Engineering Papers⌕ Search

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.

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

At least 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Accelerating science: The usage of commercial clouds in ATLAS Distributed Computing

The ATLAS experiment at CERN is one of the largest scientific machines built to date and will have ever growing computing needs as the Large Hadron Collider collects an increasingly larger volume of data over the next 20 years. ATLAS is conducting R&D projects on Amazon Web Services and Google Cloud as complementary resources for distributed computing, focusing on some of the key features of commercial clouds: lightweight operation, elasticity and availability of multiple chip architectures. The proof of concept phases have concluded with the cloud-native, vendoragnostic integration with the experiment’s data and workload management frameworks. Google Cloud has been used to evaluate elastic batch computing, ramping up ephemeral clusters of up to O(100k) cores to process tasks requiring quick turnaround. Amazon Web Services has been exploited for the successful physics validation of the Athena simulation software on ARM processors. We have also set up an interactive facility for physics analysis allowing endusers to spin up private, on-demand clusters for parallel computing with up to 4 000 cores, or run GPU enabled notebooks and jobs for machine learning applications. The success of the proof of concept phases has led to the extension of the Google Cloud project, where ATLAS will study the total cost of ownership of a production cloud site during 15 months with 10k cores on average, fully integrated with distributed grid computing resources and continue the R&D projects.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

The Electron-Ion Collider - A machine that will unlock the secrets of the strongest force in nature!

The computers and smartphones we use every day depend on what we learned about the atom in the last century. All information technology – and much of our economy today – relies on understanding the electromagnetic force between the atomic nucleus and the electrons that orbit it. The science of that force is well understood, but we still know little about the microcosm within the protons and neutrons that make up the atomic nucleus. That’s where Brookhaven National Laboratory (BNL) comes in. Brookhaven National Laboratory (located in Suffolk County, NY, about 60 miles east of midtown Manhattan) was recently chosen as the building site for an Electron-Ion Collider (EIC), a one-of-a-kind nuclear physics research facility. The EIC will be a discovery machine for unlocking the secrets of the “glue” that binds the building blocks of visible matter in the universe. The machine design will take advantage of the existing and highly optimized Relativistic Heavy Ion Collider (RHIC) that’s been operating at Brookhaven Lab since 2000. Beyond sparking scientific discoveries in a new frontier of fundamental physics, the Electron-Ion Collider will trigger technological breakthroughs that have broad-ranging impact on human health and national challenges.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Hypothesis testing via AI: Generating physically interpretable models of scientific data with machine learning (Full Technical Report)

Deep learning has demonstrated an exceptional ability to solve complex tasks (an engineering success); however, it has done so at the expense of the ability to generate new knowledge (a scientific failure). We propose an alternative framework—entitled Deep Symbolic Regression (DSR)—in which artificial neural networks (NNs) rapidly generate hypotheses about physical relationships among inputs. This framework bypasses the need to interpret an NN altogether, while still leveraging the representational power of deep learning. The resulting models are tractable mathematical expressions, which are inherently and readily human interpretable and can provide insights into underlying physical phenomena. Further, we fold this methodology into the scientific process by allowing the scientist to directly integrate a priori knowledge and beliefs to accelerate learning. We demonstrate this methodology on symbolic regression—the problem of rediscovering underlying expressions describing a dataset—and achieve state-of-the-art performance across a wide variety of symbolic regression problems. Further, we generalize our DSR framework to apply to the more general class of symbolic optimization problems, in which one seeks to optimize a sequence of symbols or “tokens” under a black-box reward function. Examples of other symbolic optimization problems include neural architecture search and computational antibody design. Our generalized tool, Deep Symbolic Optimization (DSO), has been demonstrated on the task of learning symbolic control policies for reinforcement learning environments, and has been adopted as an enabling capability for computational antibody design.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

