum computers can approximately solve NP-hard problems, such as the quadratic unconstrained binary optimization (QUBO), faster than classical computers. Since many machine learning problems are also NP-hard, we believe adiabatic quantum computers might be instrumental in training machine learning models efficiently in the post Moore’s law era. In order to solve problems on adiabatic quantum computers, they must be formulated as QUBO problems, which is very challenging. In this paper, we formulate the training problems of three machine learning models—linear regression, support vector machine (SVM) and balanced k-means clustering—as QUBO problems, making them conducive to be trained on adiabatic quantum computers. We also analyze the computational complexities of our formulations and compare them to corresponding state-of-the-art classical approaches. We show that the time and space complexities of our formulations are better (in case of SVM and balanced k-means clustering) or equivalent (in case of linear regression) to their classical counterparts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Machine Learning Model Geotiffs - Applications of Machine Learning Techniques to Geothermal Play Fairway Analysis in the Great Basin Region, Nevada

This submission contains geotiffs, supporting shapefiles and readmes for the inputs and output models of algorithms explored in the Nevada Geothermal Machine Learning project, meant to accompany the final report. Layers include: Artificial Neural Network (ANN), Extreme Learning Machine (ELM), Bayesian Neural Network (BNN), Principal Component Analysis (PCA/PCAk), Non-negative Matrix Factorization (NMF/NMFk), input rasters of feature sets, and positive/negative training sites. See readme .txt files and final report for additional metadata. A submission linking the full codebase for generating machine learning output models is available under "related resources" on this page.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Impact of Domain Knowledge on the Property Prediction of Specialized Machine Learning Models

Developing transferable machine learning models is trending in data-driven materials research. However, how to apply such models to a specific research domain remains unclear. Here, in this work, we choose high-entropy materials as a platform with a specialized data set containing 145,323 DFT-relaxed materials. This data set is used to explore the role of domain-specific knowledge in training effective models. Our tests with three representative graph neural network architectures indicate the model complexity has much smaller influence on performance than the data itself. Specifically, the consideration of low-energy atomic ordering, structures with diverse elemental coverage, and high-order interactions significantly influences the model performance. We also find that domain knowledge-driven sampling can greatly enhance unsupervised learning techniques. This research highlights that developing specialized data sets is more beneficial than further complicating deep learning architectures. Additionally, physics-inspired sampling algorithms are crucially needed for better machine learning models for a specific materials research domain.

36 MATERIALS SCIENCE↗
DOE OSTI2024

An Efficient Checkpointing System for Large Machine Learning Model Training

As machine learning models increase in size and complexity rapidly, the cost of checkpointing in ML training became a bottleneck in storage and performance (time). For example, the latest GPT-4 model has massive parameters at the scale of 1.76 trillion. It is highly time and storage consuming to frequently writes the model to checkpoints with more than 1 trillion floating point values to storage. This work aims to understand and attempt to mitigate this problem. First, we characterize the checkpointing interface in a collection of representative large machine learning/language models with respect to storage consumption and performance overhead. Second, we propose the two optimizations: i) A periodic cleaning strategy that periodically cleans up outdated checkpoints to reduce the storage burden; ii) A data staging optimization that coordinates checkpoints between local and shared file systems for performance improvement.

machine learning, artificial intelligence↗
DOE OSTI2020

Machine learning model to project the impact of COVID-19 on U.S. motor gasoline demand

Owing to the global lockdowns that resulted from the COVID-19 pandemic, fuel demand plummeted and the price of oil futures went negative in April 2020. Robust fuel demand projections are crucial to economic and energy planning and policy discussions. Here we incorporate pandemic projections and people's resulting travel and trip activities and fuel usage in a machine-learning-based model to project the US medium-term gasoline demand and study the impact of government intervention. We found that under the reference infection scenario, the US gasoline demand grows slowly after a quick rebound in May, and is unlikely to fully recover prior to October 2020. Under the reference and pessimistic scenario, continual lockdown (no reopening) could worsen the motor gasoline demand temporarily, but it helps the demand recover to a normal level quicker. Under the optimistic infection scenario, gasoline demand will recover close to the non-pandemic level by October 2020. The COVID 19 pandemic and consequent lockdown has had a substantial impact on mobility and therefore fuel demand and it is not clear when demand will recover. Ou et al. use a machine learning model that integrates health recovery scenarios to project the near-term future of gasoline demand.

