Single-Node Power Demand During AI Training: Measurements on an 8-GPU NVIDIA H100 System
Not Available
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
SEARCH · Search NASA
Results for “Data 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.
Unveiling Swift Heavy Ion Track Morphology in Sr-Based High-Entropy Perovskites
The incorporation of multiple cations on a single lattice site in the high-entropy oxides is considered the key driving factor for modifying the known atomic-level response to energetic ion irradiation due to the presence of structural disorder; however, these effects are not well-understood yet. In this work, we present atomic-level insight into irradiation-induced nanoscale phase transformations in a perovskite-structured high-entropy oxide, Sr(Zr 0.2 Sn 0.2 Ti 0.2 Hf 0.2 Nb 0.2 )O 3 (Sr(HE)O 3 ), subjected to 774 MeV swift Xe heavy ions, where damage is dominated by inelastic ion−lattice interactions. While these ions generally are known to create nanoscale disordered channels, “ion tracks”, along the penetration direction in the material, this study shows the formation of discontinuous and partially recrystallized ion tracks in Sr(HE)O 3 . Compared to SrTiO 3 irradiated under identical energy loss conditions, the ion tracks in Sr(HE)O 3 exhibit significantly reduced diameters and a markedly different interfacial structure. Notably, the crystalline−amorphous interface in Sr(HE)O 3 shows minimal lattice distortion, confined to approximately 2−3 monolayers, in contrast to the extended disordered shell commonly observed in SrTiO 3 . Using in situ atomic-resolution electron microscopy, we further demonstrate that the amorphous/disordered regions within Sr(HE)O 3 ion tracks remain highly stable under electron irradiation, whereas tracks in SrTiO 3 readily recrystallize. This enhanced stability is attributed to the dominance of structural and chemical complexity arising from multiple B-site cations, which suppress defect migration and templated recrystallization driven by electronic excitations and local heating. Overall, this study highlights how high-entropy oxide chemistry fundamentally reshapes irradiation damage evolution, offering insights into defect formation and phase stability under extreme conditions.
36 MATERIALS SCIENCE↗
Transforming Energy Through Computational Excellence: NREL's Computational Science Center
Computational methods underpin advancing the science and engineering of energy efficiency, sustainable transportation, renewable power technologies, and developing a knowledge base to optimize energy systems. NREL's Computational Science Center (CSC) proudly focuses on providing the service of computing, advancing the science of computing, and enabling NREL's clean energy mission.
applied mathematics↗
Uncertainty guided online ensemble for non-stationary data streams in fusion science
Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and machine wear-and-tear. ML models assume stationary distribution and fail to maintain performance when encountered with such non-stationary data streams. Online learning techniques have been leveraged in other domains, however it has been largely unexplored for fusion applications. In this paper, we investigate online learning for continuous adaptation to drifting data streams in the prediction of Toroidal Field (TF) coils deflection at the DIII-D fusion facility. We further address the short-term performance degradation inherent to standard online learning, which arises because ground truth is unavailable at prediction time. To mitigate this issue, we propose an uncertainty-guided online ensemble framework. The method leverages the Deep Gaussian Process Approximation (DGPA) for calibrated uncertainty estimation and uses these uncertainty measures to guide a meta-algorithm that aggregates predictions from learners trained over different historical horizons. Our results show that online learning reduces prediction error by 80% compared to a static model. The online ensemble and the proposed uncertainty-guided ensemble further reduce error by approximately 6%, and 10% respectively, relative to standard single-model online learning, while also providing calibrated uncertainty estimates to support operational decision-making.
AI↗
Measure this, not that: Optimizing the cost and model-based information content of measurements
Model-based design of experiments (MBDoE) is a powerful framework for selecting and calibrating science-based mathematical models from data. Here, this work extends popular MBDoE workflows by proposing a convex mixed integer (non)linear programming (MINLP) to optimize the selection of measurements. The solver MindtPy is modified to support calculating the D-optimality objective and its gradient via an external package, scipy, using the grey-box module in Pyomo. The new approach is demonstrated in two case studies: estimating highly correlated kinetics from a batch reactor and estimating transport parameters in a large-scale rotary packed bed for CO 2 capture. Both case studies show how examining the Pareto optimal trade-offs between information content measured by A- and D-optimality versus measurement budget offers practical guidance for selecting measurements for scientific experiments.
