Search NASA⌕ Search

SEARCH · Search NASA

Results for “NN”

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 397 records · Page 22
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Nuclear structure and elastic scattering observables obtained consistently with different N N interactions

Nucleon-nucleon ($NN$) interactions based on chiral effective theories are commonly used in ab initio calculations of light nuclei. Here we present a study based on three different $NN$ interactions (up to next-to-next-to-leading order) for which structure and elastic proton scattering observables are consistently calculated for $^4$He, $^{12}$C, and $^{16}$O. The interactions are compared at the two-body level in terms of Wolfenstein amplitudes, and their predictions for ground state energies, point-proton radii, and charge form factors, as well as proton elastic scattering observables in the leading-order spectator expansion in the energy range between 65 and 160 MeV projectile energy are presented. Finally, to gain further insight into differences visible in elastic scattering observables, we investigate the behavior of the calculated effective nucleon-nucleus interactions for the $^{12}$C nucleus based on the different $NN$ interactions.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Assessing correlated truncation errors in modern nucleon-nucleon potentials

We test the BUQEYE model of correlated effective field theory (EFT) truncation errors on Reinert, Krebs, and Epelbaum's semilocal momentum-space implementation of the chiral EFT (𝜒⁢EFT ) expansion of the nucleon-nucleon (NN) potential. This Bayesian model hypothesizes that dimensionless coefficient functions extracted from the order-by-order corrections to NN observables can be treated as draws from a Gaussian process (GP). We combine a variety of graphical and statistical diagnostics to assess when predicted observables have a 𝜒⁢EFT convergence pattern consistent with the hypothesized GP statistical model. Our conclusions are that, first, the BUQEYE model is generally applicable to the potential investigated here, which enables statistically principled estimates of the impact of higher EFT orders on observables. Second, parameters defining the extracted coefficients such as the expansion parameter 𝑄 must be well chosen for the coefficients to exhibit a regular convergence pattern—a property we exploit to obtain posterior distributions for such quantities. Third, the assumption of GP stationarity across lab energy and scattering angle is not generally met; this necessitates adjustments in future work. We provide a workflow and interpretive guide for our analysis framework, and show what can be inferred about probability distributions for 𝑄, the EFT breakdown scale Λ 𝑏 , the scale associated with soft physics in the 𝜒⁢EFT potential 𝑚 eff , and the GP hyperparameters. All our results can be reproduced using a publicly available Jupyter notebook, which can be straightforwardly modified to analyze other 𝜒⁢EFT NN potentials.

Bayesian methods↗
DOE OSTI2022

Extraction of low-energy constants of single- and double-β decays from lattice QCD: A sensitivity analysis

Lattice quantum chromodynamics (LQCD) has the promise of constraining low-energy constants (LECs) of nuclear effective field theories (EFTs) from first-principles calculations that incorporate the dynamics of quarks and gluons. Given the Euclidean and finite-volume nature of LQCD outputs, complex mappings are developed in recent years to obtain the Minkowski and infinite-volume counterparts of LQCD observables. In particular, as LQCD is moving toward computing a set of important few-nucleon matrix elements at the physical values of the quark masses, it is important to investigate whether the anticipated precision of LQCD spectra and matrix elements will be sufficient to guarantee tighter constraints on the relevant LECs than those already obtained from phenomenology, considering the nontrivial mappings involved. With a focus on the leading-order LECs of the pionless EFT, L 1,A and $g$$^{NN}_{v}$, which parametrize, respectively, the strength of the isovector axial two-body current in a single-β decay (and other related processes such pp fusion), and of the isotensor contact two-body operator in the neutrinoless double-β decay within the light neutrino exchange scenario, the expected uncertainty on future extractions of L 1,A and $g$$^{NN}_{v}$ are examined using synthetic data at the physical values of the quark masses. It is observed that achieving small uncertainties in L 1,A will be challenging, and (sub)percent-level precision in the two-nucleon spectra and matrix elements is essential in reducing the uncertainty on this LEC compared to the existing constraints. On the other hand, the short-distance coupling of the neutrinoless double-β decay, $g$$^{NN}_{v}$, is shown to be less sensitive to uncertainties on both LQCD energies and the matrix element, and can likely be constrained with percent-level precision in the upcoming LQCD calculations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Nonmonotonic Energy Dependence of Net-Proton Number Fluctuations

Nonmonotonic variation with collision energy (√ s NN) of the moments of the net-baryon number distribution in heavy-ion collisions, related to the correlation length and the susceptibilities of the system, is suggested as a signature for the quantum chromodynamics critical point. Here, we report the first evidence of a nonmonotonic variation in the kurtosis times variance of the net-proton number (proxy for net-baryon number) distribution as a function of √ s NN with 3.1 σ significance for head-on (central) gold-on-gold (Au+Au) collisions measured solenoidal tracker at Relativistic Heavy Ion Collider. Data in noncentral Au+Au collisions and models of heavy-ion collisions without a critical point show a monotonic variation as a function of √ s NN.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Collision-System and Beam-Energy Dependence of Anisotropic Flow Fluctuations

