SEARCH · Engineering Papers

Results for “Training Analysis”

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.

SourceResearch connectionFrom yearThrough year

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

At least 109 records · Page 6

All sources NASA NTRS DOE OSTI

DOE OSTI2024

A Computational Review of Privacy-Preserving Mechanisms for the Smart Grid

Smart grid technologies have rapidly become one of the largest and most comprehensive sources of data for the modern utility. For the most part, data streams are seen as an essential tool that enable utilities to carry their day-to-day business operations, but they also create the need for efficient and secure data management strategies. In the context of the smart grid, ensuring data privacy is becoming an increasing concern due to a combination of factors that range from shifts in operational paradigms and rapid technology evolution to changes in legislation. Furthermore, researchers have highlighted the risks associated with improperly protected energy records. For example, energy consumption data from homes could be used to infer the behaviors and habits of home occupants through activity recognition or user profiling (Fan, 2017), which may lead to unfair service pricing, targeted advertising, or other personal security violations. Similarly, Electric Vehicles’ (EVs) charging metadata could be used to reveal private information about the owner such as their payment methods, preferred charging stations, and other locational and timing information that could be used to reconstruct the vehicle owner’s behaviors. The privacy of user data, even when used for statistical analysis or machine learning training processes, also needs to be carefully considered, as an individual’s private traits may still be vulnerable if their inclusion/exclusion greatly impacts the result or could be linked to a public dataset through cross-reference. The breach of user privacy also has severe impacts for organizations that store, transmit, or work on the data in the form of diminishing the public’s trust in them while potentially incurring legal consequences (e.g., fines and suspensions under the European Union General Data Protection Regulation, Health Insurance Portability and Accountability Act, etc.). Because of these risks, several privacy-preserving mechanisms are available to help organizations comply with privacy legislations and prevent the unauthorized and malicious use of user data. In light of these concerns, this report focuses on performing a computational review of privacy-preserving mechanisms that have received a significant amount of interest in literature. It specifically focuses on 1) homomorphic encryption, 2) zero-knowledge proofs, 3) differential privacy, and 4) federated learning. It is worth noting that although many of the methods presented in this document rely on cryptographic primitives, their intent is not to provide perfect secrecy, but rather to enable users to maintain privacy, and thus they shall not be compared or equated to other constructs that are aimed to address cybersecurity constructs.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2023

The LSST AGN Data Challenge: Selection Methods

Abstract Development of the Rubin Observatory Legacy Survey of Space and Time (LSST) includes a series of Data Challenges (DCs) arranged by various LSST Scientific Collaborations that are taking place during the project's preoperational phase. The AGN Science Collaboration Data Challenge (AGNSC-DC) is a partial prototype of the expected LSST data on active galactic nuclei (AGNs), aimed at validating machine learning approaches for AGN selection and characterization in large surveys like LSST. The AGNSC-DC took place in 2021, focusing on accuracy, robustness, and scalability. The training and the blinded data sets were constructed to mimic the future LSST release catalogs using the data from the Sloan Digital Sky Survey Stripe 82 region and the XMM-Newton Large Scale Structure Survey region. Data features were divided into astrometry, photometry, color, morphology, redshift, and class label with the addition of variability features and images. We present the results of four submitted solutions to DCs using both classical and machine learning methods. We systematically test the performance of supervised models (support vector machine, random forest, extreme gradient boosting, artificial neural network, convolutional neural network) and unsupervised ones (deep embedding clustering) when applied to the problem of classifying/clustering sources as stars, galaxies, or AGNs. We obtained classification accuracy of 97.5% for supervised models and clustering accuracy of 96.0% for unsupervised ones and 95.0% with a classic approach for a blinded data set. We find that variability features significantly improve the accuracy of the trained models, and correlation analysis among different bands enables a fast and inexpensive first-order selection of quasar candidates.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2024

MTS-VAE

This repository accompanies the work "Design of diverse, functional mitochondrial targeting sequences across eukaryotic organisms using variational autoencoder". It includes the datasets for model training, validation, and downstream analysis.

