Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Real Time Optimization”

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 811 records · Page 45

A dynamic Bayesian optimized active recommender system for curiosity-driven partially Human-in-the-loop automated experiments

Optimization of experimental materials synthesis and characterization through active learning methods has been growing over the last decade, with examples ranging from measurements of diffraction on combinatorial alloys at synchrotrons, to searches through chemical space with automated synthesis robots for perovskites. In virtually all cases, the target property of interest for optimization is defined a priori with the ability to shift the trajectory of the optimization based on human-identified findings during the experiment is lacking. Thus, to highlight the best of both human operators and AI-driven experiments, here we present the development of a human–AI collaborated experimental workflow, via a Bayesian optimized active recommender system (BOARS), to shape targets on the fly with human real-time feedback. Here, the human guidance overpowers AI at early iteration when prior knowledge (uncertainty) is minimal (higher), while the AI overpowers the human during later iterations to accelerate the process with the human-assessed goal. We showcase examples of this framework applied to pre-acquired piezoresponse force spectroscopy of a ferroelectric thin film, and in real-time on an atomic force microscope, with human assessment to find symmetric hysteresis loops. It is found that such features appear more affected by subsurface defects than the local domain structure. This work shows the utility of human–AI approaches for curiosity driven exploration of systems across experimental domains.

36 MATERIALS SCIENCE↗

Fingerprinting shock-induced deformations via diffraction

Abstract During the various stages of shock loading, many transient modes of deformation can activate and deactivate to affect the final state of a material. In order to fundamentally understand and optimize a shock response, researchers seek the ability to probe these modes in real-time and measure the microstructural evolutions with nanoscale resolution. Neither post-mortem analysis on recovered samples nor continuum-based methods during shock testing meet both requirements. High-speed diffraction offers a solution, but the interpretation of diffractograms suffers numerous debates and uncertainties. By atomistically simulating the shock, X-ray diffraction, and electron diffraction of three representative BCC and FCC metallic systems, we systematically isolated the characteristic fingerprints of salient deformation modes, such as dislocation slip (stacking faults), deformation twinning, and phase transformation as observed in experimental diffractograms. This study demonstrates how to use simulated diffractograms to connect the contributions from concurrent deformation modes to the evolutions of both 1D line profiles and 2D patterns for diffractograms from single crystals. Harnessing these fingerprints alongside information on local pressures and plasticity contributions facilitate the interpretation of shock experiments with cutting-edge resolution in both space and time.

36 MATERIALS SCIENCE↗

Growth of SrTiO{sub 3}(110) film by oxide molecular beam epitaxy with feedback control

By controlling the growth of complex oxide films with atomic precision, emergent phenomena and fascinating properties have been discovered, and even been manipulated. With oxide molecular beam epitaxy (OMBE) we grow high-quality SrTiO{sub 3}(110) films by evaporating Sr and Ti metals with separate controls of the open/close timing of the shutters. The incident electron beam angle of the reflective high energy electron diffraction (RHEED) is adjusted to make the (01) beam sensitive to surface chemical concentration. By monitoring such an intensity, we tune the shutter timing to synchronize the evaporation amount of Sr and Ti in real-time. The intensity is further used as a feedback control signal for automatic growth optimization to fully compensate the possible fluctuation of the source flux rates upon extended growth. A 22 nm-thick film is obtained with the precision of metal cation stoichiometry better than 0.5%.

36 MATERIALS SCIENCE↗

Characterization of wind turbine flow through nacelle-mounted lidars: a review

This article provides a comprehensive review of the most recent advances in the planning, execution, and analysis of inflow and wake measurements from nacelle-mounted wind Doppler lidars. Lidars installed on top of wind turbines provide a holistic view of the inflow and wake characteristics required to characterize and optimize wind turbine performance, carry out model validation and calibration, and aid in real-time control. The need to balance the enhanced capabilities and limitations of lidars compared to traditional anemometers inspired a broad variety of approaches for scan design and wind reconstruction, which we discuss in this review. We give particular emphasis to identifying common guidelines and gaps in the available literature with the aim of providing an exhaustive picture of the state-of-the-art techniques for reconstructing wind plant flow using nacelle-mounted lidars.

