SEARCH · Engineering Papers
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.
The experiment investigates free expansion of a supercritical fluid into a two-phase liquid-vapor coexistence region. A huge molecular dynamics simulation (6 billion Lennard-Jones atoms) was run on 5760 GPUs (33% of LLNL Sierra) using LAMMPS/Kokkos software. This improved visualization workflow and started preliminary simulations of aluminum using SNAP machine learning potential.
DarkStar was a Strategic Initiative (FY2021-FY2024) to investigate applications of Artificial Intelligence (AI) and Machine Learning (ML) to scientific problems of complex hydrodynamics, shockwave physics and energetic materials. The research focused on physics and engineering design as a process that can be tremendously accelerated through merging AI with advanced physics simulation on exascale-class platforms, and to experimentally validate this revolutionary new approach through dynamic materials campaigns. A central thread of scientific inquiry was in the application of AI to enable human understanding of how to control hydrodynamic instability (which has impacts to areas such as inertial confinement fusion) via engineering features and time-dependent sources. Motivated by an unfinished line of research started by Dr. Johnny von Neumann, AI-enabled simulation approaches were developed that allowed DarkStar researchers to uncover several ground-breaking discoveries regarding hydrodynamic instability, including how to completely suppress Richtmyer-Meshkov instability (RMI). These S&T discoveries, along with other advances, have shown the way for an entirely new approach to time-dependent problems known as inverse design – the idea that complex systems can be developed directly from a final state that is to be achieved and resolve the initial design via satisfying several constraints simultaneously via AI/ML. Through experimental campaigns conducted across a wide range of facilities in the NNSA complex (the High Explosive Application Facility at LLNL, the Dynamic Compression Sector/Advanced Photon Source at Argonne National Lab, and Special Technologies Laboratory at MSTS) the radical new AI/ML approach to engineering complex material dynamics was verified, establishing a new field of study within the realm of shock physics. As advanced manufacturing capabilities continue to develop, the great importance of inverse design as a means to apply that technology effectively for NNSA missions will feature prominently over this decade. DarkStar has positioned NNSA as a world-leader in this newly emerging cross-disciplinary area of AI methods for advanced physics simulation and pioneered multiple novel approaches that have enabled the broader scientific community. By allowing us to see past the horizon, to 2030 and beyond, DarkStar has illuminated the vast potential of AI/ML to impact a wide range of new national security missions and, consequently, multiple areas of further research have already emerged across the NNSA and DOD complex.
In this document, we describe a new reconstruction workflow developed for the MicroBooNE experiment. It features the use of Deep Convolutional Neural Networks trained to recognize key structures within the data sufficient for the 3D reconstruction of neutrino interactions within the detector. As a test of the reconstruction utility, the products of the reconstruction workflow are used to select inclusive charged-current (CC) $\nu_e$ and $\nu_\mu$ interactions in both simulated and real MicroBooNE data. In simulation, our $\nu_e$ and $\nu_\mu$ selections achieve an efficiency of 57% and 68\%, respectively, with a purity of 91% and 96%, respectively. We find that these selections are competitive with the inclusive selections used for the most recent MicroBooNE LEE searches. In particular, the CC-$\nu_e$ inclusive selection efficiency improves by over 20% while also improving sample purity. As a first step in quantifying potential bias, the data and Monte Carlo expectati ons are compared for both selections using the MicroBooNE open data. Within statistical and systematic uncertainties, both the electron and muon CC-inclusive event samples agree. A comparison of the real data events chosen by our work and another reconstruction framework shows that the two analyses each identify a sizeable fraction of events the other does not. This suggests that future analyses integrating the strengths of each could lead to combined gains. This work demonstrates, for the first time on real LArTPC data, state-of-the-art neutrino interaction reconstruction centered around deep learning algorithms.