jaxhps: An elliptic PDE solver built with machine learning in mind

Elliptic partial differential equations (PDEs) can model many physical phenomena, such as electrostatics, acoustics, wave propagation, and diffusion. In scientific machine learning settings, a high-throughput PDE solver may be required to generate a training dataset, run in the inner loop of an iterative algorithm, or interface directly with a deep neural network. To provide value to machine learning users, such a PDE solver must be compatible with standard automatic differentiation frameworks, scale efficiently when run on graphics processing units (GPUs), and maintain high accuracy for a large range of input parameters. We have designed the jaxhps package with these use-cases in mind by implementing a highly efficient and accurate solver for elliptic problems with native hardware acceleration and automatic differentiation support.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Artificial Intelligence for Accelerating Nuclear Applications, Science, and Technology

Artificial intelligence (AI) and machine learning (ML) methods have had significant impacts in science and technology in recent years. These methods for generating models from datasets or logic-based algorithms that emulate aspects of human performance can similarly accelerate the fields of nuclear applications, science, and technology toward the IAEA goals of contributing to peace, health, and prosperity. In order to accomplish advances with AI in general and ML in particular across these fields, IAEA can play a significant role by establishing, hosting and curating centralised resources, including databases, adhering to FAIR (findable, accessible, interoperable and reusable) principles and Open Science best practices, providing stewardship of data sharing, supporting training efforts and development of relevant workforces, as well as enabling connections among the scientific, technology, mathematics, AI and ethics communities. Many areas can benefit from the use of AI in the realm of nuclear applications. In human health, these areas include clinical research, epidemiology, nutrition, medical imaging, radiotherapy and education of health professionals. AI-based tools are also being used to facilitate different clinical tasks in imaging, computer-assisted diagnosis in mammography and lung cancer screening programmes, and dose prediction in nuclear medicine procedures. ML methods in particular may also increase the efficiency and accuracy of the analysis of computerised tomography and dual-energy absorptiometry scans for body composition and bone analysis. The application of AI methods to nuclear and related technologies in food and agriculture can lead to significant advances and improved efficiency in the optimisation of agricultural production, food product development, management of supply chains, food safety and food authenticity control. In the water and environmental sector, AI can help inform policies to mitigate the world’s water problems. The application of AI techniques to hydrology and environmental sciences is expected to improve patterns identification and enable model predictions under a changing climate.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Artificial Intelligence and Machine Learning for Bioenergy Research: Opportunities and Challenges

The integration of artificial intelligence and machine learning (AI/ML) with automated experimentation, genomics, biosystems design, and bioprocessing technologies is poised to revolutionize scientific investigation and, particularly, bioenergy research. To identify the opportunities and challenges in this emerging research area, the U.S. Department of Energy’s (DOE) Biological and Environmental Research program (BER) and Bioenergy Technologies Office (BETO) held a joint virtual workshop on AI/ML for Bioenergy Research (AMBER) on August 23–25, 2022. These interests have since been amplified in a September 2022 Executive Order, “Advancing Biotechnology and Biomanufacturing Innovation for a Sustainable, Safe, and Secure U.S. Bioeconomy,” to promote a whole-of government approach to biotechnology development (White House 2022). Approximately 50 scientists with various backgrounds and expertise from academia, industry, and DOE national laboratories met to discuss the opportunities and challenges of AI/ML for bioenergy research. Workshop participants were tasked with assessing the potential for AI/ML and laboratory automation to advance biological understanding and engineering in general. They particularly examined how integrating AI/ML tools with laboratory automation could accelerate biosystems design and optimize biomanufacturing. Discussions included the data and computational infrastructure needed to augment biosystems design applications and the expertise and workforce development efforts urgently required to shift integrated systems toward bioenergy research more broadly. Participants discussed many existing and future applications of AI/ML for biosystems design ranging from enzymes to plants and microbes, microbiomes, and bioprocess development. They also identified three key categories of scientific and technical opportunities and challenges: high-quality data, AI/ML algorithms, and laboratory automation. Several main takeaways emerged from the workshop: 1. Numerous AI/ML and automated experimentation applications exist for a variety of DOE mission needs in energy and the environment; 2. Exemplary research grand challenges for which AI/ML could provide solutions include: building microbes and microbial communities to specifications, developing closed-loop autonomous design and control for biosystems design, and advancing scale-up and automation; 3. Lack of sufficient high-quality, annotated data hinders the development of AI/ML applications; 4. New and improved AI/ML tools are needed, particularly those meeting the specific needs of the BER and BETO research communities; 5. Trade-offs in performance, cost, and reliability exist between deploying commercially available versus building custom-developed instrumentation and software for automated or autonomous experimentation; translation of manual to automated or autonomous methods is often a nontrivial endeavor; 6. Training a new generation of young scientists who can develop and apply AI/ML tools is needed to solve long-standing scientific challenges in bioenergy research. The integration of AI/ML tools and automated experimentation represents a new data-driven research paradigm complementary to the traditional hypothesis-driven research paradigm. This paradigm accelerates design and optimization of biological systems and processes for a variety of DOE mission needs in energy and the environment. The AMBER workshop broadly explored the potential of this new paradigm for bioenergy research, of particular interest to BER and BETO, and identified key challenges and opportunities that DOE can address in the coming years by leveraging its unique capabilities and resources.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

