Search NASA⌕ Search

SEARCH · Search NASA

Results for “distributed processing”

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 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

S 8 ring content in liquid sulfur determined from x-ray diffraction

The S 8 ring content in liquid sulfur has been determined from the 4.47 Å peak in the x-ray pair distribution function over the temperature range −55 °C –330 °C. This peak represents the characteristic 3rd and 4th nearest atom-atom distances across an S 8 -ring. Three procedures were used to calculate the S 8 -ring fraction; scaling to crystalline β-S, a linear combination fit and a direct integration method. All methods gave similar values, indicating that approximately one third of the S 8 -rings break up upon melting into a distribution of short chains with an average length of 5 ± 2 atoms. Our results contradict established models of low temperature sulfur that indicate below the λ-transition the liquid comprises almost entirely of S8-rings. In addition, we find the S 8 -ring fraction increases to 76 ± 10% at −30 °C in the supercooled liquid, and decreases to 23% ± 3% at 330 °C in the high temperature melt. First principle molecular dynamics calculations confirm the onset of dynamic ring distortion via broad bond angle distributions, associated with the interstitial region between the first and second peaks in the pair distribution function. Our results are consistent with the presence of a propensity of short chains in the low temperature liquid, that are required for the bond switching mechanism responsible for the polymerization process to occur at the λ-transition temperature, T λ .

lambda transition↗
DOE OSTI2025

Angle-dependent in Situ Fast Flavor Transformations in Post-neutron-star-merger Disks

Abstract The remnant black hole–accretion disk system resulting from binary neutron star mergers has proven to be a promising site for synthesizing the heaviest elements via rapid neutron capture ( r -process). A critical factor in determining the full r -process pattern in these environments is the neutron richness of the ejecta, which is strongly influenced by neutrino interactions. One key ingredient shaping these interactions is fast neutrino flavor conversions (FFCs), which arise due to angular crossings in neutrino distributions and occur on nanosecond timescales. We present the first three-dimensional in situ angle-dependent modeling of FFCs in postmerger disks, implemented within general relativistic magnetohydrodynamics with Monte Carlo neutrino transport. Our results reveal that, by suppressing electron neutrinos, FFCs more efficiently cool the disk and weaken the early thermally driven wind. Less releptonization due to electron neutrino absorption makes this cooler wind more neutron rich, producing a more robust r -process at higher latitudes of the outflow. This study underscores the necessity of incorporating FFCs in realistic simulations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Understanding the causes of satellite–model discrepancies in aerosol–cloud interactions using near-LES simulations of marine boundary layer clouds

Aerosol–cloud interactions (ACI) remain the largest source of uncertainty in model estimates of anthropogenic radiative forcing, primarily because of deficiencies in representing aerosol–cloud microphysical processes that lead to inconsistent cloud liquid water path (LWP) responses to aerosol perturbations between observations and models. To investigate this discrepancy, we conducted a series of large-eddy-scale simulations driven by realistic meteorology over the eastern North Atlantic, and evaluated LWP susceptibility, precipitation processes, and boundary layer thermodynamics using satellite and ground-based observations. Simulated LWP responses show a strong dependence on cloud state. Non-precipitating thin clouds exhibit a modest LWP decrease with increasing cloud droplet number concentration (N d ), consistent in sign but weaker in magnitude than satellite estimates, reflecting enhanced turbulent mixing and evaporation. The largest model-observation discrepancy occurs in non-precipitating thick clouds, where simulated LWP susceptibilities are strongly positive (+0.32) while observations indicate large negative values (−0.69). This discrepancy stems from excessive precipitation driven by underestimated entrainment, overly active accretion, and overly broad drop-size distributions in polluted conditions. While our high-resolution setup mitigates the excessive drizzling common in coarser models and captures key regime transitions, these biases persist – highlighting that improved parameterizations of cloud-top processes, precipitation, and aerosol effects are needed beyond simply increasing model resolution. Additionally, misrepresented moisture inversions in reanalysis introduce a moist bias in cloud-top relative humidity, further amplifying positive LWP susceptibility. Our results also suggest that large negative N d –LWP relationships in observations may reflect internal cloud processes rather than true ACI effects.

