SEARCH · Engineering Papers

Results for “machine learning for scientific computing”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 235 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Integrating Ultra-Coarse-Grained Protein Models into Accessible Workflows for Multiscale Molecular Dynamics

To capture protein conformational transitions using molecular dynamics (MD), several simulation resolutions covering different spatial and temporal scales are typically needed. All-atom (AA) simulations provide fine resolution, but are computationally infeasible for large systems over longer durations. Coarse-grained (CG) and ultra-coarse-grained (UCG) models have a lower resolution and computational cost while still being able to conserve essential protein features. Prior work on a Multiscale Machinelearned Modeling Infrastructure (MuMMI) combined both AA and CG simulations to study RAS-RAF protein interactions, leveraging CG models for longer time scales and using AA to investigate unusual conformations in greater detail. However, MuMMI is still resource-intensive, and this study aims to maximize exploration of the protein conformational space while reducing computational cost. In this paper, we build on prior work that integrates UCG models based on heterogeneous elastic network modeling (hENM) into the MuMMI workflow. We demonstrate that UCG models enable accurate sampling of protein conformations, focusing on simulating RAS-RAF protein interactions. Using higher-resolution CG Martini simulation data, we can automatically refine intramolecular interactions in UCG models. We present a scalable Python package that uses fluctuations observed in higher-resolution CG Martini simulations to estimate bond coefficients of the UCG model. We built novel machine learning-based backmapping methods to recover more detailed CG Martini structures from UCG structures, using diffusion models to learn the mapping between scales. Finally, we present UCG-mini-MuMMI, an accessible and less compute-intensive version of MuMMI as a resource for the scientific community. Incorporating UCG models into MD studies is applicable to a broad range of systems and proteins, and our study offers insights into the advantages and limitations of these methods.

Chemical structure↗

DOE OSTI2021

Characterizing Machine Learning I/O Workloads on Leadership Scale HPC Systems

High performance computing (HPC) is no longer solely limited to traditional workloads such as simulation and modeling. With the increase in the popularity of machine learning (ML) and deep learning (DL) technologies, we are observing that an increasing number of HPC users are incorporating ML methods into their workflow and scientific discovery processes, across a wide spectrum of science domains such as biology, earth science, and physics. This gives rise to a diverse set of I/O patterns than the traditional checkpoint/restart-based HPC I/O behavior. The details of the I/O characteristics of such ML I/O workloads have not been studied extensively for large-scale leadership HPC systems. This paper aims to fill that gap by providing an in-depth analysis to gain an understanding of the I/O behavior of ML I/O workloads using darshan - an I/O characterization tool designed for lightweight tracing and profiling. We study the darshan logs of more than 23, 000 HPC ML I/O jobs over a time period of one year running on Summit - the second-fastest supercomputer in the world. This paper provides a systematic I/O characterization of ML I/O jobs running on a leadership scale supercomputer to understand how the I/O behavior differs across science domains and the scale of workloads, and analyze the usage of parallel file system and burst buffer by ML I/O workloads.

Paul, Arnab↗

DOE OSTI2021

A Confidence-Guided Technique for Tracking Time-Varying Features

Application scientists often employ feature tracking algorithms to capture the temporal evolution of various features in their simulation data. However, as the complexity of the scientific features is increasing with the advanced simulation modeling techniques, quantification of reliability of the feature tracking algorithms is becoming important. One of the desired requirements for any robust feature tracking algorithm is to estimate its confidence during each tracking step so that the results obtained can be interpreted without any ambiguity. To address this, we develop a confidence-guided feature tracking algorithm that allows reliable tracking of user-selected features and presents the tracking dynamics using a graph-based visualization along with the spatial visualization of the tracked feature. Here, the efficacy of the proposed method is demonstrated by applying it to two scientific datasets containing different types of time-varying features.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

Applications and Techniques for Fast Machine Learning in Science

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

Data imbalance in drug response prediction: multi-objective optimization approach in deep learning setting

Abstract Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

Biochemistry & Molecular Biology↗

DOE OSTI2021

Co-design Center for Exascale Machine Learning Technologies (ExaLearn)