The objective of MULTI-LEADER is to cut design costs by 80% while generating more energy-efficient designs of multi-stage compressors by developing and implementing novel machine learning (ML) techniques, which enable faster and fewer design iterations, improved solver performance, and concurrent multi-disciplinary design. Current industrial practices for the design of multi-stage compressors involve simulation-based design optimization with successive levels of model fidelity, iteratively evaluated between distinct disciplines, one stage at a time to tackle the high dimensional design variations. This project addresses these key design challenges: (1) concurrent optimization of multiple stages under many non-linear constraints; (2) multitude of evaluation of high-fidelity and expensive solvers and their gradients during optimization convergence in high-dimensional design; (3) multi-disciplinary design to maximize aerodynamic performance while guaranteeing structural integrity and additive manufacturability; (4) utilization of multiple fidelity of solvers with disparate parameterization and modeling assumptions. MULTI-LEADER achieved more than 5x speed up in detailed design of more energy-efficient compressors via these machine learning (ML) innovations: (i) rapid design surrogates by multi-source learning from diverse fidelities across multiple disciplines, (ii) physics-constrained data-augmented modeling for improved empiricism, (iii) generative manifold embedding for high dimensional concurrent design without gradient information; (iv) budget-constrained fidelity-adaptive sampling towards fewer design iterations.
Traveling-wave technology can push the accelerator field gradient of niobium SRF cavity to 70MV/m or higher beyond the fundamental limit of 50~60MV/m in Standing-Wave regime. The 1st demonstration of TW resonance excitation in a proof-of-principle 3-cell SRF cavity in 2K liquid helium was successfully carried out at Fermilab in collaboration with Euclid Techlabs. In parallel with that, to advancing TW technologies necessary more for future accelerator-scale one, Fermilab has proposed a preliminary RF design of a half-meter scale TW SRF cavity by considering the physical dimensions of existing SRF facilities and the lessons learned from the 3-cell,. It consists of a 7-cell structure and a power feedback waveguide (WG) loop with new RF configurations to control TW resonance. Development efforts toward a TW 7-cell has been in progress. Here we report the recent activities and progresses of those.
The major goals of this project are: • 1. Employ Machine Learning to solve combinatorial problems in searches for new physics phenomena, with a focus on multijet signatures. • 2. Enable high-precision tracking for CMS at the HL-LHC by carrying out the Outer Tracker project for the Phase-II detector upgrade. Compared to the original proposal, the scope is reduced due to reduced resources in final award. In particular, the program of long-lived particle searches was descoped at that time due to lack of resources.
The Department of Energy Computational Science Graduate Fellowship (DOE CSGF) is essential for addressing the increasingly complex national workforce demands stemming from the growth of computational science and engineering challenges. Computational science and engineering (CSE) takes a multidisciplinary approach that utilizes scientific computing to tackle practical problems and provide technical tools across the spectrum of scientific discovery. The DOE CSGF specifically highlights high-performance computing (HPC) as a critical enabling technology in CSE, driving advancements in science and engineering that are vital to both the DOE and the broader economy. Over the past half-century, HPC has been an essential tool for DOE’s success. During this period, important missions, such as nuclear stockpile stewardship, have turned to HPC as an essential technology. Entire science disciplines have been transformed through the augmentation of scientific observation via HPC. At government laboratories, academic institutions, and in industry, DOE CSGF alumni are helping push traditional HPC boundaries while contributing to discoveries in high-energy physics, quantum information systems, fusion-reactor design, machine learning, additive manufacturing, nano materials for next-generation batteries and transistors, and advanced nuclear reactor modeling. In addition, HPC is used to address national health needs that will eventually point to cures both by helping cancer researchers manage and analyze huge troves of data, by simulating biological mechanisms, and by accelerating drug development. A 2023 report from the ASCAC Subcommittee on American Competitiveness and Innovation to the ASCR office, “Can the United States Maintain Its Leadership in High-Performance Computing?” says of the Program, “The CSGF program provides a barometer for disciplines that will be of interest to future DOE computing. Computational biology, machine learning, and quantum computing are among the subjects that began to swell in the ranks of CSGF applicants before the labs were hiring as high a percentage of employees in these categories.” The explosion of scientific and technological data has heightened the demand for advanced high-performance computing (HPC) to transform these data into meaningful scientific insights. As access to vast amounts of data increases, the fields of Machine Learning and Artificial Intelligence are experiencing a resurgence, enhancing the established practices of computational modeling and simulation. In its September 2020 subcommittee report on "AI/ML, Data Intensive Science, and High-Performance Computing," the DOE Advanced Scientific Computing Advisory Committee (ASCAC) specifically called for a fellowship program to train computational and data scientists to address exascale and data-intensive computing challenges. This integration of empirical and theoretical modeling will increasingly guide federal policymakers in making decisions that impact American society and future generations. It demands a workforce of highly skilled and intellectually agile computational scientists capable of navigating the rapid advancements in scientific computing within the DOE National Laboratory research environment. The DOE CSGF program has consistently addressed this critical need.