COVID-19 pandemic↗
DOE OSTI2021

Physics-Informed Machine Learning Models for Predicting the Progress of Reactive-Mixing

This paper presents a physics-informed machine learning (ML) framework to construct reduced-order models (ROMs) for reactive-transport quantities of interest (QoIs) based on high-fidelity numerical simu-lations. QoIs include species decay, product yield, and degree of mixing. The ROMs for QoIs are applied to quantify and understand how the chemical species evolve over time. First, high-resolution datasets for constructing ROMs are generated by solving anisotropic reaction-di?usion equations using a non-negative finite element formulation for di?erent input parameters. The reactive-mixing model input parameters are: time-scale associated with flipping of velocity, spatial-scale controlling small/large vortex structures of velocity, perturbation parameter of the vortex-based velocity, anisotropic dispersion strength/contrast, and molecular diffusion. Second, random forests, F-test, and mutual information criterion are used to evaluate the importance of model inputs/features with respect to QoIs. We observed that anisotropic dispersion strength/contrast is the most important feature and time-scale associated with flipping of velocity is the least important feature. Third, Support Vector Machines (SVM) and Support Vector Regression (SVR) are used to construct ROMs based on the model inputs. The constructed SVR-ROMs are then used to predict scaling of QoIs. We also present estimates and inequalities on the QoIs, which inform that the species decay, mix, and produce in an exponential fashion. These inequalities also inform that a radial basis function is the most suitable kernel for the SVM/SVR models for QoIs. It is observed that R2-score for SVR-ROMs on unseen data is greater than 0.9, implying that the SVR-ROMs are able to predict the reaction-diffusion system state reasonably well. Finally, in terms of the computational cost, the proposed SVM-ROMs are O(107) times faster than running a high-fidelity finite element simulation for evaluating QoIs. This makes the proposed ML-based ROMs attractive for reactive-transport sensing and real-time monitoring applications as they are significantly faster yet reasonably accurate.

Mudunuru, Maruti K.↗
DOE OSTI2020

DLHub: Simplifying publication, discovery, and use of machine learning models in science

Machine Learning (ML) has become a critical tool enabling new methods of analysis and driving deeper understanding of phenomena across scientific disciplines. There is a growing need for "learning systems" to support various phases in the ML lifecycle. While others have focused on supporting model development, training, and inference, few have focused on the unique challenges inherent in science, such as the need to publish and share models and to serve them on a range of available computing resources. In this paper, we present the Data and Learning Hub for science (DLHub), a learning system designed to support these use cases. Specifically, DLHub enables publication of models, with descriptive metadata, persistent identifiers, and flexible access control. It packages arbitrary models into portable servable containers, and enables low-latency, distributed serving of these models on heterogeneous compute resources. In this work, we show that DLHub supports low-latency model inference comparable to other model serving systems including TensorFlow Serving, SageMaker, and Clipper, and improved performance, by up to 95%, with batching and memoization enabled. We also show that DLHub can scale to concurrently serve models on 500 containers. Finally, we describe five case studies that highlight the use of DLHub for scientific applications.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Thermodynamics-guided machine learning model for predicting convective boundary layer height and its multi-site applicability

Accurate estimation of convective boundary layer height (CBLH) is vital for weather, climate, and air quality modeling. Machine learning (ML) shows promise in CBLH prediction, but input parameter selection often lacks physical grounding, limiting generalizability. This study introduces a novel ML framework for CBLH prediction, integrating thermodynamic constraints and the diurnal CBLH cycle as an implicit physical guide. Boundary layer growth is modeled as driven by surface heat fluxes and atmospheric heat absorption represented with the low tropospheric stability, using the diurnal cycle as input and output. TPOT and AutoKeras are employed to select optimal models, validated against Doppler lidar-derived CBLH data, achieving an R 2 of 0.84 across untrained years. Comparisons of eddy covariance (ECOR) and energy balance Bowen ratio (EBBR) flux measurements show the same prediction capability. Models trained on the ARM SGP C1 site with ECOR data and tested at E37 and E39 yield R 2 values of 0.79 and 0.81, respectively, demonstrating their adaptability. The ML model trained with all sites' data slightly enhances the performance compared with ML models trained over single-site data. The interquartile range for predicted CBLH is consistently narrower than that for DL-derived CBLH, reflecting lower variability in predicted CBLH compared to DL-derived CBLH, which is influenced by additional factors, which are not well represented with the model inputs. The model's generalizability across multiple sites at the ARM SGP site demonstrates its potential for transfer to greater distances, offering a scalable approach for enhancing boundary layer parameterization in atmospheric models.