We report rapid growth in data, computational methods, and computing power is driving a remarkable revolution in what variously is termed machine learning (ML), statistical learning, computational learning, and artificial intelligence. In addition to highly visible successes in machine-based natural language translation, playing the game Go, and self-driving cars, these new technologies also have profound implications for computational and experimental science and engineering, as well as for the exascale computing systems that the Department of Energy (DOE) is developing to support those disciplines. Not only do these learning technologies open up exciting opportunities for scientific discovery on exascale systems, they also appear poised to have important implications for the design and use of exascale computers themselves, including high-performance computing (HPC) for ML and ML for HPC. The overarching goal of the ExaLearn co-design project is to provide exascale ML software for use by Exascale Computing Project (ECP) applications, other ECP co-design centers, and DOE experimental facilities and leadership class computing facilities.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Accuracy, transferability, and computational efficiency of interatomic potentials for simulations of carbon under extreme conditions

Large-scale atomistic molecular dynamics (MD) simulations provide an exceptional opportunity to advance the fundamental understanding of carbon under extreme conditions of high pressures and temperatures. However, the fidelity of these simulations depends heavily on the accuracy of classical interatomic potentials governing the dynamics of many-atom systems. Here, this study critically assesses several popular empirical potentials for carbon, as well as machine learning interatomic potentials (MLIPs), in their ability to simulate a range of physical properties at high pressures and temperatures, including the diamond equation of state, its melting line, shock Hugoniot, uniaxial compressions, and the structure of liquid carbon. Empirical potentials fail to accurately predict the behavior of carbon under high pressure–temperature conditions. In contrast, MLIPs demonstrate quantum accuracy, with Spectral Neighbor Analysis Potential (SNAP) and atomic cluster expansion (ACE) being the most accurate in reproducing the density functional theory results. ACE displays remarkable transferability despite not being specifically trained for extreme conditions. Furthermore, ACE and SNAP exhibit superior computational performance on graphics processing unit-based systems in billion atom MD simulations, with SNAP emerging as the fastest. In addition to offering practical guidance in selecting an interatomic potential with a fine balance of accuracy, transferability, and computational efficiency, this work also highlights transformative opportunities for groundbreaking scientific discoveries facilitated by quantum-accurate MD simulations with MLIPs on emerging exascale supercomputers.

36 MATERIALS SCIENCE↗

DOE OSTI2026

Frameworks, Algorithms, and Scalable Technologies for Mathematics (FASTMath) SciDAC Institute

As computational models scale to larger computers, the rate at which they produce data has far outstripped the same computers ability to write that data and further the file systems ability to store that data. Almost all of the SciDAC applications, but especially those related to fusion solve very large scale PDEs whose scientific output his impacted by this problem. To gain access to dynamics in an exascale simulation that are not identifiable a priori and to make that dynamical data available to machine learning requires fundamental research in the area of in situ data data analytics. Here data analytics includes compression, visualization, uncertainty quantification, and machine learning. This in situ data analytics will enable on-the-fly spatial and temporal compression of solution dynamics, expose that space-time compressed field to machine learning algorithms that have been specialized to work with dynamically evolving data (existing machine learning algorithms treat data sets as static), greatly improving the opportunity for machine learning to provide feedback to the compression, all within an ongoing simulation, without the need to write data to files. The same concepts are also being applied to uncertainty quantification and multi-fidelity modeling which have similar needs for spatial and temporal compression of the ongoing exascale simulation to perform either without the typical, unacceptable writing of data to files.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Multi-scale Multi-physics Scientific Machine Learning for Water Cycle Extreme Events Identification, Labelling, Representation, and Characterization

Impacts of climate are usually felt through extreme events such as droughts, floods, thunderstorms, windstorms, wildfires, and so on, that are intimately tied to the water cycle. Predicting the frequency and severity of extreme events under climate change remains a significant challenge; meanwhile, the mechanisms and impacts of these extremes are far from well understood. There are several major science challenges: (1) Lack of labelled extreme events data and missing standards in defining extremes; (2) Computational demand of high-resolution ensemble climate modeling; (3) Modeling the multiscale multi-physics hierarchical structure of compound extremes; (4) Lack of understanding of mechanisms of extreme events; (5) Large uncertainty in extreme events impacts on infrastructure; (6) Subjective assessment of weather-related risk from seasonal to multi-decadal time scales and lack of metrics for risk assessment and mitigation control.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Revolutionizing Energy Storage: AI, Automation, and Advanced Modeling as Catalysts for Next-Generation Breakthroughs

