Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning for science”

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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Considerations for Introducing Artificial Intelligence into Nuclear Power Plants

Advanced computational tools and techniques such as artificial intelligence and machine learning (AI/ML) can transform the nuclear power industry. This is necessary given that the economic viability of the existing fleet is in jeopardy and its labor-centric approach to operations and maintenance. Currently, AI/ML research is being undertaken for reactor system design and analysis including fault and accident prognosis, nuclear risk analysis such as plant safety and security evaluation, and plant operations and maintenance including predictive maintenance. Applications include both existing and advanced reactor technologies with the aim of improving operational and business efficiencies. Most every aspect of the organization can benefit, from instrumentation and control, to work planning, to human-machine interactions and business management. AI/ML in nuclear can simplify complex problems and produce more effective decision-making. Nonetheless, careful consideration must be given to the implementation of an AI/ML initiative. The aims of this research are to 1) review barriers to AI/ML adoption within the nuclear power industry, and 2) suggest potential solutions. These barriers are organized along five distinct categories (Figure 1) that are interconnected. The first are historical barriers that track the industry’s development over the decades including worldwide nuclear events that shaped public perceptions. The resulting federal scrutiny and intense safety culture that emerged are discussed. Technical barriers to AI/ML adoption are considerable, and include data privacy concerns, data governance, and the current lack of AI/ML expert knowledge at the plants. The main business case barrier remains cost, but an absence of an industry-wide vision and wide-scale adoption also produces reluctance. Stakeholder readiness is reviewed with special attention given to regulatory readiness. The 5-year strategic plan for AI readiness recently published by the U.S. Nuclear Regulatory Commission is highlighted. Last, adoption barriers at the user level are addressed including the importance of user experience and explainable AI. The AI adoption barriers described here are inter-related and ideally should be addressed in a holistic fashion.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language often provides a much richer learning medium for LLMs, compared to policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates natural language reflection to learn high-level rules from trial and error. Given any AI system containing one or more LLM prompts, GEPA samples trajectories (e.g., reasoning, tool calls, and tool outputs) and reflects on them in natural language to diagnose problems, propose and test prompt updates, and combine complementary lessons from the Pareto frontier of its own attempts. As a result of GEPA's design, it can often turn even just a few rollouts into a large quality gain. Across six tasks, GEPA outperforms GRPO by 6% on average and by up to 20%, while using up to 35x fewer rollouts. GEPA also outperforms the leading prompt optimizer, MIPROv2, by over 10% (e.g., +12% accuracy on AIME-2025), and demonstrates promising results as an inference-time search strategy for code optimization. We release our code at https://github.com/gepa-ai/gepa.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Technical Basis for Advanced Artificial Intelligence and Machine Learning Adoption in Nuclear Power Plants

The research and development reported here is part of the Technology Enabled Risk-Informed Maintenance Strategy project sponsored by the U.S. Department of Energy’s Light Water Reactor Sustainability program. The primary objective of the research presented in this report is to produce a technical basis for developing explainable and trustable artificial intelligence (AI) and machine learning (ML) technologies. The technical basis will lay the foundation for addressing the technical and regulatory adoption challenges of AI/ML technologies across plant assets and the nuclear industry at scale and to achieve seamless cost-effective automation without compromising plant safety and reliability.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Multiscale ACI Satellite Database

The SATELLITE_EAGLES_PNNL NetCDF dataset contains a suite of satellite- and reanalysis-derived atmospheric and surface parameters on a regular latitude–longitude grid. The dataset includes core geophysical fields such as land fraction, aerosol optical depth at multiple wavelengths (465, 550, 667, and 865 nm), sea surface temperature, estimated inversion strength, and various thermodynamic and dynamic quantities (e.g., relative humidity, vertical velocity, boundary-layer height, and surface fluxes) from both MERRA and ERA reanalysis products, provided as daily-mean and instantaneous values. A major component of the dataset consists of MODIS-retrieved cloud microphysical properties, including cloud droplet number concentration, cloud effective radius, optical thickness, and liquid water path, provided for three compositing regimes (“All,” “Q06,” and “G18”). Corresponding cloud-top parameters—temperature, height, and pressure—along with total and domain-mean cloud fraction fields are also included. The file further integrates additional satellite data from AMSR-E (for cloud water, rain water, and surface precipitation retrievals) and CERES (for top-of-atmosphere radiative fluxes, cloud fractions, and albedo). This dataset is designed to evaluate aerosol–cloud interactions in warm clouds, emphasizing the use of MODIS for deriving cloud droplet number concentration and liquid water path statistics. The complementary satellite and reanalysis fields are co-located and time-matched to the same instantaneous MODIS observations, enabling consistent comparisons between cloud properties, aerosol loading, and large-scale meteorological conditions. The dataset is recently featured in Christensen et al. (2025), Machine Learning Reveals Strong Grid-Scale Dependence in the Satellite Nd–LWP Relationship, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2025-3850, 2025.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Structural- and Functional-Informed Machine Learning for Protein Function Prediction