17 WIND ENERGY↗

The Liquid Jet Endstation for Hard X-ray Scattering and Spectroscopy at the Linac Coherent Light Source

The ability to study chemical dynamics on ultrafast timescales has greatly advanced with the introduction of X-ray free electron lasers (XFELs) providing short pulses of intense X-rays tailored to probe atomic structure and electronic configuration. Fully exploiting the full potential of XFELs requires specialized experimental endstations along with the development of techniques and methods to successfully carry out experiments. The liquid jet endstation (LJE) at the Linac Coherent Light Source (LCLS) has been developed to study photochemistry and biochemistry in solution systems using a combination of X-ray solution scattering (XSS), X-ray absorption spectroscopy (XAS), and X-ray emission spectroscopy (XES). The pump–probe setup utilizes an optical laser to excite the sample, which is subsequently probed by a hard X-ray pulse to resolve structural and electronic dynamics at their intrinsic femtosecond timescales. The LJE ensures reliable sample delivery to the X-ray interaction point via various liquid jets, enabling rapid replenishment of thin samples with millimolar concentrations and low sample volumes at the 120 Hz repetition rate of the LCLS beam. This paper provides a detailed description of the LJE design and of the techniques it enables, with an emphasis on the diagnostics required for real-time monitoring of the liquid jet and on the spatiotemporal overlap methods used to optimize the signal. Additionally, various scientific examples are discussed, highlighting the versatility of the LJE.

EXAFS↗

Dilute Combustion Control Using Spiking Neural Networks

Dilute combustion with exhaust gas recirculation (EGR) in spark-ignition engines presents a cost-effective method for achieving higher levels of engine efficiency. At high levels of EGR, however, cycle-to-cycle variability (CCV) of the combustion process is exacerbated by sporadic occurrences of misfires and partial burns. Previous studies have shown that temporal deterministic patterns emerge at such conditions and certain combustion cycles have a significant influence over future events. Due to the complexity of the combustion process and the nature of CCV, harnessing all the deterministic information for control purposes has remained challenging even with physics based 0-D, 1-D, and high-fidelity computational fluid dynamics (CFD) models. In this study, we present a data-driven approach to optimize the combustion process by controlling CCV adjusting the cycle-to-cycle fuel injection quantity. Readily available data from in-cylinder pressure was used to train a spiking neural network (SNN) which learns the optimal way to manage fuel injection in order to reduce CCV while maintaining acceptable levels of fuel consumption. SNNs are particularly well suited for powertrain control applications due to their ability to be deployed on FPGA-based neuromorphic hardware which are small, inexpensive, and have a low power demand. The high-performance computing (HPC) resources of Oak Ridge National Laboratory were used to run an evolutionary-based training approach for choosing the best SNN configuration that minimizes the size of the network while achieving the desired goal. The neuromorphic hardware with the optimized SNN deployed was connected to the rapid prototyping engine control system for real-time control implementation and tested on a single cylinder version of a GM LNF 4-cylinder engine. The results show a significant reduction of CCV with a small percentage of additional fuel used to stabilize the charge.

33 ADVANCED PROPULSION SYSTEMS↗

Current Status of Human Resource Training Program for Fostering RIBiomics Professionals