The Presidential Symposium (PRES) at the 2025 Fall Meeting, hosted by the President’s Office and Energy and Fuels Division, American Chemical Society (ACS) in Washington, DC, brought together a diverse group of chemists, engineers, and materials scientists working in battery materials & systems, automation and artificial intelligence from academia, industry, and national laboratories. The accelerating demand for high-performance, scalable, and sustainable energy storage has catalyzed a paradigm shift in how materials are dis-covered, devices are engineered, and systems are optimized. This Presidential Symposium, entitled “Revolutionizing Energy Storage: AI, Automation, and Advanced Modeling Driving Next-Gen Breakthroughs”, brings together global leaders to unveil transformative strategies anchored in the AAA framework: Artificial Intelligence, Automation, and Advanced Modeling. Artificial Intelligence is redefining the frontiers of energy storage by enabling predictive design, real-time optimization, and intelligent control across diverse chemistries and architectures. Automation is streamlining the synthesis, characterization, and testing of battery materials, dramatically accelerating innovation cycles and unlocking scalable solutions for grid and mobility applications. Advanced Modeling, spanning atomic to system-level scales, provides unprecedented insight into electrochemical dynamics, degradation pathways, and thermal behavior, particularly when coupled with physics-informed machine learning and digital twin technologies. Digital twins, in turn, leverage the AAA framework by integrating real-time data, physics-based models, and AI predictions into dynamic virtual replicas, enabling proactive diagnostics, optimization, and system resilience. Together, these synergistic pillars are not only re-shaping the scientific landscape but also forging a new era of reproducible, data-driven, and resilient energy storage innovation. In conclusion, this symposium marks a pivotal moment in the convergence of computational intelligence and experimental rigor, charting the course for next-generation breakthroughs in lithium-ion, solid-state, and flow battery technologies.

Artificial Intelligence (AI)↗

DOE OSTI2024

Hutchinson Trace Estimation for high-dimensional and high-order Physics-Informed Neural Networks

Physics-Informed Neural Networks (PINNs) have proven effective in solving partial differential equations (PDEs), especially when some data are available by seamlessly blending data and physics. However, extending PINNs to high-dimensional and even high-order PDEs encounters significant challenges due to the computational cost associated with automatic differentiation in the residual loss function calculation. Herein, we address the limitations of PINNs in handling high-dimensional and high-order PDEs by introducing the Hutchinson Trace Estimation (HTE) method. Starting with the second-order high-dimensional PDEs, which are ubiquitous in scientific computing, HTE is applied to transform the calculation of the entire Hessian matrix into a Hessian vector product (HVP). This approach not only alleviates the computational bottleneck via Taylor-mode automatic differentiation but also significantly reduces memory consumption from the Hessian matrix to an HVP’s scalar output. We further showcase HTE’s convergence to the original PINN loss and its unbiased behavior under specific conditions. Comparisons with the Stochastic Dimension Gradient Descent (SDGD) highlight the distinct advantages of HTE, particularly in scenarios with significant variability and variance among dimensions. We further extend the application of HTE to higher-order and higher-dimensional PDEs, specifically addressing the biharmonic equation. By employing tensor-vector products (TVP), HTE efficiently computes the colossal tensor associated with the fourth-order high-dimensional biharmonic equation, saving memory and enabling rapid computation. The effectiveness of HTE is illustrated through experimental setups, demonstrating comparable convergence rates with SDGD under memory and speed constraints. Additionally, HTE proves valuable in accelerating the Gradient-Enhanced PINN (gPINN) version as well as the Biharmonic equation. Overall, HTE opens up a new capability in scientific machine learning for tackling high-order and high-dimensional PDEs.