In this project we aimed to extend methods for protein function prediction to include structural prediction data, and benchmark methods against existing tools. We proposed to apply the method to large metagenome datasets, and develop approaches to examine activity-based protein profiling results for protein function-structure patterns. Nitrogen cycle protein families were previously identified and are used here to provide a proof-of-principle for use of structure prediction in protein function classification.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Microstructure modeling of nuclear structural materials: Recent progress and future directions

Modeling and simulation of microstructures are essential to understand the complex responses and behaviors of nuclear materials in extreme environments. The needs to assess the extended life operation as well as the growing interest in accelerating nuclear materials development and qualification have stimulated the use of high-fidelity multiscale models aided by empirical and ab initio data. This paper reviews the role of various models across different length and time scales in investigating irradiation effects on microstructure evolution and degradation, in particular the embrittlement caused by radiation induced or enhanced formation of nanoscale chemical heterogeneities. The strength and limitations of these models, including classical rate theories, cluster dynamics, phase-field methods, and atomistic models informed by ab initio energies, are discussed with seminal examples. Challenges regarding the lack of thermo-kinetic data and theoretical treatments considering chemical complexities and magnetic excitations, as well as the stabilizing effect by excess point defects in nuclear structural materials are presented, along with potential solutions based on ab initio informed surrogate energy models and statistical sampling by Monte Carlo simulations. Further, the review then highlights the opportunities to leverage the advantages of different methods by establishing hybrid models by shared variables or coupled codes and applications. Finally, the review concludes with forward-looking remarks on how the use of physics-based models can aid the improvement of machine-learning models of property degradation and vice versa.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Rapid, antibiotic incubation-free determination of tuberculosis drug resistance using machine learning and Raman spectroscopy

Tuberculosis (TB) is the world’s deadliest infectious disease, with over 1.5 million deaths and 10 million new cases reported anually. The causative organism Mycobacterium tuberculosis (Mtb) can take nearly 40 d to culture, a required step to determine the pathogen’s antibiotic susceptibility. Both rapid identification and rapid antibiotic susceptibility testing of Mtb are essential for effective patient treatment and combating antimicrobial resistance. Here, we demonstrate a rapid, culture-free, and antibiotic incubation-free drug susceptibility test for TB using Raman spectroscopy and machine learning. We collect few-to-single-cell Raman spectra from over 25,000 cells of the Mtb complex strain Bacillus Calmette-Guérin (BCG) resistant to one of the four mainstay anti-TB drugs, isoniazid, rifampicin, moxifloxacin, and amikacin, as well as a pan-susceptible wildtype strain. By training a neural network on this data, we classify the antibiotic resistance profile of each strain, both on dried samples and on patient sputum samples. On dried samples, we achieve >98% resistant versus susceptible classification accuracy across all five BCG strains. In patient sputum samples, we achieve ~79% average classification accuracy. We develop a feature recognition algorithm in order to verify that our machine learning model is using biologically relevant spectral features to assess the resistance profiles of our mycobacterial strains. Finally, we demonstrate how this approach can be deployed in resource-limited settings by developing a low-cost, portable Raman microscope that costs <$5,000. We show how this instrument and our machine learning model enable combined microscopy and spectroscopy for accurate few-to-single-cell drug susceptibility testing of BCG.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Perspectives on Machine Learning-assisted Plasma Medicine: Towards Automated Plasma Treatment

Cold atmospheric plasmas (CAPs) have shown great promise for medical applications through their synergistic chemical, electrical, and thermal effects, which can induce therapeutic outcomes. However, safe and reproducible plasma treatment of complex biological surfaces poses a major hurdle to the widespread adoption of CAPs for medical applications. Predictive modeling of the mutual interactions between the plasma and biological surfaces and, thus, systematic approaches to quantify and predict plasma treatment outcomes remain largely elusive due to the lack of mechanistic understanding of plasma-surface interactions that can span across vastly different length-and time-scales. In addition, real-time sensing capabilities in biomedical CAP devices are often limited, which can be detrimental to plasma treatment due to the intrinsic plasma and surface variability during the treatment, as well as sensitivity to external perturbations. All of these challenges can make reproducible and effective plasma treatment of biological surfaces difficult to realize, which is further compounded by errors due to human operation of hand-held CAP devices. Machine learning and data-driven approaches can be particularly useful in addressing these challenges in three major ways: (i) data-driven modeling of hard-to-model plasma-surface interactions and plasma treatment outcomes; (ii) learning data analytics for plasma and surface diagnostics in real-time; and (iii) developing predictive controllers that enable reliable and effective CAP treatments. Furthermore, this paper discusses the promise of machine learning to accelerate plasma medicine research in these areas, toward machine learning-assisted and automated CAP treatment of complex biological surfaces.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Computationally Tractable High-Fidelity Representation of Global Hydrology in ESMs via Machine Learning Approaches to Scale-Bridging