MLCommons Science Benchmarks

Benchmarks are a cornerstone of modern machine learning practice, providing standardized eval- uations that enable reproducibility, comparison, and scientific progress. Yet, as AI systems particularly deep learning models become increasingly dynamic, traditional static benchmarking approaches are losing their relevance. Models rapidly evolve in architecture, scale, and capability; datasets shift; and deployment contexts continuously change, creating a moving target for evaluation. Without adaptive benchmarking frame- works, both scientific assessment and real-world de- ployment risk becoming misaligned with actual system behavior. Drawing on our experience from MLCommons, educa- tional initiatives, and government programs such as the DOE s Million Parameter Consortium, we identify key barriers that hinder the broader adoption and utility of benchmarking in AI. These include substantial resource demands, limited access to specialized hardware, lack of expertise in benchmark design, and uncertainty among practitioners about how to relate benchmark results to their own application domains. Moreover, current benchmarks often emphasize peak performance on leadership-class hardware, offering limited guidance for more diverse, real-world deployment scenarios. We argue that benchmarking itself must become dy- namic in order to incorporate evolving models, updated data, and heterogeneous computational platforms while maintaining transparency, reproducibility, and inter- pretability. Democratizing this process requires not only technical innovation, but also systematic educational efforts spanning undergraduate to professional levels to develop sustained expertise in benchmark design and use. Finally, benchmarks should be framed and com- municated to support application-relevant comparisons, enabling both developers and users to make informed, context-sensitive decisions. Advancing dynamic and inclusive benchmarking practices will be essential to ensure that evaluation keeps pace with the evolving AI landscape and supports responsible, reproducible, and accessible AI deployment.

Hawks, Benjamin G. [Fermilab]↗
DOE OSTI2025

Method to simultaneously facilitate all jet physics tasks

Machine learning has become an essential tool in jet physics. Due to their complex, high-dimensional nature, jets can be explored holistically by neural networks in ways that are not possible manually. However, innovations in all areas of jet physics are proceeding in parallel. We show that specially constructed machine learning models trained for a specific jet classification task can improve the accuracy, precision, or speed of all other jet physics tasks. This is demonstrated by training on a particular multiclass generation and classification task and then using the learned representation for different generation and classification tasks, for datasets with a different (full) detector simulation, for jets from a different collision system ($pp$ versus $ep$), for generative models, for likelihood ratio estimation, and for anomaly detection. We consider our omnilearn approach thus as a jet-physics foundation model. It is made publicly available for use in any area where state-of-the-art precision is required for analyses involving jets and their substructure.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Green AI: Insights Into Deep Learning's Looming Energy Efficiency Crisis