Mitochondria↗

DOE OSTI2023

Improving the NOvA 3-Flavour Neutrino Oscillation Analysis

NOvA is a long-baseline neutrino experiment studying neutrino oscillations, a quantum mechanical interference phenomena where the observed neutrino flavour differs from that measured earlier, stemming from neutrino mass and flavour states mixing. NOvA consists of two functionally identical tracking calorimeter detectors deployed in the Fermilab NuMI beam. Both detectors are placed 14.6 mrad off the beam axis to achieve a narrow energy peak at 1.8 GeV at an oscillation maximum. The NOvA 3-flavour oscillation analysis measures the neutrino oscillation parameters sin2θ23 and ∆m232 as well as sets limit to δCP , the octant of θ23 and the sign of ∆m32. The event selection for 3-flavour neutrino oscillation analysis ensures the maximum quantity of signal is made available and a minimal amount of background is present. The current disappearance analysis selection has an efficiency of 80% for selecting νμ CC events, and with some improvements additional events could be recovered into the analysis to improve the sensitivity to the aforementioned oscillation parameters. In an effort to recover the currently rejected signal event to the analysis, these events were trained in a classification neural network. The aim of the network was to divide the data into signal (νμ CC events) and background (NC and νe CC events). The highest performing network gave an additional figure of merit gain of 2.34 increasing the sensitivity by 4.3% in effective POT equal to 33 days of additional data taking. This was compared to changing the current particle identification event selection cuts, the best result out of the tested cut combinations gave an additional FOM of 3.36 equal to 3.7% increase in effective POT equivalent to 28 days of data taking.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2021

DETECTING FIRE WITH MACHINE LEARNING-ENABLED VISUAL MONITORING FOR NUCLEAR POWER PLANT ENVIRONMENTS

Nuclear power plants are experiencing significant cost challenges to remain competitive with other energy-generation utilities. Unlike other industries, the cost of operation and maintenance activities is mostly attributed to workforce costs. To mitigate this, nuclear power plant stakeholders are increasingly interested in the development and deployment of machine learning methods to potentially automate or augment manually intensive tasks to reduce costs, especially for monitoring activities. One monitoring function that is visually demanding and that can occur frequently to meet the requirements of a fire protection program is visually monitoring an area for fire occurrence. Currently, fire watch activities consist of a worker physically stationed at a given location with the sole responsibility of observing a given area to ensure a fire is detected and mitigated promptly. This effort focused on the development and evaluation of a suitable deep convolutional neural network to classify individual video frames at a sub-second frequency for the occurrence of “fire” and “no fire” in varying industrial environments similar to nuclear power plants. It is believed that a trained neural network model could be integrated with existing facility video surveillance camera feeds to generate alerts when fire inferences occur in individual frames captured at sub-second temporal resolutions. Extensive effort was dedicated to identifying and curating suitable imagery training data representing varying environments and scene settings with and without flame features to maximize generalization in nuclear power plant environments. The data collection effort resulted in the aggregation of a large, labeled image library exceeding 12,000 images to support model training for diverse industrial environments. A deep neural network model incorporating parallel multi-scale capabilities was developed and trained to support accurate image-based detection of flame incidents of varying sizes and spectral feature properties within heterogeneous scenes. Analysis results show that the trained model can achieve high inference accuracy despite heterogeneous scene environments and components. Testing accuracy exceeded 95.0 percent with very low false positive and false negative inferences.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2026