Focal Areas: This paper responds primarily to Focal Area 2, focusing on AI techniques to improve model fidelity. Science Challenge: “Hyperresolution” [1, 2] land surface models (LSMs) running at far higher resolution than typically employed in global Earth system models (ESMs) can help answer critical questions about the water cycle and associated ecosystem and biogeochemical feedbacks. Even with all foreseeable advances in computing power and efficient solver algorithms, however, employing hyperresolution LSMs inside ESMs for studies of long-term global climate is not computationally feasible. Instead, we argue for incorporating the fidelity of hyperresolution LSMs only where and when it is needed by using machine learning approaches to scale-bridging.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Simulation and Emulation of X-Ray Diffraction from Dynamic Compression Experiments

Many important aspects of the dynamic thermo-mechanical response of materials occur at the mesoscale, i.e. a physical scale of interactions smaller than what can be adequately described by homogenous behaviors, yet larger than the scale of the atomic lattice. Concurrent advancements in computational power, continuum theory, and experimental diagnostics are enabling unprecedented understanding of such interactions. However, we cannot develop a sufficient level of confidence in such mesoscale capability until the constitutive description of the underlying constituents is reliably representative of their actual physical behavior. Therefore, there is a strong need to combine experimental, modeling, and data-science techniques to validate models of the thermomechanical response of individual single crystals. One experimental diagnostic with high potential impact to shock physics and materials science is in-situ x-ray diffraction. This paper is primarily focused on simulation of x-ray diffraction in shock physics, but with an aim toward quantifying parametric uncertainty of simulation models. Here, we develop and demonstrate a data-science and model-driven approach to constrain the parameterization of continuum models of crystal lattice deformation associated with the shock response of crystalline materials. The framework is built around the connection between continuum hydrodynamic simulations of lattice deformation and a new Bragg diffraction simulation code, BarberShop. The dynamic deformation of a crystal lattice is modeled using the DiscoFlux model within an arbitrary Lagrangian-Eulerian hydrodynamic code, FLAG. These detailed continuum simulations of lattice deformation can be computationally slow, thus a statistical model is used to emulate the evolution of lattice deformation fields in time and across the considered model parameter space. Emulated lattice deformation fields can then be generated rapidly for any combination of physics model parameters. In turn, these fields can be fed into BarberShop to realize a rapid prediction of Bragg diffraction patterns associated with particular values of physics model parameters. The framework enables parameterization of the single crystal model to obtain Bragg diffraction patterns that most closely resemble a corresponding measurement. Furthermore, the framework naturally provides sensitivities of the lattice deformation to the physics parameters. We highlight the utility of this framework through the application to a synthetic closed-loop inverse problem leading to the parameterization of a single crystal material model. As a model problem, we consider the dynamic response of the energetic molecular crystal, cyclotrimethylenetrinitramine (or RDX), under dynamic compression induced by simulated flyer plate impact experiments.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Comparative performance and technoeconomic analyses of two microalgae harvesting systems evaluated at a commercially relevant scale

Using a commercially scalable system designed for processing thousands of liters a day, here we evaluated the factors that affected the performance, energy consumption and capital/operating costs of both flocculation-based and filtration-based algal harvesting systems over a 16 month period. Coagulation efficiency was the primary driver of harvest efficiency in the flocculation-based method, while cell lysis was important for the filtration-based method. Culture (algae) age differentially influenced harvest efficiency through changes in cell fragility and stickiness. The average energy consumption of the flocculation-based method was 0.389 kWh/m 3 , while that for the filtration-based method was 4.343 kWh/m 3 . The average harvesting cost of the filtration-based method was 5.35 $\$$/m 3 , while for flocculation-based method it was 4.52 $\$$/m 3 . The concentration factor of filtration-based and flocculation-based method were 770–1086 and 407–448, respectively. For both harvesting methods, labor costs dominated and ranged from 55.84%–67.94% of total cost. Further system automation is a potential method to lower the harvesting cost. The filtration-based harvesting method could produce a better quality of algal biomass with higher concentration factors and less ash content, but needed more energy input, as compared with a flocculation-based method. This study highlights the importance of algal culture status to successful harvesting, and it also provides insight into developing more efficient harvesting technology with lower energy and capital cost.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Data reduction in deterministic neutron transport calculations using machine learning