As demands grow to integrate artificial intelligence into every aspect of industry, commerce, and life, deep learning's exploding energy cost has become a looming crisis, making AI systems a salient energy-efficiency challenge. One might expect that doubling a neural network's size would halve its error rate, or at least allow it to achieve greater performance given the same amount of time and energy. I will present clear and substantial scientific evidence which indicates that not only is this intuition wildly wrong, but that neural networks scale so poorly that to increase deep learning performance by only a small fraction can easily require an order of magnitude or more increase in computational resources and energy. Further, the marginal trade-off price of to increase model performance rapidly explodes as performance targets are increased. To address this challenge, I will provide a toolkit of techniques that can be applied today to mitigate the inefficiency of modern deep learning. And, I will conclude by illuminating a practical path forward towards efficient, Green AI.

artificial intelligence↗
DOE OSTI2025

Optimal Transport as a Tool for Scientific Discovery in Radiation Biology

This report summarizes findings from research conducted for the “Exploration of the Poten tial for Artificial Intelligence and Machine Learning to Advance Low-Dose Radiation Biology Re search” (RadBio-AI) program, supported by the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, under Awards KP1601011/FWP CC121 and KP1601017/FWP CC121. The research reported here was undertaken in an effort to assess the potential of optimal measure transport methods as components within the larger scope of a com putational framework envisioned to support research in the radiation biology domain. Within this effort, our interest centered on enabling a unified generic framework where probabilistic modeling, inference, and statistical learning can be carried out for a wide range of data distributions. As described next in Section 1 (and in more detail in our original publication), optimal measure transport offers the possibility of such unified approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Portable, heterogeneous ensemble workflows at scale using libEnsemble

libEnsemble is a Python-based toolkit for running dynamic ensembles, developed as part of the DOE Exascale Computing Project. The toolkit utilizes a unique generator–simulator–allocator paradigm, where generators produce input for simulators, simulators evaluate those inputs, and allocators decide whether and when a simulator or generator should be called. The generator steers the ensemble based on simulation results. Generators may, for example, apply methods for numerical optimization, machine learning, or statistical calibration. libEnsemble communicates between a manager and workers. Flexibility is provided through multiple manager–worker communication substrates each of which has different benefits. These include Python’s multiprocessing, mpi4py, and TCP. Multisite ensembles are supported using Balsam or Globus Compute. We overview the unique characteristics of libEnsemble as well as current and potential interoperability with other packages in the workflow ecosystem. We highlight libEnsemble’s dynamic resource features: libEnsemble can detect system resources, such as available nodes, cores, and GPUs, and assign these in a portable way. These features allow users to specify the number of processors and GPUs required for each simulation; and resources will be automatically assigned on a wide range of systems, including Frontier, Aurora, and Perlmutter. Such ensembles can include multiple simulation types, some using GPUs and others using only CPUs, sharing nodes for maximum efficiency. We also describe the benefits of libEnsemble’s generator–simulator coupling, which easily exposes to the user the ability to cancel, and portably kill, running simulations based on models that are updated with intermediate simulation output. We demonstrate libEnsemble’s capabilities, scalability, and scientific impact via a Gaussian process surrogate training problem for the longitudinal density profile at the exit of a plasma accelerator stage. In conclusion, the study uses gpCAM for the surrogate model and employs either Wake-T or WarpX simulations, highlighting efficient use of resources that can easily extend to exascale.