Towards Scaling Law Analysis For Spatiotemporal Weather Data

Compute-optimal scaling laws are relatively well studied for NLP and CV, where objectives are typically single-step and targets are comparatively homogeneous. Weather forecasting is harder to characterize in the same framework: autoregressive rollouts compound errors over long horizons, outputs couple many physical channels with disparate scales and predictability, and globally pooled test metrics can disagree sharply with per-channel, late-lead behavior implied by short-horizon training. We extend neural scaling analysis for autoregressive weather forecasting from single-step training loss to long rollouts and per-channel metrics. We quantify (1) how prediction error is distributed across channels and how its growth rate evolves with forecast horizon, (2) if power law scaling holds for test error, relative to rollout length when error is pooled globally, and (3) how that fit varies jointly with horizon and channel for parameter, data, and compute-based scaling axes. We find strong cross-channel and cross-horizon heterogeneity: pooled scaling can look favorable while many channels degrade at late leads. We discuss implications for weighted objectives, horizon-aware curricula, and resource allocation across outputs.

Kiefer Jr, Alexander [ORNL] (ORCID:000000025398874↗

DOE OSTI2026

Computational Modeling of Atmospheric Processes at Texas Southern University

Texas Southern University (TSU) is strengthening its research program in atmospheric chemistry and physics with a climate science emphasis by leveraging partnerships with the U.S. Department of Energy’s Atmospheric Radiation Measurement (ARM) Facility, Brookhaven National Laboratory (BNL), and the Tracking Aerosol Convection Interactions ExpeRiment (TRACER). This RDPP-supported program focuses on secondary organic aerosols (SOAs) and reactive atmospheric species that influence cloud formation, precipitation processes, and radiative forcing. SOAs play a critical role in cloud microphysics and Earth’s energy balance, yet the chemical and physical mechanisms governing SOA–cloud interactions remain a significant source of uncertainty in predictive climate models. Through computational modeling, observational data analysis, and national laboratory collaboration, this program develops a skilled cohort of students trained in atmospheric science, environmental data analysis, and climate-relevant modeling. These research experiences build technical competencies that are transferable to careers in government laboratories, academia, and industry. By engaging students from historically underrepresented communities in high-impact climate research, TSU expands participation in the atmospheric sciences workforce while contributing meaningful scientific insights to DOE-supported ARM research activities. This partnership strengthens national capacity in climate science and supports the development of the next generation of atmospheric researchers.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

One Million Open-source Cislunar Orbits

Cislunar space, encompassing the region from geosynchronous orbit to beyond the Moon, is poised to become a cornerstone for future exploration, scientific discovery, and national security. Missions in this region, spanning durations from weeks to decades, require robust infrastructure and reliable transit capabilities. The complex gravitational influences of the Moon, Sun, and planets, along with thermal radiation from Earth and the Sun, lead to significant trajectory deviations, resulting in kilometer-scale errors within days. Leveraging the high-performance computing resources at Lawrence Livermore National Laboratory (LLNL), we have simulated one million high-fidelity cislunar trajectories, now publicly available via LLNL’s Green Data Oasis and the Unified Data Library. Generated using the open-source Space Situational Awareness Python package, these trajectories match the precision of commercial tools such as AGI’s Systems Tool Kit and NASA’s General Mission Analysis Tool. This data set is a valuable resource for reference, statistical analysis of cislunar orbit populations, and training machine learning models for rapid orbit classification with minimal observational input. Preliminary analysis reveals stable bands in Keplerian element space, particularly around five geosynchronous radii across a range of inclinations and eccentricities. Beyond this threshold, the Moon’s influence disrupts most unassisted orbits, though co-orbiting L4/L5 Lunar Trojans persist throughout the six-year simulation.