Aerosol-cloud interaction↗
DOE OSTI2026

Data and scripts associated with a manuscript modeling microbial regulation of priming effects

This data package is associated with the publication “Modeling Microbial Regulatory Feedback in Organic Matter Decomposition Identifies Copiotrophic Traits as Key Drivers of Positive Priming” published as a preprint on BioRXiv by Ahamed et al. (2026); https://doi.org/10.1101/2024.08.11.607483. The package contains MATLAB scripts and saved simulation outputs used to implement a cybernetic model of microbial regulation during complex organic matter (OM) decomposition governing priming effects. It includes models of (i) single microbial functional groups (copiotrophic or oligotrophic degraders) and (ii) binary consortia composed of degraders and non-degraders with contrasting or common growth traits. Simulation results were generated using Monte Carlo analyses, with randomized key model parameters across a range of environmental mixing fractions of complex and labile OM. The dataset was created to provide a transparent and reusable computational framework for systematically exploring how microbial growth traits, metabolic regulation, and community composition influence OM decomposition dynamics and priming effects. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. In addition to a readme, this data package also includes a file-level metadata (FLMD) file that describes each file and a data dictionary (DD) that describes the variable definitions. This package includes: (1) annotated MATLAB code implementing the system of ordinary differential equations and cybernetic control laws; (2) saved output files containing data (e.g., biomass, substrates, enzyme levels, priming metrics); and (3) scripts for processing saved outputs and regenerating figures. Specifically, the data package contains three main MATLAB scripts: runPrimingModel.m, runPlotData.m, and runPlotSuppFigS1.m, along with this readme and supporting documentation. Users should begin with runPrimingModel.m, which contains the annotated code implementing the system of ordinary differential equations and cybernetic control laws. This script runs the Monte Carlo simulations of microbial OM decomposition and allows users to modify microbial trait definitions, adjust parameter distributions, or define new community configurations. Simulation outputs are automatically saved as .mat files in the folder named SavedData, which stores all pre-generated results included in this package. The second script, runPlotData.m, reads files from the SavedData folder and processes them to regenerate the figures presented in the manuscript. The third script, runPlotSuppFigS1.m, specifically generates Figure S1 in the Supplementary Material of the manuscript. The package also includes the aforementioned files in non-proprietary .txt format. If users intend to use them, they should first save the files in their respective .m or .mat formats prior to execution in MATLAB.

Biomass concentration↗
DOE OSTI2024

Hydropower Black Start: A Guidebook for Retrofitting Grid Dependent Hydropower

Not all United States (US) hydropower plants were designed to provide black start, but they are increasingly needed to uphold resilience in the evolving electric grid. This guidance is designed to help understand the minimal retrofits required for grid dependent hydropower (GDH) plants behind the point of interconnection (POI). For distribution connected hydropower plants or those with dedicated cranking paths, such upgrades can be sufficient for the plant to provide black start. For others, more coordination with the transmission system operator will be needed. This guidebook answers a number of questions relevant to retrofitting hydropower plants with black start capabilities. For example, the guidebook answers: • How flexible do the wicket gate controls need to be? • Who needs to do hydro governor model validation, why, and how? • How robust and flexible do the excitation and AVR controls need to be? • What protection settings need to be adjusted? • What relay(s) will need to be bypassed or overridden and at what risk? • What is the electrical energy demand of the station load or auxiliary power systems? • What should the strategy to energize transformer(s) along cranking path to address inrush currents be? • How should the critical load restoration be sequenced? In addition to outlining the specifications that hydropower plants need to meet for each component to be able to perform black start, this guidebook provides a set of case studies for specific upgrades needed at actual plants. Between the case studies of plants that have already performed black start retrofits and the examples of how this guidebook can be applied to scope future retrofits, five key themes have been identified for retrofit needs. 1. Protection needs “black start” mode: hydropower plants that are not designed with black start capabilities will have protections that prevent them from interconnecting to a “dead bus.” These protections will need to be overridden in every retrofit case and a separate black start mode should be established so that operators can safely switch between black start and grid connected modes, minimizing the risk to the plant. 2. Wicket gates need modern controls: digital governors accelerate the parameter tuning process and gate position sensors improve controllability, so plants with mechanical governors should be upgraded. Furthermore, a black start and islanding mode should be established for controls to maximize plant performance. 3. Robust excitation support: the DC system or excitation generator needs to be reliable enough to form and sustain the rotor electromagnetic field. These systems are typically undersized in plants that were not designed for black start, so they will need to be upgraded. 4. Turbine-governor model validation and operator training: validation of a standard hydro governor model is needed to characterize the dynamic response (i.e., inertial and primary frequency response) of the GDH. This is required for control development and old hydropower plants often have outdated or incorrect models. Operator training is also typically required to ensure the hardware retrofits are utilized correctly during the black start process. 5. Transformer and cranking path energization: any upgradation and control adjustment in front of the POI will depend upon the existing interconnection. Coordination with the transmission or distribution operator may be required.