Mock-up waveguide loop development toward a half-meter scale traveling-wave SRF cavity ABSTRACT = Traveling-Wave (TW) technology can push the accelerator field gradient of niobium SRF cavity to 70MV/m or higher beyond the fundamental limit of 50~60MV/m in Standing-Wave regime. The success of TW resonance excitation in a proof-of-principle 3-cell SRF cavity in 2K liquid helium encouraged to advance TW technologies necessary more for future accelerator-scale one. Fermilab has proposed a preliminary RF design of a half-meter scale TW cavity by considering the physical dimensions of existing SRF facilities and the lessons learned from the 3-cell. It consists of a 7-cell structure and a power feedback waveguide (WG) loop with new TW excitation and control schemes such as, double directional coupler and two WG tuners. Mock-up waveguide loop development was launched under Fermilab LDRD program to demonstrate those new RF schemes at a room temperature. Fabrication drawings of a mock-up loop were completed. More details and plans of the development will be presented.
My fellowship research focused on making physics-based simulations faster and more useful through machine learning. Many problems in science and engineering are governed by partial differential equations, but high-fidelity simulations are often too expensive to run repeatedly. I worked on improving Latent Space Dynamics Identification (LaSDI), a reduced-order modeling framework that compresses large simulation data sets into a smaller representation and then learns how that representation evolves over time. The motivation was to develop reduced models that remain accurate for more challenging systems, especially when predictions must remain reliable over long time intervals or when the underlying dynamics are more complicated than standard methods can easily handle. I also contributed to related work on Quandary, a high-performance software effort for simulation and control of open quantum systems, before focusing primarily on Latent Space Dynamics Identification methods. The main outcomes of the fellowship were two new algorithms (both of which were published), Rollout-LaSDI and Higher-Order LaSDI, together with supporting work on multi-stage Latent Space Dynamics Identification. Rollout-LaSDI improved long-term prediction by training the model to stay accurate over extended time horizons, and Higher-Order LaSDI broadened the method so it could model systems with higher-order time dynamics. My contributions to multistage Latent Space Dynamics Identification also helped show that its later training stages could be simplified without losing effectiveness, and that this behavior held across different model architectures and training strategies. Taken together, these advances improved the accuracy, flexibility, and practical value of reduced-order modeling tools for computational science.
AI models are criticized as being black boxes, potentially subjecting climate science to greater uncertainty. Explainable artificial intelligence (XAI) has been proposed to probe AI models and increase trust. In this review and perspective paper, we suggest that, in addition to using XAI methods, AI researchers in climate science can learn from past successes in the development of physics-based dynamical climate models. Dynamical models are complex but have gained trust because their successes and failures can sometimes be attributed to specific components or sub-models, such as when model bias is explained by pointing to a particular parameterization. We propose three types of understanding as a basis to evaluate trust in dynamical and AI models alike: (1) instrumental understanding, which is obtained when a model has passed a functional test; (2) statistical understanding, obtained when researchers can make sense of the modeling results using statistical techniques to identify input–output relationships; and (3) component-level understanding, which refers to modelers' ability to point to specific model components or parts in the model architecture as the culprit for erratic model behaviors or as the crucial reason why the model functions well. We demonstrate how component-level understanding has been sought and achieved via climate model intercomparison projects over the past several decades. Such component-level understanding routinely leads to model improvements and may also serve as a template for thinking about AI-driven climate science. Currently, XAI methods can help explain the behaviors of AI models by focusing on the mapping between input and output, thereby increasing the statistical understanding of AI models. Yet, to further increase our understanding of AI models, we will have to build AI models that have interpretable components amenable to component-level understanding. We give recent examples from the AI climate science literature to highlight some recent, albeit limited, successes in achieving component-level understanding and thereby explaining model behavior. The merit of such interpretable AI models is that they serve as a stronger basis for trust in climate modeling and, by extension, downstream uses of climate model data.