Astronomy and AstroPhysics↗

DOE OSTI2023

Spread Spectrum Time Domain Reflectometry (SSTDR) and Frequency Domain Reflectometry (FDR) for Detection of Cable Anomalies Using Machine Learning

Cables are initially qualified for nuclear power plant use for 40 years. As plants extend their operating license to 60 and 80 years, continued use of these cables must shift to a performance-based approach since it is cost prohibitive to completely replace cables that are likely still capable of performing their design function. A variety of cable tests are available and are commonly applied during outages when the cables can be taken out of service. Frequency domain reflectometry (FDR) is one of these test methods that is being more broadly accepted and used because it not only detects anomalies along the cable with a low-voltage signal that does not stress the cable insulation, but the technique also locates the anomalies. This supports follow-up local inspection and local repair or partial replacement of a damaged cable segment. Currently, FDR testing is only applied to cables that are taken out of service since the test instrument would be damaged by operational voltages. A related technology that has found some acceptance in the aircraft and rail industry is spread spectrum time domain reflectometry (SSTDR). This technology has been implemented with a custom commercial instrument by LiveWire Innovation Inc. that is designed to operate on live cables up to 1000 volts. One of the main conclusions of a previous effort was that cable reflectometry plots can be difficult for humans to analyze due to baseline noise, low or noisy anomaly response peaks, or large responses from cable ends. Detection of cable anomalies for many of these frequencies and test conditions was challenging for manual analysis. This presented an ideal opportunity for ML analysis to distinguish undamaged cable indications from anomalous cable indications. This research discusses application of machine learning (ML) to reflectometry cable test methods. The goal was to assess feasibility to distinguish undamaged cable reflectometry responses from damaged or anomalous cable reflectometry responses. The assessment considered the 3 instruments, multiple frequency bandwidths from each instrument, multiple cable anomalies and test conditions, and both supervised and unsupervised ML approaches. Although approaches and analysis methods were not identical or directly comparable, both outputs were encouraging. The unsupervised prediction weighted accuracy was assessed by instrument and by frequency. It performed better at high frequencies with the highest prediction accuracy of 0.84 for the higher frequency FDR, 0.79 for the 48-MHz LiveWire SSTDR, and 0.77 for 300-MHz PNNL SSTDR. The initial weighted accuracy average across all frequencies for using supervised ML was 0.56 to 0.68. The supervised analysis was repeated with noisier training data removed resulting in weighted accuracies of 0.69 to 0.87. These weighted accuracies are not directly comparable due to differences in the supervised and unsupervised analysis details but do indicate an encouraging trend. Even with limited and unbalanced data, strong prediction accuracies seem encouraging for further work including more data under a wider range of conditions.

42 ENGINEERING↗

DOE OSTI2021

KBase partners with community developers from several Department of Energy Science Focus Areas to increase functionality of tools and analysis

Several SFAs were selected for training on the KBase Software Development Kit (SDK) to integrate tools and data into the KBase platform. Overall, the collaborative effort was viewed as highly successful. Every SFA project was able to achieve their proposed targets for training and functionality, while also gaining an appreciation for the role KBase plays/could play in their future science plans. Both the SFA and KBase teams felt that continued collaboration would be beneficial, especially if the programs were able to jointly prioritize scope and readiness of future projects. This poster will outline the scope of functionality added by SFA community developers, and highlight points of intersection across these efforts.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Multi-GeV wakefield acceleration in a plasma-modulated plasma accelerator

We investigate the accelerator stage of a plasma-modulated plasma accelerator (P-MoPA) [Jakobsson , ] using both the paraxial wave equation and particle-in-cell (PIC) simulations. We show that adjusting the laser and plasma parameters of the modulator stage of a P-MoPA allows the temporal profile of pulses within the pulse train to be controlled, which in turn allows the wake amplitude in the accelerator stage to be as much as 72 % larger than that generated by a plasma beat-wave accelerator with the same total drive laser energy. Our analysis shows that Rosenbluth-Liu detuning is unimportant in a P-MoPA if the number of pulses in the train is less than ∼ 30 , and that this detuning is also partially counteracted by increased red-shifting, and hence increased pulse spacing, towards the back of the train. An analysis of transverse mode oscillations of the driving pulse train is found to be in good agreement with 2D (Cartesian) PIC simulations. PIC simulations demonstrating energy gains of ∼ 1.5 GeV ( ∼ 2.5 GeV ) for drive pulse energies of 2.4 J ( 5.0 J ) are presented. Our results suggest that P-MoPAs driven by few-joule, picosecond pulses, such as those provided by high-repetition-rate thin-disk lasers, could accelerate electron bunches to multi-GeV energies at pulse repetition rates in the kilohertz range. Published by the American Physical Society 2024