13 HYDRO ENERGY↗
DOE OSTI2026

Assessing Uncertainty in Solar Measurements: Key Findings From NLR's SUNI Application Across 89 Stations

The Solar Uncertainty Integrator (SUNI) study was developed by the National Laboratory of the Rockies (NLR's) to provide a standardized "bulk uncertainty processing" method for solar irradiance data, which are essential for the successful deployment of solar energy systems. This poster provides an overview of key findings from NLR's SUNI application across 89 stations.

14 SOLAR ENERGY↗
DOE OSTI2025

γIn-beam angular distribution and linear polarization measurements with GRETINA using a simple energy-ordering approach

Angular distribution and linear polarization measurements are powerful tools for inferring the spins and parities of nuclear levels. In this work, the performance of the Gamma-Ray Energy Tracking In-beam Nuclear Array (GRETINA) as a Compton polarimeter was characterized in a fusion-evaporation reaction experiment using a simple energy-ordering approach for the interaction points assigned in the signal decomposition process. A variety of multipolarities and characters for γ-ray transitions in the reaction products 25 Mg, 25 Na, and 22 Ne, formed from fusion-evaporation of an 18 O beam on a 9 Be target, were examined. The experimental angular distributions and linear polarization asymmetries were consistent with predictions using the theoretical formalism accounting for the Lorentz boost.

Angular distribution↗
DOE OSTI2024

Hydrogen Leak Modeling for Development of Smart Distributed Monitoring Under Unintended Releases

Hydrogen is a versatile and clean energy carrier that can be produced from various renewable sources such as wind, solar, and hydropower. Hydrogen has the potential to play a crucial role in decarbonizing industrial processes that are currently reliant on fossil fuels and provide long-duration and/or seasonal energy storage to enable electricity decarbonization. Hydrogen can also be used as a fuel for fuel cell vehicles, providing a zero-emission alternative to traditional internal combustion engines. DOE launched the Hydrogen Energy Earthshot (Hydrogen Shot) in June 2021 to reduce the cost of clean hydrogen by 80% to $1 per 1 kilogram in 1 decade ("1 1 1"). While promising, Hydrogen is highly-flammable, and in the presence of oxygen, it can form explosive mixtures. . Therefore, understanding leak scenarios is essential to evaluate and mitigate the safety risks associated with potential hydrogen leaks. An increased understanding of leak behavior, and having tools to model leaks, can help assess how hydrogen would disperse in different environments, influencing emergency response plans and safety measures, and identify potential issues with materials and design systems that can withstand the challenges posed by hydrogen. Recently, researchers have attempted to study hydrogen leaks for development of risk management strategies. However, the focus has been on closed or semi-closed spaces like storage rooms, vehicles, garages, and fueling stations - all promising locations for future hydrogen infrastructure. In this presentation, the modeling environment extends the span of research further by modeling hydrogen leak in an outdoor, open space. We will present the key challenges with modeling hydrogen leaks in an uncontrollable environment, how they were handled, and how modeling results informed sensor selection and placement. A Hydrogen research facility at the National Renewable Energy Laboratory (NREL) was used as a case study to model hydrogen leaks. In the future, Hydrogen wide area detection methodologies will be developed and tested at this site to monitor for unintended and operational hydrogen releases. The data generated from modeling will be used to develop a predictive model to detect hydrogen leak location based on concentration measured by sensors in this open space. Furthermore, the facility was also chosen because controlled hydrogen releases can be performed. A computational fluid dynamics (CFD) based modeling approach was taken to model hydrogen leak. The full-scale hydrogen facility was modeled with a large ambient domain. The electrolyzer at the facility can produce a controlled release rate of 27 kg-H2/hr. Site-specific atmospheric and weather condition data such as wind direction, wind speed at various altitudes, and temperature were used as inputs to the model. To capture the variability of weather conditions, a subset of the weather conditions experienced during daytime hours without precipitation over the course of three months was generated; using established data clustering techniques, a total of 100 condition sets were chosen. The results show statistical distributions and ranges of hydrogen concentrations at locations throughout the domain. These distributions are compared to experimental data from a constant mass flow, controlled hydrogen release at the facility. The stochastic wind conditions of the release make direct validation difficult, therefore, statistical comparison approaches were used. Wind conditions are found to significantly impact the release behavior, including direction and concentration. Sensor selection and placement is proposed for the facility and is now based on release behavior predicted for the facility given its weather patterns; this is much more informed than without the modeling results. The methodology and analysis procedure can be translated to other facilities using modified geometries and site-specific weather conditions. Hydrogen holds great promise as a renewable energy fuel, but ensuring safety in its production, storage, and use is paramount. Studying potential leak scenarios in an open space will help develop sensors to detect hydrogen on a large spectrum of concentration and eventually build a smart distributed monitoring system.