Here, elliptic flow measurements from two-, four- and six-particle correlations are used to investigate flow fluctuations in collisions of U+U at $\sqrt{s_{NN}}$ = 193 GeV, Cu+Au at $\sqrt{s_{NN}}$ = 200 GeV and Au+Au spanning the range $\sqrt{s_{NN}}$ = 11.5 - 200 GeV. The measurements show a strong dependence of the flow fluctuations on collision centrality, a modest dependence on system size, and very little if any, dependence on particle species and beam energy. The results, when compared to similar LHC measurements, viscous hydrodynamic calculations, and Glauber model eccentricities, indicate that initial-state-driven fluctuations predominate the flow fluctuations generated in the collisions studied.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Nucleation and growth of polar clusters with in-phase tilts into a long-range ferroelectric matrix in a sodium niobate based complex relaxor

In this study, we have investigated the temperature dependence of atomic ordering at multiple length scales in a lead-free sodium niobate-based relaxor, i.e., 0.75 NaNbO 3 -0.25 Ba 0.9⁢ Ca 0.1⁢ TiO 3 (NN-25BCT) via synchrotron x-ray diffraction, Raman spectroscopy, and pair distribution function analysis. High-resolution synchrotron x-ray powder diffraction (SXRD) measurements reveal a ferroelectric phase transition in the relaxor ferroelectric NN-25BCT below the Vogel-Fulcher freezing temperature (𝑇 VF ≈ 270 K). In addition, SXRD analysis demonstrates the competition between in-phase octahedral tilting and ferroelectric order at the long-range scale using mode crystallography. On the other hand, Raman spectroscopic analysis provides evidence of polar ordering for 𝑇 > 𝑇 VF (with tetragonal symmetry) persisting up to the Burns temperature (𝑇 B ). Furthermore, pair distribution function (PDF) analysis reveals the presence of a polar antiferrodistortive tetragonal phase with 𝑃⁢4⁢𝑏𝑚 space group at short ranges throughout the studied temperatures (i.e., 110 K ≤ 𝑇 ≤500 K), irrespective of nonpolar long-range ordering above 𝑇 VF . Therefore, our measurements provide direct evidence for the presence of polar ordering at short ranges and their gradual transformation into long-range polar ordering using an integrated multiscale structural analysis. In conclusion, as a result of a transition from relaxor to a ferroelectric phase in the vicinity of room temperature, NN-25BCT can be exploited for applications in pyroelectric detectors, electrocaloric devices, and multilayered ceramic capacitors.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Neural Network Molecular Dynamics at Scale

Neural network molecular dynamics (NNMD) simulations could revolutionize atomistic modeling of materials with quantum-mechanical accuracy at a fraction of computational cost. However, popular NNMD frameworks are generally implemented for a single computing node, and conventional energy-based NN models still suffer from large time-to-solution (T2S), prohibiting the application of NNMD to challenging materials simulations encompassing large spatiotemporal scales. Consequently, no leadership-scale NNMD simulation has thus far been reported. Here, we present a scalable parallel NNMD software (RXMD-NN) based on our scalable reactive molecular dynamics simulation engine named RXMD. RXMD-NN has achieved high scalability up to 786,432 IBM BlueGene/Q cores involving 1.7 billion atoms. Furthermore, we have achieved 4.6-fold reduction of T2S by using a novel network that directly predicts atomic forces from feature vectors. Reduced T2S has for the first time allowed the study of large-scale off-stoichiometry effect in a widely used phase change material, Ge 2 Se 2 Te 5 , thereby resolving its "firstsharp diffraction peak mystery".

fist sharp diffraction peak↗
DOE OSTI2020

Adapting In Situ Accelerators for Sparsity With Granular Matrix Reordering

Neural network (NN) inference is an essential part of modern systems and is found at the heart of numerous applications ranging from image recognition to natural language processing. In situ NN accelerators can efficiently perform NN inference using resistive crossbars, which makes them a promising solution to the data movement challenges faced by conventional architectures. Although such accelerators demonstrate significant potential for dense NNs, they often do not benefit from sparse NNs, which contain relatively few non-zero weights. Processing sparse NNs on in situ accelerators results in wasted energy to charge the entire crossbar where most elements are zeros. To address this limitation, this paper proposes Granular Matrix Reordering (GMR): a preprocessing technique that enables an energy-efficient computation of sparse NNs on in situ accelerators. GMR reorders the rows and columns of sparse weight matrices to maximize the crossbars' utilization and minimize the total number of crossbars needed to be charged. The reordering process does not rely on sparsity patterns and incurs no accuracy loss. Finally, GMR achieves an average of 28% and up to 34% reduction in energy consumption over seven pruned NNs across four different pruning methods and network architectures.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Anticipating Technical Expertise and Capability Evolution in Research Communities Using Dynamic Graph Transformers