Curse of dimensionality↗

DOE OSTI2023

Mixed-Precision S/DGEMM Using the TF32 and TF64 Frameworks on Low-Precision AI Tensor Cores

Using NVIDIA graphics processing units (GPUs) equipped with Tensor Cores has enabled the significant acceleration of general matrix multiplication (GEMM) for applications in machine learning (ML) and artificial intelligence (AI) and in high-performance computing (HPC) generally. The use of such power-efficient, specialized accelerators can provide a performance increase between 8 × and 20 ×, albeit with a loss in precision. However, a high level of precision is required in many large scientific and HPC applications, and computing in single or double precision is still necessary for many of these applications to maintain accuracy. Fortunately, mixed-precision methods can be employed to maintain a higher level of numerical precision while also taking advantage of the performance increases from computing with lower-precision AI cores. With this in mind, we extend the state of the art by using NVIDIA’s new TF32 framework. This new framework not only burdens some constraints of the previous frameworks, such as costly 32 16-bit castings but also provides an equivalent precision and performance by using a much simpler approach. We also propose a new framework called TF64 that attempts double-precision arithmetic with low-precision Tensor Cores. Although this framework does not exist yet, we validated the correctness of this idea and achieved an equivalent of 64-bit precision on 32-bit hardware.

Valero Lara, Pedro↗

DOE OSTI2023

A rigorous uncertainty-aware quantification framework is essential for reproducible and replicable machine learning workflows

The capability to replicate the predictions by machine learning (ML) or artificial intelligence (AI) models and the results in scientific workflows that incorporate such ML/AI predictions is driven by a variety of factors.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Unsupervised physics-informed disentanglement of multimodal data

Here, we introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal datasets. Individual modalities are embedded into a shared latent space and fused through a product-of-experts formulation, enabling a Gaussian mixture prior to identify shared features. Sampling from clusters allows cross-modal generative modeling, with a mixture-of-experts decoder that imposes inductive biases from prior scientific knowledge and thereby imparts structured disentanglement of the latent space. This approach enables cross-modal inference and the discovery of features in high-dimensional heterogeneous datasets. Consequently, this approach provides a means to discover fingerprints in multimodal scientific datasets and to avoid traditional bottlenecks related to high-fidelity measurement and characterization of scientific datasets.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Department of Energy’s Atmospheric System Research (ASR) Program’s Workshop on the Future of Atmospheric Large Eddy Simulation (LES): Workshop Report

Large-eddy simulation (LES) is used as a tool to understand physical processes such as turbulence, aerosols, clouds, precipitation, radiation, the interactions among all these, and their interactions with the underlying surface. Over the next 10 years, LES will drive fundamental progress in open scientific questions in these areas as LES is increasingly used to gain understanding of complex interacting physical processes involving atmospheric turbulence. This growth will be driven both by scientific demand and the expansion of computational resources needed to conduct LES, and the form that the growth takes will largely be determined by how computational resources are leveraged for scientific gain. In particular, we suggest that computational resources are likely to be leveraged in two separate but not necessarily distinct ways. On one hand, growth in computational resources will allow LES to be made more routine, that is, performed more frequently, while on the other hand, the computational expense (measured in total floating point operations) afforded to individual LES will expand dramatically, allowing simulations to increase in both domain size and resolution as well as physical detail. Current U.S. Department of Energy (DOE) projects such as LES ARM Symbiotic Simulation and Observation Activity (LASSO) are leading the way in conducting routine LES, building large, public databases that are accessible for data science, sensitivity studies, and training for machine learning. LES will also become more routine as it becomes more accessible for individual researchers to address their scientific questions of interest. Scientific questions addressed by LES over the next 10 years are likely to include cloud organization and aggregation; aerosol cloud interactions and atmospheric chemistry (including geo-engineering); urban-scale LES; atmospheric extreme events, ranging from small-scale severe weather to wildfires; and ocean-wave-atmosphere interactions. Further LES-related research will likely grow significantly in areas related to societal impact studies of air quality and extreme weather events, applications to renewable energy forecasting and resource assessment, and aid in decision-making processes. The growth in the use of LES in atmospheric science research will drive the need for better physical process representations (e.g., cloud aerosol microphysics, radiation, and atmospheric chemistry) at the scales resolved by LES. To date, many of the process representations used by LES have been taken directly from coarser-resolution models. Promising methods for LES process representations include superdroplet and quadrature methods for microphysics, 3D approaches for radiation, and better representation of chemistry and aerosol processes. At LES resolution, land-atmosphere interactions for complex terrains, land cover/types, biogeochemistry, and plant canopy models are needed as an improvement beyond traditional and widely used Monin-Obuhkov similarity theory.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Department of Energy’s Atmospheric System Research (ASR) Program’s Workshop on the Future of Atmospheric Large Eddy Simulation (LES) (Workshop Report)