Neutron cross section matrices for fission and scattering data are required for each material, temperature, and enrichment level to calculate the neutron transport equation accurately. Here, this information can be a limiting factor when using the multigroup discrete ordinates (S N ) method when the number of energy groups is large. Machine Learning (ML) can be used to replace the need for the cross section matrices by reproducing the function that maps the scalar flux to the scattering and fission sources. Through the use of autoencoders and Deep Jointly-Informed Neural Networks (DJINN), the data storage requirements are reduced by 94% of the original data for a 618 group problem. This is accomplished while preserving the scalar flux, maintaining generality, and decreasing wall clock times.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2021

Improvements of pre-emptive identification of particle accelerator failures using binary classifiers and dimensionality reduction

In this paper we look at the properties of the Spallation Neutron Source (SNS) Differential Beam Current Monitor (DCM) data and various methods of data transformation to improve pre-emptive detection of machine trips. In this study, the foundation of the approach is the analysis of new underlying data and understanding various properties with the goal of faster classification, higher precision and higher recall with the aim to reduce false positives as low as required. The result of the research presented in this paper are a binary classifier capable of predicting accelerator failures with millisecond classification time, 96% precision, 58% true positive and 0% false positive rate and optimization techniques enabling real-time implementations.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Accelerating scientific discoveries through data-driven innovations

Developing artificial intelligence (AI) and machine learning (ML) methods that can accelerate scientific discoveries and advance science has become one of the important research directions for the AI/ML research community. It has been gaining increasing attention from researchers in diverse scientific areas, including biomedical science, materials science, climate science, physics, chemistry, and many others. Data-driven AI/ML innovations to enable reliable predictions and optimal decision making for scientific discoveries face several critical challenges, among which are high system complexity, large search space, incomplete knowledge, and small data, all of which demand novel strategies to effectively address them. Meeting these challenges and thereby accelerating scientific discoveries and industrial innovations, calls for research that can take full advantage of the latest advances in AI/ML to integrate data-driven techniques with scientific knowledge and is able to execute them in modern high-performance computing (HPC) environments at scale. This Patterns special collection "Accelerating scientific discoveries through data-driven innovations" features articles that showcase the promising roles of AI/ML and data-driven modeling in accelerating scientific discoveries and may inspire the next wave of data-driven innovations in various scientific domains.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

In the Mix : A Workshop Merging Computational Chemistry and Electrochemistry Alongside Data Science

As chemistry expands to more complex and interdisciplinary areas, a new generation of diverse researchers must engage with science and learn effective cross-disciplinary collaboration and communication. To these ends, we designed and implemented In the Mix, a graduate student-led, two-day workshop for undergraduate students promoting collaborative science in the context of energy storage innovations. Here, the interactive workshop was designed for future and emerging researchers to gain hands-on experience with data science, computational chemistry, and electrochemistry techniques that are critical for developing materials for battery technologies. Participants also visited commercial renewable energy facilities to help them connect discovery-based research with industry and broader societal considerations. The workshop content and structure ensured that participants experienced the interrelatedness of the fields and understood the importance of collaborative research to yield scientific advances with real-world applications. An external team evaluated the workshop and participants’ perceptions of their experiences. While our research context was energy storage, the workshop goals and outcomes are applicable to other contexts. Interdisciplinary, experiential workshops are a key avenue to broadening participation in science and research, and the ideas presented here can be readily modified for other scientific contexts and/or incorporated as broader impact activities.

25 ENERGY STORAGE↗
DOE OSTI2020

Variational fast forwarding for quantum simulation beyond the coherence time

Abstract Trotterization-based, iterative approaches to quantum simulation (QS) are restricted to simulation times less than the coherence time of the quantum computer (QC), which limits their utility in the near term. Here, we present a hybrid quantum-classical algorithm, called variational fast forwarding (VFF), for decreasing the quantum circuit depth of QSs. VFF seeks an approximate diagonalization of a short-time simulation to enable longer-time simulations using a constant number of gates. Our error analysis provides two results: (1) the simulation error of VFF scales at worst linearly in the fast-forwarded simulation time, and (2) our cost function’s operational meaning as an upper bound on average-case simulation error provides a natural termination condition for VFF. We implement VFF for the Hubbard, Ising, and Heisenberg models on a simulator. In addition, we implement VFF on Rigetti’s QC to demonstrate simulation beyond the coherence time. Finally, we show how to estimate energy eigenvalues using VFF.

97 MATHEMATICS AND COMPUTING↗