97 MATHEMATICS AND COMPUTING↗
Supporting Information for manuscript: “A latitudinal gradient in S/G lignin monomer ratio driven by laccase in natural poplar variants”
Lignin composition plays a crucial role in plant structural integrity and environmental adaptation. However, the genetic and molecular mechanisms underlying natural variation in lignin composition remain poorly understood. This study investigates the syringyl-to-guaiacyl (S/G) lignin monomer ratio across a natural population of Populus trichocarpa spanning a latitudinal gradient along the Northwest coast of North America. By integrating biochemical, genomic, and geographic analysis, we identify key gene variants associated with S/G ratio differences. These datasets provide valuable insights into the evolutionary and functional genomics of lignin composition and serve as a resource for developing poplar variants optimized for forestry and bioenergy applications.
Poplar, lignin composition, laccases, latitude, ad↗
Modeling inter‐reader variability in clinical target volume delineation for soft tissue sarcomas using diffusion model
Abstract Background Accurate delineation of the clinical target volume (CTV) is essential in the radiotherapy treatment of soft tissue sarcomas. However, this process is subject to inter‐reader variability due to the need for clinical assessment of risk and extent of potential microscopic spread. This can lead to inconsistencies in treatment planning, potentially impacting treatment outcomes. Most existing automatic CTV delineation methods do not account for this variability and can only generate a single CTV for each case. Purpose This study aims to develop a deep learning‐based technique to generate multiple CTV contours for each case, simulating the inter‐reader variability in the clinical practice. Methods We employed a publicly available dataset consisting of fluorodeoxyglucose positron emission tomography (FDG‐PET), x‐ray computed tomography (CT), and pre‐contrast T1‐weighted magnetic resonance imaging (MRI) scans from 51 patients with soft tissue sarcoma, along with an independent validation set containing five additional patients. An experienced reader drew a contour of the gross tumor volume (GTV) for each patient based on multi‐modality images. Subsequently, two additional readers, together with the first one, were responsible for contouring three CTVs in total based on the GTV. We developed a diffusion model‐based deep learning method that is capable of generating arbitrary number of different and plausible CTVs to mimic the inter‐reader variability in CTV delineation. The proposed model incorporates a separate encoder to extract features from the GTV masks, leveraging the critical role of GTV information in accurate CTV delineation. Results The proposed diffusion model demonstrated superior performance with the highest Dice Index (0.902 compared to values below 0.881 for state‐of‐the‐art models) and the best generalized energy distance (GED) (0.209 compared to values exceeding 0.221 for state‐of‐the‐art models). It also achieved the second‐highest recall and precision metrics among the compared ambiguous image segmentation models. Results from both datasets exhibited consistent trends, reinforcing the reliability of our findings. Additionally, ablation studies exploring different model structures and input configurations highlighted the significance of incorporating prior GTV information for accurate CTV delineation. Conclusions The proposed diffusion model successfully generates multiple plausible CTV contours for soft tissue sarcomas, effectively capturing inter‐reader variability in CTV delineation.
Dong, Yafei [Yale Biomedical Imaging Institute Yal↗
Recommendations for Best Practices for Data Preservation and Open Science in HEP
These recommendations are the result of reflections by scientists and experts who are, or have been, involved in the preservation of high-energy physics data. The work has been done under the umbrella of the Data Lifecycle panel of the International Committee of Future Accelerators (ICFA), drawing on the expertise of a wide range of stakeholders. A key indicator of success in the data preservation efforts is the long-term usability of the data. Experience shows that achieving this requires providing a rich set of information in various forms, which can only be effectively collected and preserved during the period of active data use. The recommendations are intended to be actionable by the indicated actors and specific to the particle physics domain. They cover a wide range of actions, many of which are interdependent. These dependencies are indicated within the recommendations and can be used as a road map to guide implementation efforts. These recommendations are best accessed and viewed through the web application, see https://icfa-data-best-practices.app.cern.ch/
Campana, Simone [CERN]↗
ReVise: A Human-AI Interface for Incremental Algorithmic Recourse
The recent adoption of artificial intelligence in socio-technical systems raises concerns about the black-box nature of the resulting decisions in fields such as hiring, finance, admissions, etc. If data subjects—such as job applicants, loan applicants, and students—receive an unfavorable outcome, they may be interested in algorithmic recourse, which involves updating certain features to yield a more favorable result when re-evaluated by algorithmic decision-making. Unfortunately, when individuals do not fully understand the incremental steps needed to change their circumstances, they risk following misguided paths that can lead to significant, long-term adverse consequences. Existing recourse approaches focus exclusively on the final recourse goal but neglect the possible incremental steps to reach the goal with real-life constraints, user preferences, and model artifacts. To address this gap, we formulate a visual analytic workflow for incremental recourse planning in collaboration with AI/ML experts and contribute an interactive visualization interface that helps data subjects efficiently navigate the recourse alternatives and make an informed decision. We also present one of the many usage scenarios, developed during exploratory feedback sessions with twelve graduate students using a real-world dataset, which demonstrates that our approach can be instrumental for data subjects in choosing a suitable recourse path.