van de Wetering, J. J. (ORCID:0000000303292355)↗

DOE OSTI2021

Characterizing Signatures of Geothermal Exploration Data with Machine Learning Techniques: An Application to the Nevada Play Fairway Analysis

We are introducing machine learning methods to the play fairway analysis to generate geothermal potential maps to support the evaluation of geothermal resource potential and the exploration for undiscovered blind geothermal systems in the Nevada Great Basin region. Our project aims to identify new ways to combine the play fairway data and empirically organize relationships between feature weights and labels in an improved workflow. As a means of doing this, we introduce machine learning methods to evaluate the influence of certain geological and geophysical features/feature sets in predicting geothermal favorability. This report highlights promising approaches based on supervised and unsupervised learning methods. First, we demonstrate a filter method applied to supervised classification modeling. The supervised filter method is based on permutation analysis to evaluate every possible feature combination/drop out scenario and rank feature influence based on the performance variance of supervised classification models. Additionally, we present an unsupervised factor analysis based on principal component analysis coupled with a semi-supervised kmeans clustering algorithm. This analysis allows us to identify the optimal number of groups/clusters for training sites and structural settings to identify feature patterns including correlation, variance, and latent and dominant feature relationships. The results from these methods offer a promising avenue for identifying favorable sources of predictive information to identify the locations of blind geothermal systems and furthering our understanding of complex geothermal feature and label relationships in the Great Basin region and beyond.

15 GEOTHERMAL ENERGY↗

DOE OSTI2022

Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.

Boice, Emily N. (ORCID:0000000171802842)↗

DOE OSTI2024

A Generative Model for Realistic Galaxy Cluster X-Ray Morphologies

Abstract The X-ray morphologies of clusters of galaxies display significant variations, reflecting their dynamical histories and the nonlinear dependence of X-ray emissivity on the density of the intracluster gas. Qualitative and quantitative assessments of X-ray morphology have long been considered a proxy for determining whether clusters are dynamically active or “relaxed.” Conversely, the use of circularly or elliptically symmetric models for cluster emission can be complicated by the variety of complex features realized in nature, spanning scales from megaparsecs down to the resolution limit of current X-ray observatories. In this work, we use mock X-ray images from simulated clusters from The Three Hundred project to define a basis set of cluster image features. We take advantage of the clusters’ approximate self-similarity to minimize the differences between images before encoding the remaining diversity through a distribution of high-order polynomial coefficients. Principal component analysis then provides an orthogonal basis for this distribution, corresponding to natural perturbations from an average model. This representation allows novel, realistically complex X-ray cluster images to be easily generated, and we provide code to do so. The approach provides a simple way to generate training data for cluster image analysis algorithms and could be straightforwardly adapted to generate clusters displaying specific types of features or selected by physical characteristics available in the original simulations.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2020

SAM Plug-in Development (Phase I Final Report)