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Dial

A key step in almost all scientific endeavors is answering the question: Given this data I already collected, what new data do I expect will yield the most useful information toward my scientific objective? The area of (sequential) experimental design has long been investigating answers to this question, but in recent years techniques from the machine learning subfield of active learning are increasingly applied. Researchers need a simple software tool for active learning applied to experimental design that can easily integrate into their existing workflows. This computer code, Dial, provides a microservice in ORNL's INTERSECT ecosystem for active learning applied to experimental design. By being part of the INTERSECT ecosystem, Dial is simple to integrate into any INTERSECT-based workflow. Dial provides multiple backend options, where a backend is an implementation of a specific active learning method. Users can select the backend that performs best for their application. Developers can also add new backends as needed. At its core, Dial receives a set of pre-existing measurements and input parameter bounds and then recommends one or more new sets of parameters to measure. Dial also includes interfaces to other microservices in the INTERSECT ecosystem so that it can be incorporated into INTERSECT campaigns. Dial provides a simple, yet powerful interface to convert automated INTERSECT workflows into autonomous workflows that adapt based on the results that are obtained. A shared microservice for active learning prevents duplicated effort by each application team implementing its own adaptive design of experiments tool.

Drane, Lance [Oak Ridge National Laboratory (ORNL)↗

NASA NTRS1993

A pattern recognition system for locating small volvanoes in Magellan SAR images of Venus

The Magellan data set constitutes an example of the large volumes of data that today's instruments can collect, providing more detail of Venus than was previously available from Pioneer Venus, Venera 15/16, or ground-based radar observations put together. However, data analysis technology has not kept pace with data collection and storage technology. Due to the sheer size of the data, complete and comprehensive scientific analysis of such large volumes of image data is no longer feasible without the use of computational aids. Our progress towards developing a pattern recognition system for aiding in the detection and cataloging of small-scale natural features in large collections of images is reported. Combining classical image processing, machine learning, and a graphical user interface, the detection of the 'small-shield' volcanoes (less than 15km in diameter) that constitute the most abundant visible geologic feature in the more that 30,000 synthetic aperture radar (SAR) images of the surface of Venus are initially targeted. Our eventual goal is to provide a general, trainable tool for locating small-scale features where scientists specify what to look for simply by providing examples and attributes of interest to measure. This contrasts with the traditional approach of developing problem specific programs for detecting Specific patterns. The approach and initial results in the specific context of locating small volcanoes is reported. It is estimated, based on extrapolating from previous studies and knowledge of the underlying geologic processes, that there should be on the order of 10(exp 5) to 10(exp 6) of these volcanoes visible in the Magellan data. Identifying and studying these volcanoes is fundamental to a proper understanding of the geologic evolution of Venus. However, locating and parameterizing them in a manual manner is forbiddingly time-consuming. Hence, the development of techniques to partially automate this task were undertaken. The primary constraints for this particular problem are that the method must be reasonably robust and fast. Unlike most geological features, the small volcanoes of Venus can be ascribed to a basic process that produces features with a short list of readily defined characteristics differing significantly from other surface features on Venus. For pattern recognition purposes the relevant criteria include (1) a circular planimetric outline, (2) known diameter frequency distribution from preliminary studies, (3) a limited number of basic morphological shapes, and (4) the common occurrence of a single, circular summit pit at the center of the edifice.

Burl, M. C.↗