Electricity grids are challenged to maintain reliability during more intense and frequent extreme weather events due to climate change. This challenge is exacerbated by multi-sector electrification and power sector decarbonization through increased reliance on variable renewable energy, which necessitates the expansion of transmission infrastructure. However, transmission expansion planning is often complicated by intertwined planning authorities and jurisdictions, and allocation of large capital investment needs. These factors cause authorities to manage transmission investments individually (i.e., only/mostly intraregional planning), which can lead to suboptimal transmission networks. This study investigates the potential benefits of cooperative transmission expansion planning (i.e., both intraregional and interregional planning that optimizes transmission investments across the entire physical system). Using sectoral and economic optimization, and machine learning models, it analyzes the impact of different levels of cooperation among transmission planning regions within U.S. Western Interconnection in 2019 and 2059 via an iterative investment process. Furthermore, it examines the effects of future climate change on transmission cooperation by simulating historical heat waves from 2019 under conditions of 2059. The results indicate that cooperative transmission planning leads to lower wholesale electricity prices, decreased energy outages, and reduced greenhouse gas emissions. However, the advantages of collaboration diminish during widespread heat waves, despite remaining beneficial especially for regions like California Independent System Operator with substantial solar installations. The study underscores the importance of transmission cooperation in reducing costs and enhancing reliability, emphasizing the need for strategic investments in storage to address challenges posed by future extreme weather events with varying spatial scales.
Separating charged and neutral pions as well as calibrating the pion energy response is a core component of reconstruction in the ATLAS calorimeter. This note presents an investigation of deep learning techniques for these tasks, representing the signal in the ATLAS calorimeter layers as pixelated images. Deep learning approaches outperform the classification applied in the baseline local hadronic calibration and are able to improve the energy resolution for a wide range in particle momenta, especially for low energy pions. This work demonstrates the potential of deep-learning-based low-level hadronic calibrations to significantly improve the quality of particle reconstruction in the ATLAS calorimeter.
Traveling-Wave (TW) technology can push the accelera-tor field gradient of niobium SRF cavity to 70MV/m or higher beyond the fundamental limit of 50~60MV/m in Standing-Wave regime. The success of TW resonance excitation in a proof-of-principle 3-cell SRF cavity in 2K liquid helium encouraged to advance TW technologies necessary more for future accelerator-scale one. Fermilab has proposed a preliminary RF design of a half-meter scale TW cavity by considering the physical dimensions of existing SRF facilities and the lessons learned from the 3-cell. It consists of a 7-cell structure and a power feed-back waveguide (WG) loop with new TW excitation and control schemes such as, double directional coupler and two WG tuners. Mock-up waveguide loop development was launched under Fermilab LDRD program to demon-strate those new RF schemes at a room temperature. Fab-rication drawings of a mock-up loop were completed. Here details and plans of the development are reported.
Multicomponent polymer mixtures are ubiquitous in biological self-organization but are notoriously difficult to study computationally. Plagued by both slow single molecule relaxation times and slow equilibration within dense mixtures, molecular dynamics simulations are typically infeasible at the spatial scales required to study the stability of mesophase structure. Polymer field theories offer an attractive alternative, but analytical calculations are only tractable for mean-field theories and nearby perturbations, constraints that become especially problematic for fluctuation-induced effects such as coacervation. Here, we show that a recently developed technique for obtaining numerical solutions to partial differential equations based on operator learning, neural operators, lends itself to a highly scalable training strategy by parallelizing per-species operator maps. We illustrate the efficacy of our approach on six-component mixtures with randomly selected compositions and that it significantly outperforms the state-of-the-art pseudospectral integrators for field-theoretic simulations, especially as polymer lengths become long.