Dynamic ensembles↗
DOE OSTI2022

Technical Characterization and Benefit Evaluation of 5G-Enabled Grid Data Transport and Applications

This report summarizes the Year 1 work of Pacific Northwest National Laboratory’s (PNNL’s) 5G Fabricated Resource and Asset Management Encompassment for energy infrastructure (Energy FRAME) project funded by the Department of Energy Office of Science’s Advanced Scientific Computing Research Program. 5G is a breakthrough technology that enables a fully mobile and connected society, and a 5G-enabled digital continuum will be one of the critical foundations for a clean energy economy and grid modernization. In collaboration with PNNL’s Advanced Wireless Communication team and Center for Advanced Technology Evaluation team, the project team has been evaluating the system performance of 5G testbeds in the PNNL 5G Innovation Studio, and has formulated a co-simulation test case of power system transmission, distribution, and communication (T&D&C) networks considering 5G technology and high penetration of distributed energy resources. The methodology developed in the 5G Energy FRAME project can be customized to fit different future grid scenarios to evaluate multiple (dynamic) configurations (computing, sensing, communication, environment) for different stakeholders. In summary, our main technical highlights in project Year 1 are as follows: 1) Technical characterization of 5G standalone architectures, 2) Formulation of co-simulation test case of T&D&C networks embedded with 5G, 3) Initial benefit evaluation of 5G communication platform for grid use cases, and 4) Additional extended discussions on edge computing, artificial intelligence and machine learning, and high-performance computing and cloud computing adoptions. In addition, a collection of system performance data is shared through the publicly available weblink, https://www.pnnl.gov/projects/5g-energy-frame/publications

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRSDate not supplied

Open Science for Life in Space: Data Sharing and Tools for Knowledge Discovery

The next era in human space exploration is rapidly approaching and will require the use of countermeasures to deep space health hazards. The development of countermeasures (or, the re-purposing of existing agents) will be highly dependent on our understanding of basic biological responses to space stressors (e.g. ionizing radiation, altered gravitational fields, altered day-night cycles, confinement, isolation, hostile-closed environments, distance-duration from Earth, exposure to celestial regolith, etc.). The fast-growing array of space biological data, which in the past was simply archived after minimal analysis, holds great potential if it can be reorganized and formatted for Open Science. Organizing the data for such analysis is a challenge because of its diverse nature (molecular, cellular, tissue, imaging, whole organism and behavior). We will discuss here several strategies that NASA’s Biological and Physical Science Division has put in place to maximize the return on investment for spaceflight bioscience data. Open Science, as a scientific philosophy, is the concept that the more people who have access to the data, the more knowledge will be gained from it. This guiding principle led NASA to develop GeneLab in 2015. GeneLab houses spaceflight and relevant ground-based multi-omics data, and has grown to ~400 transcriptomic, proteomic, metabolomic and epigenomic datasets from plant, rodent, small animal, and microbial space experiments. GeneLab provides users with various tools for data analysis and a visualization portal that allows users to interact with gene expression data from space-related ‘omics experiments. Open Science is also about building scientific communities, and with this spirit in mind, GeneLab has spawned several Analysis Working Groups (AWGs), comprised of more than 200 volunteer scientists. The AWGs initially provided feedback on the processing pipeline and metadata ‘omics standards for GeneLab. Over the last few years, they have become a community-driven science enterprise, engaging in large meta-analysis of GeneLab datasets, resulting in 10 publications (beyond the originally submitted research). Overall, the Open Science nature of GeneLab has resulted in a high degree of data re-use, resulting in 38 additional publications derived from the original 67 publication over the past four years. The enormous success and knowledge gained from GeneLab has led to a collection of sister NASA “Open Science Data Repositories (OSDR)” and research support groups. These include the NASA Ames Life Sciences Data Archive (ALSDA), the NASA Biological Institutional Scientific Collection (NBISC), and the Biospecimen Sharing Program (BSP). All are adopting the GeneLab data architecture system to maximize open-access, find-ability, accessibility, interoperability, and reusability (FAIR). ALSDA collects and curates phenotypic-physiological bioimaging-behavioral data from space and space-relevant non-human experiments, oftentimes coming from the same omics-associated experimental datasets found in GeneLab. Since 2021, a community of ~100 researchers have rallied around ALSDA, to provide feedback in a new ALSDA AWG focused on phenotypic-physiological investigation-sample-assay metadata standards (e.g., Micro-Computed Tomography, Light/Fluorescence Microscopy, Western Blot, Flow Cytometry, Novel Object Recognition, Elevated Plus Maze, etc. of ~50 assays collected). These standards are part of a new single point-of-entry data submission portal for all non-human Space Biology and Human Research Program principal investigators, to submit, curate, and share their research data. With open-access space biological data now collected and curated together with rich metadata, and with the potential for linkage to “big data” from the international biological and medical communities (NIH, EBI, etc.), the artificial intelligence and machine learning (AI/ML) era has started for Space Biology. Several other talks will cover these topics in this conference.