RI-Biomics is a state-of-the-art radiation fusion technology for evaluating in-vivo dynamics such as absorption, distribution, metabolism and excretion (ADME) of new drug candidates and biomaterials using radioisotope (RI), and quantitative evaluation of their efficacy via molecular imaging techniques and animal models. The RI-Biomics center is the sole comprehensive research and experiment complex in Korea that can simultaneously perform the radio-synthesis of drug candidate with radioisotope, analysis, and molecular imaging evaluation with animal model. Molecular imaging techniques, including nuclear imaging (SPECT and PET), near-infrared fluorescent (NIRF) imaging, and magnetic resonance imaging (MRI), are the cutting-edge technologies for evaluating drug candidates. Since they allow in vivo real-time imaging of the diseased site, monitoring the biodistribution of drug and determining the optimal therapeutic efficacy following treatments, we have integrated RI-ADME and molecular imaging to provide useful information for drug evaluation and to accelerate the development of new drugs and biomaterials. The RI-Biomics center was established with total investment of 18 million $ during four years from 2009 to 2012 in order to develop a comprehensive analyzing system using RI for new drug development as an axis for national growth in the next generation. The RI-Biomics center has labeling synthesis facility for the radiosynthesis of drug candidate with radioisotope such as Tc-99m, I-125, I-131, F-18, H-3 and C-14 using hot cell. It also includes RI-general analysis facilities, such as Radio-HPLC, LC/MS, GC/MS, gamma counter that can analyzing the radio-synthesized materials, and animal image analysis facilities that developed small animal imaging equipment such as SPECT/PET/CT, 7 T MRI, in-vivo optical imaging system and others. In order to achieve the system to verify safety and effectiveness of the new drugs using RI, it is necessary to establish a human resource training program for fostering RI-Biomics professionals in the following key fields; (1) Radio-pharmaceuticals synthesis and labeled compound development, (2) Development of RI-ADME in the living object and image assessment technology. Personnel training program that carries out theoretical education and practical training in the field related to RI-Biomics in parallel is being conducted. Internship training for university students has been administered twice already while educational program for the existing professionals in the RI-Biomics field will be carried out during the summer of 2014. The human resource training program for combination of RIADME and different molecular imaging techniques can offer synergistic advantages to facilitate understanding RIADME and fostering RI-ADME professionals. (authors)

62 RADIOLOGY AND NUCLEAR MEDICINE↗

The Importance of Imaging in Radiation Oncology for National Clinical Trials Network Protocols

Imaging is essential in successfully executing radiation therapy (RT) in oncology clinical trials. As technically sophisticated diagnostic imaging and RT were incorporated into trials, quality assurance in the National Clinical Trials Network groups entered a new era promoting image acquisition and review. Most trials involving RT require pre- and post-therapy imaging for target validation and outcome assessment. The increasing real-time (before and during therapy) imaging and RT object reviews are to ensure compliance with trial objectives. Objects easily transmit digitally for review from anywhere in the world. Physician interpretation of imaging and image application to RT treatment plans is essential for optimal trial execution. Imaging and RT data sets are used to credential RT sites to confirm investigator and institutional ability to meet trial target volume delineation and delivery requirements. Real-time imaging and RT object reviews can be performed multiple times during a trial to assess response to therapy and application of RT objects. This process has matured into an effective data management mechanism. When necessary, site and study investigators review objects together through web media technologies to ensure the patient is enrolled on the appropriate trial and the intended RT is planned and executed in a trial-compliant manner. Real-time imaging review makes sure: (1) the patient is entered and eligible for the trial, (2) the patient meets trial-specific adaptive therapy requirements, if applicable, and (3) the intended RT is according to trial guidelines. This review ensures the study population is uniform and the results are believable and can be applied to clinical practice.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Optimizing Individualized Treatment Planning for Parkinson’s Disease Using Deep Reinforcement Learning

More than one million people currently live with Parkinson's Disease (PD) in the U.S. alone. Medications, such as levodopa, can help manage PD symptoms. However, medication treatment planning is generally based on patient history and limited interaction between physicians and patients during office visits. This limits the extent of benefit that may be derived from the treatment as disease/patient characteristics are generally non-stationary. Wearable sensors that provide continuous monitoring of various symptoms, such as bradykinesia and dyskinesia, can enhance symptom management. However, using such data to overhaul the current static medication treatment planning approach and prescribe personalized medication timing and dosage that accounts for patient/care-giver/physician feedback/preferences remains an open question. We develop a model to prescribe timing and dosage of medications, given the motor fluctuation data collected using wearable sensors in real-time. We solve the resulting model using deep reinforcement learning (DRL). The prescribed policy determines the optimal treatment plan that minimizes patient's symptoms. Our results show that the model-prescribed policy outperforms the static a priori treatment plan in improving patients' symptoms, providing a proof-of-concept that DRL can augment medical decision making for treatment planning of chronic disease patients.