Chu, Yufei [Stony Brook Univ., NY (United States)]↗
DOE OSTI2024

Improving streamflow predictions across CONUS by integrating advanced machine learning models and diverse data

Accurate streamflow prediction is crucial to understand climate impacts on water resources and develop effective adaption strategies. A global long short-term memory (LSTM) model, using data from multiple basins, can enhance streamflow prediction, yet acquiring detailed basin attributes remains a challenge. To overcome this, we introduce the Geo-vision transformer (ViT)-LSTM model, a novel approach that enriches LSTM predictions by integrating basin attributes derived from remote sensing with a ViT architecture. Applied to 531 basins across the Contiguous United States, our method demonstrated superior prediction accuracy in both temporal and spatiotemporal extrapolation scenarios. Geo-ViT-LSTM marks a significant advancement in land surface modeling, providing a more comprehensive and effective tool for better understanding the environment responses to climate change.

Tayal, Kshitij↗
DOE OSTI2025

Multiscale Machine-Learned Modeling Infrastructure

The Multiscale Machine-Learned Modeling Infrastructure (MuMMI) is a multiscale workflow management infrastructure that can concurrently orchestrate thousands of molecular dynamics (MD) simulations operating at different time and/or length scales, spanning nanoseconds to seconds and nanometers to micrometers. MuMMI uses machine learning (backed by biology experiments) to guide a massive ensemble of MD simulations that capture biologically relevant time and length scales with unprecedented resolution. MuMMI supports multiple MD codes such as GROMACS and ddcMD and can be fully deployed using the HPC package manager Spack. MuMMI has been used in many publications to run hundreds of thousands simulations, leading to significant biology breakthroughs.

Di Natale, Francesco [Lawrence Livermore National ↗
DOE OSTI2022

Estimating mass-absorption cross-section of ambient black carbon aerosols: theoretical, empirical, and machine learning models

The mass-absorption cross-section of black carbon (MAC BC ) is an essential parameter to link the atmospheric concentration of black carbon (BC) with its radiative forcing. When a direct calculation of MAC BC based on observations of aerosol light absorption and BC mass concentration is impossible, we rely on modeling and simulations to estimate MAC BC , but currently, there is no consensus model that can be relied on for accurate predictions across all atmospheric environments when BC particles have different coating thicknesses. Here, we applied five MAC BC prediction models (including three light scattering theories, an empirical model based on observations of particle mass concentrations, and a machine learning model developed in our previous work) to aerosols from three Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) field campaigns. While many studies have found that increasing the complexity of the models helps to constrain biases of the estimated MAC BC , our effort is to evaluate the models based on the criteria of simplicity and accuracy. We find that our machine learning model (support vector machine for regression, SVM) generally performs well across all DOE ARM field campaign data, while the accuracy of core-shell Mie theory depends on the bias correction algorithm applied to filter-based light absorption data. Generally, the empirical model for internally-mixed particles that we considered tends to over-predict MAC BC , while Mie theory for externally-mixed particles tends to under-predict MAC BC . An examination of the influence of coating material on BC cores suggests that the performance of our current SVM model is degraded when the BC is thickly-coated (e.g., it has undergone aging and mixing with other materials in the atmosphere).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Accelerating multilevel Markov Chain Monte Carlo using machine learning models

Here, this work presents an efficient approach for accelerating multilevel Markov Chain Monte Carlo (MCMC) sampling for large-scale problems using low-fidelity machine learning models. While conventional techniques for large-scale Bayesian inference often substitute computationally expensive high-fidelity models with machine learning models, thereby introducing approximation errors, our approach offers a computationally efficient alternative by augmenting high-fidelity models with low-fidelity ones within a hierarchical framework. The multilevel approach utilizes the low-fidelity machine learning model (MLM) for inexpensive evaluation of proposed samples thereby improving the acceptance of samples by the high-fidelity model. The hierarchy in our multilevel algorithm is derived from geometric multigrid hierarchy. We utilize an MLM to accelerate the coarse level sampling. Training machine learning model for the coarsest level significantly reduces the computational cost associated with generating training data and training the model. We present an MCMC algorithm to accelerate the coarsest level sampling using MLM and account for the approximation error introduced. We provide theoretical proofs of detailed balance and demonstrate that our multilevel approach constitutes a consistent MCMC algorithm. Additionally, we derive the expression for cost reduction due to machine learning model to facilitate cost analysis of the hierarchical sampling algorithm. Our technique is demonstrated on a standard benchmark inference problem in groundwater flow, where we estimate the probability density of a quantity of interest using a four-level MCMC algorithm. Our proposed algorithm accelerates multilevel sampling by a factor of two while achieving similar accuracy compared to sampling using the standard multilevel algorithm.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