Large-scale river models are being refined over coastal regions to improve the scientific understanding of coastal processes, hazards and responses to climate change. However, coarse mesh resolutions and approximations in physical representations of tidal rivers limit the performance of such models at resolving the complex flow dynamics near the river-ocean interface, resulting in inaccurate simulations of flood inundation. In this research, we propose a machine learning (ML) framework based on the state-of-the-art physics-informed neural network (PINN) to simulate the downscaled flow at the subgrid scale. First, we demonstrate that PINN is able to assimilate observations of various types and solve the one-dimensional (1-D) Saint-Venant equations (SVE) directly. We perform the flow simulations over a floodplain and along an open channel in several synthetic case studies. The PINN performance is evaluated against analytical solutions and numerical models. Our results indicate that the PINN solutions of water depth have satisfactory accuracy with limited observations assimilated. In the case of flood wave propagation induced by storm surge and tide, a new neural network architecture is proposed based on Fourier feature embeddings that seamlessly encodes the periodic tidal boundary condition in the PINN's formulation. Furthermore, we show that the PINN-based downscaling can produce more reasonable subgrid solutions of the along-channel water depth by assimilating observational data. The PINN solution outperforms the simple linear interpolation in resolving the topography and dynamic flow regimes at the subgrid scale. This study provides a promising path towards improving emulation capabilities in large-scale models to characterize fine-scale coastal processes.
We present the first sub-microsecond transformer implementation on an FPGA achieving competitive performance for state-of-the-art high-energy physics benchmarks. Transformers have shown exceptional performance on multiple tasks in modern machine learning applications, including jet tagging at the CERN Large Hadron Collider (LHC). However, their computational complexity prohibits use in real-time applications, such as the hardware trigger system of the collider experiments up until now. In this work, we demonstrate the first application of transformers for jet tagging on FPGAs, achieving $\mathcal{O}(100)$ nanosecond latency with superior performance compared to alternative baseline models. We leverage high-granularity quantization and distributed arithmetic optimization to fit the entire transformer model on a single FPGA, achieving the required throughput and latency. Furthermore, we add multi-head attention and linear attention support to hls4ml, making our work accessible to the broader fast machine learning community. This work advances the next-generation trigger systems for the High Luminosity LHC, enabling the use of transformers for real-time applications in high-energy physics and beyond.
Plasma-surface interactions (PSI) play a crucial role in microelectronics fabrication; however, their multiscale nature and array of complex, often unknown interactions make computational modeling of PSIs extremely difficult. To this end, we propose a general neural master equation (NME) framework that uses master equations to describe the dynamics of a molecular process, wherein neural networks learned from atomistic simulations represent unknown transitions between different system states. By leveraging the physics-based structure of master equations and data-driven state transitions, the NME framework promotes generalizability and physics interpretability, and can bridge disparate length and time scales. The framework is demonstrated for multiscale modeling of Si atomic layer etching and reactive ion etching, where the learned NME-based surface kinetic models exhibit good predictive and extrapolative capabilities for predicting experimentally relevant observables as a function of process parameters. The NME-based surface kinetic models obey physical constraints, which are violated in models based on neural ordinary differential equations. The proposed NME framework for multiscale modeling of molecular processes can pave the way for the discovery of new chemistries and materials in atomic-scale plasma processes.
This paper describes a milling stability identification approach that simultaneously considers: physics-based models for the tool tip frequency response functions and stability predictions; the binary result from a milling test (automatically labeled as stable or unstable based on frequency content); chatter frequency when an unstable result is obtained; and user risk tolerance. The algorithm applies probabilistic Bayesian machine learning with adaptive, parallelized Markov Chain Monte Carlo sampling to update the probability of stability with each milling test. Furthermore, the result is a robust solution for rapid convergence to optimized milling parameters for maximum metal removal rate using all available information.