Watts, Jeremy↗

Flexibility Options: A Proposed Product for Managing Imbalance Risk

The presence of variable renewable energy resources with uncertain outputs in day-ahead electricity markets results in additional balancing needs in real-time. Addressing those needs cost-effectively and reliably within a competitive market with unbundled products is challenging as both the demand for and the availability of flexibility depends on day-ahead energy schedules. Existing approaches for reserve procurement usually rely either on oversimplified demand curves that do not consider how system conditions that particular day affect the value of flexibility, or on bilateral trading of hedging instruments that are not co-optimized with day-ahead schedules. This article proposes a new product, ‘Flexibility Options', to address these two limitations. The demand for this product is endogenously determined in the day-ahead market and it is met cost-effectively by considering real-time supply curves for product providers, which are co-optimized with the energy supply. As we illustrate with numerical examples and mathematical analysis, the product addresses the hedging needs of participants with imbalances cost-effectively, provides a less intermittent revenue stream for participants with flexible outputs, promotes value-driven pricing of flexibility, and ensures that the system operator is revenue-neutral. This article provides a comprehensive design that can be further tested and applied in large-scale systems.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Unsupervised classification-based hyperspectral data processing: lossy compression

The existing lossy compression algorithms play an important role in reducing the cost of storage equipment and bandwidth for hyperspectral (HS) application. However, none of the lossy compression algorithms considers the real-time classification of HS data. In this paper, we present a new lossy compression method for HS data that aims to optimally compress in both spatial and spectral domains and simultaneously maximize classification performance. For this target, Harsanyi–Farrand–Chang (HFC) and k-means++ algorithms are applied to achieve a spectral library and an index matrix for HS image. Spectral angle mapping and Euclidean distance are used to update the spectral library and the index matrix. The experiment results indicate that the proposed method has a good classification performance. The results also reveal that the proposed method works well in real-time classification and compression of HS data with a large volume and achieves a high compression ratio. It is noteworthy to mention that the superiority of our method in compression becomes more apparent as the volume of HS data grows. Consequently, the proposed method has a strong advantage in HS applications that require both compression and classification.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

High Momentum Transfer Nucleon Elastic Electromagnetic Form Factor Measurements Using Super BigBite Spectrometer at Jefferson Lab

The nucleons - protons and neutrons - are the basic building blocks of atomic nuclei. We now know that the nucleon consists of fundamental particles called quarks and gluons. The quarks interact with each other by exchanging gluons via the strong interaction. Understanding the quark-gluon structure of the nucleon, especially the confinement of quarks within the nucleon in its ground state, remains one of the main unsolved puzzles of particle physics. The nucleon electromagnetic form factors are directly related to the internal structure of the nucleon. A new generation of high precision experiments, GEp-V, GEn-II, GEn-RP, and GMn, measuring the ground state nucleon space-like electro-magnetic form factor at high momentum transfer is underway at Jefferson Lab experimental Hall-A as part of the Super Bigbite Spectrometer (SBS) program. This series of experiments will provide a new level of understanding of the nucleon structure. These experiments are highly demanding due to the extremely fast drop off of the elastic cross section with the increasing four-momentum transfer squared(Q2). This thesis provides an overview of the SBS physics program and reports on the extensive R&D program carried out to achieve the high rate running conditions essential for carrying out the SBS experiments. SBS will provide an intermediate solid angle of approximately 35 msr, which is significantly larger than the solid angle of other dipole based spectrometers at Jefferson lab. Of course, there are much larger acceptance spectrometers at Jefferson Lab, CLAS12 for example. What is special about SBS is that it provides a sizable acceptance while operating at the highest possible luminosity at Jefferson Lab. With this combination of medium acceptance and the highest available luminosity, SBS provides an unparalleled opportunity to explore the nucleon in its ground state with unprecedented resolution. The relatively large acceptance of SBS is achieved by using a large gap dipole magnet and placing it close to the target. An unavoidable consequence of this is that the SBS GEM trackers and other detectors have a clear line-of-sight view of the target and a portion of the beam-line. As a result, the background hit rate in the SBS front GEM trackers is expected to be up to 500 kHz/cm2, over the entire active area of 6000 cm2. To the best of our knowledge, this extremely high rate over such a large area is unprecedented in any particle tracking system used anywhere in the world before. Correctly reconstructing the particle tracks of interest in this very high background environment is achieved by using especially adapted high rate techniques at every step of the tracking process: optimizing the GEM module and tracker design at the hardware level, using high bandwidth electronics and real time Field Programmable Gate Array (FPGA) based background suppression techniques at the Data Acquisition (DAQ) level, and developing highly specialized tracking algorithms to pick out the signal hits from among the vast amount of background hits. In order to ensure a smooth start and running of the SBS experiments, it is extremely crucial that these techniques are developed, implemented, and tested under realistic conditions well before the actual start of the SBS experimental program. A detailed Geant4 simulation of the experiment was combined with a digitization package to generate the detector level pseudodata similar to what is expected in the actual experiments. The digitization procedures were calibrated against actual GEM data from cosmic-ray runs, X-ray tests, beam test runs in experimental Hall-A, and the PRad experiment in Hall B. Then, optimized tracking algorithms were developed and implemented in an analysis program used to analyze these pseudo-data and to extract expected high-level parameters. These extracted quantities were then compared with the input parameters from the simulation to verify and determine the performance characteristics for the SBS tracker. From this work, a final tracking efficiency of 69% at 25% occupancy was achieved, with the required reconstruction accuracy, for the GMn experiment, the first experiment in the SBS program, with background level at 100 kHz/cm2. These demonstrated parameters are adequate for the successful running of not only the GMn experiment but as well as for GEn-RP and GEn-II experiments, the second and third experiments in the program. This work builds the solid ground to further improve the tracking performance for these experiments and achieve similar conditions for the running of the GEp-V experiment, the most demanding experiment in the SBS program, with an expected background level at 500 kHz/cm2.