life sciences↗
NASA NTRSDate not supplied

Open Science for Life in Space: Data Sharing and Tools for Knowledge Discovery

The next era in human space exploration is rapidly approaching and will require the use of countermeasures to deep space health hazards. The development of countermeasures (or, there-purposing of existing agents) will be highly dependent on our understanding of basic biological responses to space stressors (e.g. ionizing radiation, altered gravitational fields, altered day-night cycles, confinement, isolation, hostile-closed environments, distance-duration from Earth, exposure to celestial regolith, etc.). The fast-growing array of space biological data, which in the past was simply archived after minimal analysis, holds great potential if it can be reorganized and formatted for Open Science. Organizing the data for such analysis is a challenge because of its diverse nature (molecular, cellular, tissue, imaging, whole organism and behavior). We will discuss here several strategies that NASA's Biological and Physical Science Division has put in place to maximize the return on investment for spaceflight bioscience data. Open Science, as a scientific philosophy, is the concept that the more people who have access to the data, the more knowledge will be gained from it. This guiding principle led NASA to develop GeneLab in 2015. GeneLab houses spaceflight and relevant ground-based multi-omics data, and has grown to ~400 transcriptomatic, proteomic, metabolomic and epigenomic datasets from plant, rodent, small animal, and microbial space experiments. GeneLab provides users with various tools for data analysis and a visualization portal that allows users to interact with gene expression data from space-related 'omics experiments. Open Science is also about building scientific communities, and with this spirit in mind, GeneLab has spawned several Analysis Working Groups (AWGs), comprised of more than 200 volunteer scientists. The AWGs initially provided feedback on the processing pipeline and metadata 'omics standards for GeneLab. Over the last few years, they have become a community-driven science enterprise, engaging in large meta-analysis of GeneLab datasets, resulting in 10 publications (beyond the originally submitted research). Overall, the Open Science nature of GeneLab has resulted in a high degree of data-use, resulting in 40 enabled publications by open data. The enormous success and knowledge gained from GeneLab has led to a collection of sister NASA "Open Science Data Repositories (OSDR)" and research support groups. These include the NASA Ames Life Sciences Data Archive (ALSDA), the NASA Biological Institutional Scientific Collection (NBISC), and the Biospecimen Sharing Program (BSP). All are adopting the GeneLab data architecture system to maximize open-access, find-ability, accessibility, interoperability, and reusability (FAIR). ALSDA collects and curates phenotypic-physiological bioimaging-behavioral data from space and space-relevant non-human experiments, oftentimes coming from the same omics-associated experimental datasets found in GeneLab. Since 2021, a community of ~100 researchers have rallied around ALSDA, to provide feedback in a new ALSDA AWG focused on phenotypic-physiological investigation-sample-assay metadata standards (e.g., Micro-Computed Tomography, Light/Flourescence Microscopy, Western Blot, Flow Cytometry, Novel Object Recognition, Elevated Plus Maze, etc. of ~50 assays collected). These standards are part of a new single point-of-entry data submission portal for all non-human Space Biology and Human Research Program principal investigators, to submit, curate, and share their research data. With open-access space biological data now collected and curated together with rich metadata, and with the potential for linkage to "big data" from the international biological and medical communities (NIH, EBI, etc.), the artificial intelligence and machine learning (AI/ML) era has started for Space Biology.