algorithmic recourse↗
Nuclear Physics Network Requirements Review (Final Report)
The Energy Sciences Network (ESnet) is the high-performance network user facility for the US Department of Energy (DOE) Office of Science (SC) and delivers highly reliable data transport capabilities optimized for the requirements of data-intensive science. In essence, ESnet is the circulatory system that enables the DOE science mission by connecting all its laboratories and facilities in the US and abroad. ESnet is funded and stewarded by the Advanced Scientific Computing Research (ASCR) program and managed and operated by the Scientific Networking Division at Lawrence Berkeley National Laboratory (LBNL). ESnet is widely regarded as a global leader in the research and education networking community. ESnet interconnects DOE national laboratories, user facilities, and major experiments so that scientists can use remote instruments and computing resources as well as share data with collaborators, transfer large datasets, and access distributed data repositories. ESnet is specifically built to provide Between July 2023 and October 2023, ESnet and the Nuclear Physics program (NP) of the DOE SC organized an ESnet requirements review of NP-supported activities. Preparation for these events included identification of key stakeholders: program and facility management, research groups, and technology providers. Each stakeholder group was asked to prepare formal case study documents about its relationship to the NP program to build a complete understanding of the current, near-term, and long-term status, expectations, and processes that will support the science going forward.
97 MATHEMATICS AND COMPUTING↗
Deep learning models map rapid plant species changes from citizen science and remote sensing data
Anthropogenic habitat destruction and climate change are reshaping the geographic distribution of plants worldwide. However, we are still unable to map species shifts at high spatial, temporal, and taxonomic resolution. Here, we develop a deep learning model trained using remote sensing images from California paired with half a million citizen science observations that can map the distribution of over 2,000 plant species. Our model— Deepbiosphere— not only outperforms many common species distribution modeling approaches (AUC 0.95 vs. 0.88) but can map species at up to a few meters resolution and finely delineate plant communities with high accuracy, including the pristine and clear-cut forests of Redwood National Park. These fine-scale predictions can further be used to map the intensity of habitat fragmentation and sharp ecosystem transitions across human-altered landscapes. In addition, from frequent collections of remote sensing data, Deepbiosphere can detect the rapid effects of severe wildfire on plant community composition across a 2-y time period. These findings demonstrate that integrating public earth observations and citizen science with deep learning can pave the way toward automated systems for monitoring biodiversity change in real-time worldwide.
Gillespie, Lauren E.↗
Targeted delivery of genome editors in vivo
Genome editing has revolutionized the treatment of genetic diseases, yet the difficulty of tissue-specific delivery currently limits applications of editing technology. Here, in this Review, we discuss preclinical and clinical advances in delivering genome editors with both established and emerging delivery mechanisms. Targeted delivery promises to considerably expand the therapeutic applicability of genome editing, moving closer to the ideal of a precise ‘magic bullet’ that safely and effectively treats diverse genetic disorders.
Ngo, Wayne [University of California, Berkeley, CA↗
Efficient and generalizable nested Fourier-DeepONet for three-dimensional geological carbon sequestration
Geological carbon sequestration (GCS) involves injecting CO2 into subsurface geological formationsfor permanent storage. Numerical simulations could guide decisions in GCS projects by predictingCO 2 migration pathways and the pressure distribution in storage formation. However, these simula-tions are often computationally expensive due to highly coupled physics and large spatial-temporalsimulation domains. Surrogate modelling with data-driven machine learning has become a promis-ing alternative to accelerate physics-based simulations. Among these, the Fourier neural operator(FNO) has been applied to three-dimensional synthetic subsurface models. Despite its good accuracyin simulating CO 2 plume migration, it requires large computational resources in training and alsolacks generalizability. Here, to further improve performance, we have developed a nested Fourier-DeepONet by combining the expressiveness of the FNO with the modularity of a deep operatornetwork (DeepONet). This new framework is twice as efficient as a nested FNO for training and has atleast 80% lower GPU memory requirement due to its flexibility to treat temporal coordinates sepa-rately. These performance improvements are achieved without compromising prediction accuracy.In addition, the generalization and extrapolation ability of nested Fourier-DeepONet beyond thetraining range has been thoroughly evaluated. Nested Fourier-DeepONet outperformed the nestedFNO for extrapolation in time with more than 50% reduced error. It also exhibited good extrapolationaccuracy beyond the training range in terms of reservoir properties, number of wells, and injectionrate.