Di, Danning↗

Simulation-based Performance Analysis and Tuning for a Two-level Directly Connected System

Hardware and software co-design is becoming increasingly important due to complexities in supercomputing architectures. Simulating applications before there is access to the real hardware can assist machine architects in making better design decisions that can optimize application performance. At the same time, the application and runtime can be optimized and tuned beforehand. BigSim is a simulation-based performance prediction framework designed for these purposes. It can be used to perform packet-level network simulations of parallel applications using existing parallel machines. In this paper, we demonstrate the utility of BigSim in analyzing and optimizing parallel application performance for future systems based on the PERCS network. We present simulation studies using benchmarks and real applications expected to run on future supercomputers. Future petascale systems will have more than 100,000 cores, and we present simulations at that scale.

97 MATHEMATICS AND COMPUTING↗

Optimal assignment for the single-household shared autonomous vehicle problem

Autonomous vehicles have the potential to transform the way people are transported. While driverless technology may mean fewer vehicles are required to transport people to and from their daily activities, such changes may result in increased congestion or total miles traveled. In this study, we solve the single-household shared autonomous vehicle problem to identify cost-optimal routings of vehicles throughout the day. Such a tool will be useful for consumers seeking to minimize cost and for regulators seeking to understand and predict how people may behave in different scenarios. Here, we provide a thorough literature review and construct a mixed-integer linear program to minimize the daily travel cost of a household attending a given set of activities. Since solution time is a determinant for applicability of such a model, we present the model in a component-wise fashion. This approach allows us to understand which features most affect the problem complexity and solution time. We note that modeling carpooling is the feature that most increases time to find an optimal solution, and we therefore propose a novel modeling technique for carpooling two people. We illustrate the performance of our model by comparing it with other models from the literature and note that our model can solve significantly larger problem instances and in a time that is short enough to facilitate real-time scheduling. We also highlight the utility of our model for regulators, who can use it to analyze quickly produced optimal routes under different cost/tax scenarios.

33 ADVANCED PROPULSION SYSTEMS↗

Stochastic Continuous-time Flexibility Scheduling and Pricing in Wholesale Electricity Markets