CFD↗
DOE OSTI2025

Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that poses the problem of learning low-dimensional model terms as a regression of state space data and corresponding time derivatives by minimizing the residual of reduced system equations. Standard operator inference models perform well with accurate training data that are dense in time, but producing stable and accurate models when the state data are noisy and/or sparse in time remains a challenge. Another challenge is the lack of uncertainty estimation for the predictions from the operator inference models. Our approach addresses these challenges by incorporating Gaussian process surrogates into the operator inference framework to (1) probabilistically describe uncertainties in the state predictions and (2) procure analytical time derivative estimates with quantified uncertainties. The formulation leads to a generalized least-squares regression and, ultimately, reduced-order models that are described probabilistically with a closed-form expression for the posterior distribution of the operators. The resulting probabilistic surrogate model propagates uncertainties from the observed state data to reduced-order predictions. Furthermore, we demonstrate the method is effective for constructing low-dimensional models of two nonlinear partial differential equations representing a compressible flow and a nonlinear diffusion–reaction process, as well as for estimating the parameters of a low-dimensional system of nonlinear ordinary differential equations representing compartmental models in epidemiology.

Data-driven model reduction↗
DOE OSTI2025

Laser-induced slip casting as an additive manufacturing approach for silicon carbide

Here, this work presents processing silicon carbide (SiC) with the laser-induced slip casting (LIS) additive manufacturing (AM). SiC was stabilized in water with polyethyleneimine (PEI) dispersant, and SiC slurries were made with rheology for LIS printing. High-density ceramic parts were printed, followed by single-step binder burnout and sintering. The printed parts achieved 93–95 % of theoretical density. X-ray computed tomography (XCT) revealed a small distribution of flaws exceeding 100 microns. The mechanical properties were measured in both parallel and perpendicular to the printing layers, and the orientation with layers perpendicular to the bending moment resulted in higher strength compared to the parallel direction. Porosity resulting from processing and large inclusions of boron carbide (B4C) were the root cause of failure in the measured samples. Despite these defects through this effort, this new approach demonstrates promise for green forming of SiC with densities greater than 95 % theoretical and tensile strengths above 250 MPa.

Additive Manufacturing↗
DOE OSTI2025

Scalable training of trustworthy and energy-efficient predictive graph foundation models for atomistic materials modeling: a case study with HydraGNN

We present our work on developing and training scalable, trustworthy, and energy-efficient predictive graph foundation models (GFMs) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) computations in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define nearest-neighbor convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFMs training to tens of thousands of GPUs on datasets consisting of hundreds of millions of graphs. Our GFMs use multitask learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as energy and atomic forces. Using over 154 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two state-of-the-art US Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge Leadership Computing Facility. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2000 GPUs on Perlmutter and 16,000 GPUs on Frontier.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Controlled large-area lithium deposition to reduce swelling of high-energy lithium metal pouch cells in liquid electrolytes

Lithium (Li) metal battery technology, renowned for its high energy density, faces practical challenges, particularly concerning large volume change and cell swelling. Despite the profound impact of external pressure on cell performance, there is a notable gap in research regarding the interplay between external pressure and the electroplating behaviours of Li+ in large-format pouch cells. Here we delve into the impact of externally applied pressure on electroplating and stripping of Li in 350 Wh kg –1 pouch cells. Employing a hybrid design, we monitor and quantify self-generated pressures, correlating them with observed charge–discharge processes. A two-stage cycling process is proposed, revealing controlled pouch cell swelling of less than 10%, comparable to state-of-the-art Li-ion batteries. Finally, the pressure distribution across the cell surface unveils a complex Li+ detour behaviour during electroplating, highlighting the need for innovative strategies to address uneven Li plating and enhance Li metal battery technology.