omics↗
DOE OSTI2021

End-to-End Differentiable Modeling and Management of the Environment

Focal Area: (2) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization. We emphasize the importance of leveraging optimization techniques from AI/machine learning (ML) to solve challenging problems in Earth system modeling. Science Challenge: Automatic differentiation has had a transformative effect on ML by allowing the calculation of gradients of arbitrary functions in an incredibly large class of models. We can potentially realize similar improvements in parameter estimation and control for Earth system models (ESMs) by reimplementing them in computational frameworks from ML. Practitioners working with large (>10 7 parameters) models in ML and AI can obtain good predictive performance in a range of spatiotemporal tasks by making use of optimization via stochastic gradient descent and incorporating prior knowledge at multiple levels. We propose writing ESMs in open-source computational frameworks such as Torch, Tensorflow, and JAX to greatly expand the scope of environmental forecasting and management challenges, which can be addressed by leveraging automatic differentiation and gradient descent-like algorithms. We do not call for a wholesale replacement of physical models with data-driven surrogates, but rather advocate for interleaving physical and empirical equations in a manner that is most faithful to the extent of our scientific knowledge and observational data. Central to this topic is the merging of differentiable physical simulations with differentiable optimization layers, which are now both beginning to come to the forefront.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Opportunities and Challenges from Artificial Intelligence and Machine Learning for the Advancement of Science, Technology, and the Office of Science Missions

In February 2019, the President signed Executive Order 13859, Maintaining American Leadership in Artificial Intelligence. This order launched the American Artificial Intelligence Initiative, a concerted effort to promote and protect AI technology and innovation in the United States. The Initiative implements a government-wide strategy in collaboration and engagement with the private sector, academia, the public, and like-minded international partners. Among other actions, key directives in the Initiative called for Federal agencies to: Prioritize AI research and development investments, Enhance access to high-quality cyberinfrastructure and data, Ensure that the US maintains an international leadership role in the development of technical standards for AI, and Provide education and training opportunities to prepare the American workforce for the new era of AI. The mission of the Department of Energy (DOE) is to ensure America’s security and prosperity by addressing its energy, environmental, and nuclear challenges through transformative science and technology solutions. In terms of Science and Innovation, the DOE’s mission is to maintain a vibrant US effort in science and engineering as a cornerstone of our economic prosperity with clear leadership in strategic areas. From July to October in 2019, the Argonne, Oak Ridge, and Berkeley National Laboratories hosted a series of four AI for Science Town Hall meetings in Chicago, Oak Ridge, Berkeley, and Washington DC. The four meetings were attended by over 1300 scientists from the 17 DOE Labs, 39 companies, and over 90 universities. The goal of the Town Hall series was ‘to examine scientific opportunities in the areas of artificial intelligence, Big Data, and high-performance computing (HPC) in the next decade, and to capture the big ideas, grand challenges, and next steps to realizing these.’ The discussions at the meetings were captured in the final report of the AI for Science Town Hall meetings.

42 ENGINEERING↗
DOE OSTI2024

Spin-Controllable Dynamics in Defect-Engineered Carbon Nanotubes as Single Photon Emitters: Data-Driven Modeling and Computations