Large-scale integration of intermittent renewable energy sources (RES) is calling for additional flexibility resources as well as more advanced modeling and optimization techniques to account for the increasing uncertainty and variability in power systems operation. As the RES integration gains momentum, the magnitude and frequency of their variations increase, which may trigger ramping scarcity events in real-time power systems operation. This necessitates revisiting the present definition of power systems flexibility and reserve services to reflect their robustness and adequacy towards sub-interval variations of the load and RES, as well as adjusting the operation models to accommodate the new reserve services. This project took a fundamental approach and aimed at developing continuous-time scheduling and pricing model that accurately models the continuous-time variations of load and RES and efficiently deploys the ramping capability of flexible resources to compensate the sources of variability and uncertainty in the market. In this regard, this project pursued the following goals: Developing stochastic multi-fidelity continuous-time optimization models for scheduling of energy storage (ES) systems and flexible loads in wholesale energy markets; Developing the theory and practices of continuous-time locational marginal pricing for valuating energy storage systems and flexible loads in wholesale energy markets; Developing function space solution approach to convert the proposed stochastic multi-fidelity continuous-time optimization models into tractable mixed-integer linear optimization models; and Defining flexibility reserve as a new type of reserve in markets that would enable ultimate participation of energy storage devices in provision of services to compensate the variability and uncertainty of RES in electricity markets. This project successfully completed all five major tasks defined in the SOPO, and produced 8 high-impact journal papers, 6 conference papers, 3 published U.S. patents, and one web-based software for continuous-time operation optimization of power systems. The application of the proposed flexibility reserve and the stochastic multi-fidelity continuous-time operation scheduling models would modify the forward commitment and schedule of generating units, ES devices and flexible loads, and would line up the resources in such a way that the composition of available resources is better prepared to respond to the sub-hourly variations of the load and renewable resources in real-time operation. Therefore, this project paves the way to sustainable, reliable, and economic integration of renewable energy resources in power system, supporting the progress towards reaching the national targets on energy independence. Even if the proposed models offers a radically different point of view as compared to existing models, it does not alter fundamentally the architecture of power systems operations, nor the complexity of the scheduling problem, so the integration of this project in power systems is extremely practical.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Lightweight Metal Stamping Optimization Enabled by Artificial Intelligence

Successfully manufacturing an automotive body structure made via the sheet metal stamping process depends upon simultaneous consideration of component design, tooling design, stamping process control, and material properties. In many cases, introducing lightweight sheet materials (e.g., aluminum alloys, magnesium alloys, advanced high strength steels) holds the potential to significantly reduce vehicle weight, but challenges the stamping process by introducing materials with inherently less ductility. Successful and repeatable applications require co-developing the stamping process controls with the varying material properties, including formability. During the stamping process, as soon as the forming limit of the sheet is exceeded, the material shows localized necking which quickly leads to splits. Controlling process variability to avoid these material splits will enable deployment of less formable, lighter, and stronger materials for stamped automotive components. A typical optimization procedure for manufacturing requires an iterative process involving parameter setting, execution of computational simulations, and modifying the parameters. The entire process demands substantial computational time, making it impractical for real-time feedback towards rapid corrective actions required for in-line control for running production processes. To overcome this challenge, artificial intelligence (AI) can be leveraged to determine optimal manufacturing parameters within a single manufacturing cycle time. This research proposes an in-line optimization framework incorporating a trained AI model to predict kidney-shaped die forming. Preliminary results indicate that the AI framework can accurately predict draw-in values based on a given parameter set, a process referred to as forward prediction. Furthermore, the AI framework can also predict the optimal parameter set that leads to the desired draw-in values, referred to as inverse optimization (or backward prediction). This research has been performed in collaborations with USCAR (US Council for Automotive Research) and AutoForm. The members of USCAR are Ford, GM, and Stellantis.

36 MATERIALS SCIENCE↗

Integrated edge-to-exascale workflow for real-time steering in neutron scattering experiments

We introduce a computational framework that integrates artificial intelligence (AI), machine learning, and high-performance computing to enable real-time steering of neutron scattering experiments using an edge-to-exascale workflow. Focusing on time-of-flight neutron event data at the Spallation Neutron Source, our approach combines temporal processing of four-dimensional neutron event data with predictive modeling for multidimensional crystallography. At the core of this workflow is the Temporal Fusion Transformer model, which provides voxel-level precision in predicting 3D neutron scattering patterns. The system incorporates edge computing for rapid data preprocessing and exascale computing via the Frontier supercomputer for large-scale AI model training, enabling adaptive, data-driven decisions during experiments. This framework optimizes neutron beam time, improves experimental accuracy, and lays the foundation for automation in neutron scattering. Although real-time experiment steering is still in the proof-of-concept stage, the demonstrated potential of this system offers a substantial reduction in data processing time from hours to minutes via distributed training, and significant improvements in model accuracy, setting the stage for widespread adoption across neutron scattering facilities and more efficient exploration of complex material systems.

97 MATHEMATICS AND COMPUTING↗