Lee, Jonathan E. [Department of Chemical and Envir↗
Seeing is Believing: Autonomous Microscopy and the Data Revolution in Materials Science
This presentation explores the transformative potential of autonomous electron microscopy and artificial intelligence (AI) in accelerating materials science discovery, particularly for energy applications and materials operating in extreme environments. We discuss pioneering self-driving laboratories at NREL designed to intelligently probe material synthesis and degradation across multiple scales, aiming to rapidly bridge the gap between atomic-level understanding and the development of high-performance, reliable materials. Utilizing advanced machine learning techniques, such as few-shot learning and multimodal analysis integrating imaging and spectroscopy, we demonstrate methods to extract actionable descriptors for material behavior, quantify complex microstructural evolution, and statistically link synthesis parameters to defect populations. This AI-driven approach promises to accelerate the creation of predictive materials tailored for specific missions, enabling faster development cycles and enhanced material assurance.
36 MATERIALS SCIENCE↗
Seeing is Believing: Autonomous Microscopy and the Data Revolution in Materials Science
This presentation explores the transformative potential of autonomous electron microscopy and artificial intelligence (AI) in accelerating materials science discovery, particularly for energy applications and materials operating in extreme environments. We discuss pioneering self-driving laboratories at NREL designed to intelligently probe material synthesis and degradation across multiple scales, aiming to rapidly bridge the gap between atomic-level understanding and the development of high-performance, reliable materials. Utilizing advanced machine learning techniques, such as few-shot learning and multimodal analysis integrating imaging and spectroscopy, we demonstrate methods to extract actionable descriptors for material behavior, quantify complex microstructural evolution, and statistically link synthesis parameters to defect populations. This AI-driven approach promises to accelerate the creation of predictive materials tailored for specific missions, enabling faster development cycles and enhanced material assurance.
97 MATHEMATICS AND COMPUTING↗
Seeing is Believing: Autonomous Microscopy and the Data Revolution in Materials Science [Slides]
Machine intelligence has the potential to revolutionize materials science, enabling autonomous synthesis, self-driving characterization, and accelerated modeling. However, despite the promise, successful implementation of these methods in day-to-day research remains a challenge. This talk will delve into the reasons behind this, exploring how truly intelligent experiments are hindered by opaque experiment control, a lack of domain-specific models, and human-centric design. Through a focus on the characterization of next-generation microelectronics and energy storage materials, I will share insights from both successful and failed attempts to implement machine intelligence. We will then explore the next steps necessary to unlock the full potential of machine intelligence in materials science, creating a future where intelligent systems work seamlessly alongside researchers to drive innovation and discovery.
36 MATERIALS SCIENCE↗
Recommendations for developing, documenting, and distributing data products derived from NEON data
The National Ecological Observatory Network (NEON) provides over 180 distinct data products from 81 sites (47 terrestrial and 34 freshwater aquatic sites) within the United States and Puerto Rico. These data products include both field and remote sensing data collected using standardized protocols and sampling schema, with centralized quality assurance and quality control (QA/QC) provided by NEON staff. Such breadth of data creates opportunities for the research community to extend basic and applied research while also extending the impact and reach of NEON data through the creation of derived data products—higher level data products derived by the user community from NEON data. Derived data products are curated, documented, reproducibly-generated datasets created by applying various processing steps to one or more lower level data products—including interpolation, extrapolation, integration, statistical analysis, modeling, or transformations. Derived data products directly benefit the research community and increase the impact of NEON data by broadening the size and diversity of the user base, decreasing the time and effort needed for working with NEON data, providing primary research foci through the development via the derivation process, and helping users address multidisciplinary questions. Creating derived data products also promotes personal career advancement to those involved through publications, citations, and future grant proposals. However, the creation of derived data products is a nontrivial task. Here we provide an overview of the process of creating derived data products while outlining the advantages, challenges, and major considerations.
54 ENVIRONMENTAL SCIENCES↗
Carbon Storage Technical Viability Approach (CS TVA) Data Availability Results Database
The Carbon Storage Technical Viability Approach (CS TVA) Data Availability Results Database v1.0 is the output of a data availability assessment workflow that was developed by NETL to create a tool for spatial data availability assessment. This results database is the output of the first version of the workflow performed on the data with the CS TVA Database v2.0.
carbon storage↗