The DOE Office of Nuclear Energy (NE) has created an extensive set of advanced modeling and simulation tools for nuclear engineering analysis. The advanced capabilities of these newer analysis codes require more in-depth training, skills, and knowledge in order to effectively utilize them for the design, analysis, and licensing of advanced nuclear systems and experiments. A high learning curve for inexperienced users may deter organizations from incorporating these tools into their internal processes. This project involved development of a plug-in to the Symbolic Nuclear Analysis Package (SNAP) for the System Analysis Module (SAM) tool. SAM is an advanced system analysis tool for reactor transient analyses being developed at Argonne National Laboratory under the U.S. DOE Office of Nuclear Energy’s Nuclear Energy Advanced Modeling and Simulation (NEAMS) program. SAM utilizes an object-oriented application framework (MOOSE), and its underlying meshing and finite-element library (libMesh) and linear and non-linear solvers (PETSc), to leverage modern advanced software environments and numerical methods. SNAP provides a highly flexible framework for creating, modifying and documenting input for engineering analysis codes such as SAM as well as extensive functionality for submitting, monitoring, and interacting with the codes through an intuitive graphical user interface (GUI). The common user interface provided by SNAP minimizes the learning curve for engineers starting with a new analysis code and provides an intuitive framework for transitioning between different analysis codes. SNAP provides a powerful but intuitive interface to facilitate access to advanced modeling and simulation tools for inexperienced users. Unlike many “form based” GUI’s, SNAP maps each engineering code’s component input to an internal database which manages all component input parameters along with component interconnections. This level of abstraction permits SNAP to support several advanced capabilities such as renodalization, model validation and consistency checks, embedded documentation, model notebook generation, data ownership and reviewer tracking, and variable assignment for inputs to name a few. SNAP includes a built-in Python interpreter and is interfaced to several commercial and open source packages including CPython, MATLAB/OCTAVE, Microsoft Office, Open Office, and SANDIA’s DAKOTA package which provides Uncertainty Quantification analysis through the SNAP plug-ins. Phase I of this project involved development a fully functional basic SAM plug-in to SNAP. This plug-in provides the ability to import existing models, graphically construct, edit and submit models using SNAP’s extensive functionality.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2026

Synthetic data-driven deep learning for label-free autonomous atomic force microscopy

Atomic force microscopy (AFM) is a widely used tool for nanoscale characterization across materials science, energy research, and biology. However, its adoption in high-throughput materials discovery and statistically driven studies remains limited by a strong dependence on expert operator input and by the scarcity of annotated experimental AFM datasets needed to enable data-driven automation. Here, we introduce SimuScan, a synthetic-data–driven framework that enables reliable AFM feature identification, segmentation, and targeted imaging without requiring large manually labeled experimental datasets. SimuScan generates tunable, high-fidelity synthetic AFM images of defined morphologies while incorporating realistic experimental artifacts, including tip–sample convolution, noise, flattening distortions, and surface debris. These datasets are shown to support scalable, label-free training of modern deep learning models for AFM analysis. When integrated into data-driven AFM workflows, SimuScan-trained models can locate and analyze nanoscale structures across large datasets and guide targeted follow-up imaging. We validate this approach on nanostructured surfaces, DNA assemblies, and bacterial cells, demonstrating robust generalization across diverse sample types with minimal operator intervention. More broadly, this work establishes a general strategy for generating explicitly conditioned, task-relevant synthetic data to improve the reliability of downstream models in autonomous microscopy.

Millan-Solsona, Ruben [Oak Ridge National Laborato↗

DOE OSTI2025

The Analysis Description Language Ecosystem: Latest developments and physics applications

We present latest developments in Analysis Description Language (ADL), a declarative domain-specific language describing the physics algorithm of a HEP data analysis decoupled from software frameworks. Analyses written in ADL can be integrated into any framework for various tasks. ADL is a multipurpose construct with uses ranging from analysis design to preservation, reinterpretation, queries, visualisation, combination, etc. The most advanced infrastructure to execute ADL on events is the CutLang runtime interpreter. Recent technical developments include an automated interface with different data types, generation of the abstract syntax tree, a visualization tool that that auto-converts analysis flows to graphs, incorporation of trained machine learning models and a Jupyter-based plotting tool. We also report physics implications including a large scale LHC analysis implementation and validation effort for beyond the standard model reinterpretation purposes and studies with ATLAS and CMS open data.

Sekmen, Sezen [Kyungpook National Univ., Daegu (Ko↗

DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