25 ENERGY STORAGE↗
DOE OSTI2025

Measurements of radial neutral density profiles from Balmer- α emission in Wendelstein 7-X

Radial neutral density profiles are estimated from measurements of passive H α emission in the Wendelstein 7-X stellarator. To parametrize the generally three-dimensional distribution with a low number of degrees of freedom, the neutral density is reduced to a flux surface quantity. Accounting for emission from excitation and recombination processes, neutral density profiles are derived independently for each of the available lines of sight. Density profiles obtained from the different viewing geometries are found to vary within one order of magnitude. Toroidally oriented lines of sight predict systematically lower neutral densities when compared to poloidally oriented ones. This discrepancy is attributed to the simplifications inherent in the imposed model and significant differences in integration volumes across the viewing geometries. In line with expectations, obtained neutral densities are found to decrease with increasing plasma density. Key restrictions of the model include the reduction of the neutral density to a flux surface quantity, uncertainties in the plasma profiles and instrument function, and line integration effects outside the last closed flux surface.

Wendelstein 7-X↗
DOE OSTI2024

Bayesian Neural Network Variational Autoencoder Inverse Mapper (BNN-VAIM) and its application in Compton Form Factors extraction

Abstract We extend the Variational Autoencoder Inverse Mapper (VAIM) framework for the inverse problem of extracting Compton Form Factors (CFFs) from deeply virtual exclusive reactions, such as the unpolarized Deeply virtual exclusive scattering (DVCS) cross section. VAIM is an end-to-end deep learning framework to address the solution ambiguity issue in ill-posed inverse problems, which comprises of a forward mapper and a backward mapper to simulate the forward and inverse processes, respectively. In particular, we incorporate Bayesian Neural Network (BNN) into the VAIM architecture (BNN-VAIM) for uncertainty quantification. By sampling the weights and biases distributions of the BNN in the backward mapper of the VAIM, BNN-VAIM is able to estimate prediction uncertainty associated with each individual solution obtained for an ill-posed inverse problem. We first demonstrate the uncertainty quantification capability of BNN-VAIM in a toy inverse problem. Then, we apply BNN-VAIM to the inverse problem of extracting 8 CFFs from the unpolarized DVCS cross section.

Instruments & Instrumentation↗
DOE OSTI2025

Electromagnetic energy calibration of the SoLid detector with horizontal muons

SoLid is a neutrino experiment at very-short baselinesearching for active-to-sterile oscillations of reactorantineutrinos. The detection principle is based on the pairing oftwo types of solid scintillators: polyvinyl toluene and $^{6}$Li:ZnS(Ag), which is a new technology used in this field ofPhysics. In addition to good neutron-gamma discrimination, thissetup allows the detector to be highly segmented; the basicdetection unit is a 5 cm cube. High segmentation provides numerousadvantages including precise localisation of the Inverse Beta Decay(IBD) products, the derivation of an antineutrino energy estimatorbased on the isolated positron energy, and a powerful backgroundreduction tool that relies on the topological signature of thesignal. Finally, the system is read out by a network ofwavelength-shifting fibres coupled to photosensors. A relativeelectromagnetic calibration is performed with horizontal cosmicmuons. This source poses the simplest calibration problem in which asingle detection unit is involved. In addition, large muon energydeposits allow us to perform a calibration at the most detailedlevel (i.e. per fibre) and to accurately define the fraction ofenergy escaping to neighbouring detection cells. A statisticalprecision at the sub-percent level is reached. The paper alsodiscusses two methods to calibrate the absolute energy scale andpresents their implementation and results. The first method relieson horizontal muons, though the precision is limited to around 10%because of the uncertainty in the energy distribution of suchmuons. A novel, alternative method based on the radioactiveamericium-beryllium source is proposed. It takes advantage of theelectron-positron pair-production process and provides a calibrationpoint at 3.4 MeV (i.e. in the core of the IBD positronspectrum). The paper is concluded with various cross-check includinga determination of the energy spectrum of the standard cosmogenicbackground candle: $^{12}$B.