Quantum technologies, such as quantum computing and sensing, require efficient single-photon emission (SPE) sources that operate at room temperature in telecom wavelengths. While several materials can serve as SPE sources, no single platform meets all the criteria for efficiency, ambient operation, and scalability. Single-walled carbon nanotubes (SWCNTs) with covalently attached molecules offer a promising solution. Their SPE can be easily tuned via modifications of the SWCNT's diameter, chirality, and bonded molecules, enabling emission across near-IR to telecom wavelengths at ambient conditions. However, to fully realize the potential of SWCNTs and unlock their quantum capabilities, a deeper understanding of how structural defects from molecular adducts affect their emission and competing photoexcited processes is essential. To address this gap in our knowledge, this project combined quantum chemistry calculations with data-driven methods of cheminformatics (QSAR) and machine learning (ML). The developed computational approaches have provided several design strategies for covalent functionalization of SWCNTs to improve their optical response. The collaboration with Los Alamos National Lab (LANL) enabled direct comparison of computational and experimental data, facilitating method validation. This partnership was enhanced through access to LANL's Center for Integrated Nanotechnologies (CINT) utilizing User Facility Program and summer internships, which provided three NDSU graduate students with hands-on experience at LANL. The outcomes of this project included (1) Advancing the current stage of computational methods in accurate modeling of non-adiabatic spin-dependent photoexcited dynamics and its applicability to nanosystems consisting of thousands of atoms, realized as open-access codes linked to existing DFT-based software; (2) Establishing the relationship between the structure of adducts and SWCNTs and intrinsic excitonic and spin properties of defect states for guiding novel synthetic strategies and experimental probes of chemically functionalized SWCNTs as near-IR emitting materials; (3) Generating virtual libraries of hypothetical functionalized SWCNTs for virtual screening of their chemical structures and optical properties, leveraging new functionalities of SWCNTs; (4) Offering a unique experience for NDSU graduate students that prepared them for future scientific careers related to materials modeling and big data processing. These results were summarized in 12 published journal papers and 3 recently submitted papers. One of a key finding is that the position of defect sites on the SWCNT surface primarily drives the emission redshift (up to 100 meV), while the polarity of the defect-inducing molecules has a much smaller effect (~10 meV). However, the electron-donating or withdrawing properties of a molecule influence selecting reactivity of defect sites. These insights important for optimizing synthetic protocols for desired emissions in SWCNTs. We also revealed that the interaction between two defects at various positions on the SWCNT enhances the redshift and optical activity of states, favoring strong near-IR emission. This suggests that manipulations in defect concentrations is a promising strategy for controlling efficient emission. Mostly important, the defect position was found controllable by the spin states of photoexcited intermediates: Excited aromatic molecules form ortho defects with SWCNTs at their singlet states in the presence of oxygen, while oxygen-free conditions favor para defects via the triplet-state mechanism. Additionally, a heat-activated [2+2] cycloaddition reaction facilitates divalent defect formation with fewer bonding positions that narrows emission bands. These groundbreaking findings have been experimentally validated and significantly advance our understanding of defect chemistry in SWCNTs. Using a novel encoding technique and 3D-MoRSE descriptors, we developed highly accurate ML/QSAR models to predict both the 3D structure and optical properties of SWCNTs with chemical defects. This model enabled the creation of a virtual library of 125,556 structures, providing new insights into the relationship between SWCNT-defect structure and emission.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2021

AI-based design of a nuclear reactor core

The authors developed an artificial intelligence (AI)-based algorithm for the design and optimization of a nuclear reactor core based on a flexible geometry and demonstrated a 3× improvement in the selected performance metric: temperature peaking factor. The rapid development of advanced, and specifically, additive manufacturing (3-D printing) and its introduction into advanced nuclear core design through the Transformational Challenge Reactor program have presented the opportunity to explore the arbitrary geometry design of nuclear-heated structures. The primary challenge is that the arbitrary geometry design space is vast and requires the computational evaluation of many candidate designs, and the multiphysics simulation of nuclear systems is very time-intensive. Therefore, the authors developed a machine learning-based multiphysics emulator and evaluated thousands of candidate geometries on Summit, Oak Ridge National Laboratory’s leadership class supercomputer. The results presented in this work demonstrate temperature distribution smoothing in a nuclear reactor core through the manipulation of the geometry, which is traditionally achieved in light water reactors through variable assembly loading in the axial direction and fuel shuffling during refueling in the radial direction. The conclusions discuss the future implications for nuclear systems design with arbitrary geometry and the potential for AI-based autonomous design algorithms.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