Abreu, Y. [Antwerp U.]↗
DOE OSTI2024

Parasitic Modulation of Microwave Signals by a Hypersonic Plasma Layer

During hypersonic flight, compressional and viscous heating of the air can form a plasma layer which encases the aircraft. If the boundary layer becomes turbulent, then the electron density fluctuations can effect a parasitic modulation in microwave signals transmitted through the plasma. We developed an approach for studying the interaction of microwave signals with a turbulent, hypersonic plasma layer. The approach affords a great deal of flexibility in both the plasma layer model and the antenna configuration. We then analyzed a situation in which microwaves, transmitted from a rectangular aperture antenna, propagate through a turbulent plasma layer to a distant receiver. We characterized the first-and second-order statistics of the computed parasitic modulation and quantified the depolarization of the signal. The amplitude fluctuations are lognormally distributed at low frequencies and Rice-distributed at high frequencies. Fluctuations in the copolarized phase and amplitude of the far-field signal are strongly anticorrelated. Here, we used a multioutput Gaussian process (MOGP) to model these quantities. The efficacy of the MOGP model is demonstrated by recovering the time evolution of the copolarized phase given the copolarized amplitude and occasional measurements of the phase.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Uncertainty propagation and sensitivity analysis for constrained optimization of nuclear waste vitrification

Abstract The vitrification of high‐level waste (HLW) by heating a mixture of glass‐forming chemicals (GFCs) with the waste can be improved using a constrained optimization problem. This study explores how different uncertainty propagation (UP) methods implemented with the optimization process can affect the glass formulation of nuclear waste glasses. UP is the effort of propagating uncertain inputs through a system to understand and quantify output distributions. Uncertainty intervals are crafted from output distributions to inform the optimization algorithm. UP is often implemented with Monte Carlo (MC) sampling for large nonlinear systems, which can be difficult to implement within a constrained optimization algorithm that requires derivative information. Other UP methods often used for optimization under uncertainty (OUU) can be designed to work within an established constrained optimization framework. Methods of UP are evaluated in this study including iterative sampling approaches, first‐order approximations, and surrogate modeling with machine learning (ML). A method of dimensional reduction based on global sensitivity analysis is introduced to support the UP methods for the large dimensionality of the problem. Analytical UP methods able to achieve similar optimums 10 times faster than the baseline MC approach, and produce 93.9% similar output distributions are reported.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Smart Pixels: In-pixel AI for on-sensor data filtering

We present a smart pixel prototype readout integrated circuit (ROIC) designed in CMOS 28 nm bulk process, with in-pixel implementation of an artificial intelligence (AI) / machine learning (ML) based data filtering algorithm designed as proof-of-principle for a Phase III upgrade at the Large Hadron Collider (LHC) pixel detector. The first version of the ROIC consists of two matrices of 256 smart pixels, each 25$\times$25 µm\textsuperscript{2} in size. Each pixel consists of a charge-sensitive preamplifier with leakage current compensation and three auto-zero comparators for a 2-bit flash-type ADC. The frontend is capable of synchronously digitizing the sensor charge within 25 ns. Measurement results show an equivalent noise charge (ENC) of $\sim$30e\textsuperscript{-} and a total dispersion of $\sim$100e\textsuperscript{-} The second version of the ROIC uses a fully connected two-layer neural network (NN) to process information from a cluster of 256 pixels to determine if the pattern corresponds to highly desirable high-momentum particle tracks for selection and readout. The digital NN is embedded in-between analog signal processing regions of the 256 pixels without increasing the pixel size and is implemented as fully combinatorial digital logic to minimize power consumption and eliminate clock distribution, and is active only in the presence of an input signal. The total power consumption of the neural network is $\sim$ 300 $\mu$W. The NN performs momentum classification based on the generated cluster patterns and even with a modest momentum threshold, it is capable of 54.4\% – 75.4\% total data rejection, opening the possibility of using the pixel information at 40MHz for the trigger. The total power consumption of analog and digital functions per pixel is $\sim$ 6 $\mu$W per pixel, which corresponds to $\sim$ 1 W/cm\textsuperscript{2} staying within the experimental constraints.

Parpillon, Benjamin↗