The ability to anticipate global technical expertise and capability evolution trends is essential for national and global security, especially in safety-critical domains such as nuclear nonproliferation (NN) and rapidly emerging fields like artificial intelligence (AI). Here, in this work, we extend traditional statistical relational learning approaches (e.g., link prediction in collaboration networks) and formulate a problem of anticipating technical expertise and capability evolution using dynamic heterogeneous graph representations. We develop novel capabilities to forecast collaboration patterns, authorship behavior, and technical capability evolution at different granularities (e.g., scientist and institution levels) in two distinct research fields. We implement a dynamic graph transformer (DGT) neural architecture, which pushes the state-of-the-art graph neural network models by: 1) forecasting heterogeneous (rather than homogeneous) nodes and edges; and 2) relying on both discrete- and continuous-time inputs. We demonstrate that our DGT models predict collaboration, partnership, and expertise patterns with 0.26, 0.73, and 0.53 mean reciprocal rank values for AI and 0.48, 0.93, and 0.22 for NN domains. DGT model performance exceeds the best-performing static graph baseline models by 30%–80% across AI and NN domains. Our findings demonstrate that DGT models boost inductive task performance when previously unseen nodes appear in the test data for the domains with emerging collaboration patterns (e.g., AI). Specifically, models accurately predict which established scientists will collaborate with early career scientists and vice versa in the AI domain.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n e ) and electron temperature (T e ) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I p ), toroidal magnetic field (B Φ ), neutral beam heating power (P NBI ) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2020

Partitioning net carbon dioxide fluxes into photosynthesis and respiration using neural networks

The eddy covariance (EC) technique is used to measure the net ecosystem exchange (NEE) of CO 2 between ecosystems and the atmosphere, offering a unique opportunity to study ecosystem responses to climate change. NEE is the difference between the total CO 2 release due to all respiration processes (RECO), and the gross carbon uptake by photosynthesis (GPP). These two gross CO 2 fluxes are derived from EC measurements by applying partitioning methods that rely on physiologically based functional relationships with a limited number of environmental drivers. However, the partitioning methods applied in the global FLUXNET network of EC observations do not account for the multiple co-acting factors that modulate GPP and RECO flux dynamics. To overcome this limitation, we developed a hybrid data-driven approach based on combined neural networks (NN C-part ). NN C-part incorporates process knowledge by introducing a photosynthetic response based on the light-use efficiency (LUE) concept, and uses a comprehensive dataset of soil and micrometeorological variables as fluxes drivers. We applied the method to 36 sites from the FLUXNET2015 dataset and found a high consistency in the results with those derived from other standard partitioning methods for both GPP (R 2 > .94) and RECO (R 2 > .8). High consistency was also found for (a) the diurnal and seasonal patterns of fluxes and (b) the ecosystem functional responses. NNC-part performed more realistic than the traditional methods for predicting additional patterns of gross CO 2 fluxes, such as: (a) the GPP response to VPD, (b) direct effects of air temperature on GPP dynamics, (c) hysteresis in the diel cycle of gross CO 2 fluxes, (d) the sensitivity of LUE to the diffuse to direct radiation ratio, and (e) the post rain respiration pulse after a long dry period. In conclusion, NN C-part is a valid data-driven approach to provide GPP and RECO estimates and complementary to the existing partitioning methods.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Accelerating iterative ptychography with an integrated neural network

Electron ptychography is a powerful and versatile tool for high-resolution and dose-efficient imaging. Iterative reconstruction algorithms are powerful but also computationally expensive due to their relative complexity and the many hyperparameters that must be optimised. Gradient descent-based iterative ptychography is a popular method, but it may converge slowly when reconstructing low spatial frequencies. Here, in this work, we present a method for accelerating a gradient descent-based iterative reconstruction algorithm by training a neural network (NN) that is applied in the reconstruction loop. The NN works in Fourier space and selectively boosts low spatial frequencies, thus enabling faster convergence in a manner similar to accelerated gradient descent algorithms. We discuss the difficulties that arise when incorporating a NN into an iterative reconstruction algorithm and show how they can be overcome with iterative training. We apply our method to simulated and experimental data of gold nanoparticles on amorphous carbon and show that we can significantly speed up ptychographic reconstruction of the nanoparticles.

4DSTEM↗
DOE OSTI2024

Lifetimes of excited states in $^{16}$C as a benchmark for ab initio developments

Lifetimes of higher-lying states ($2_2^+$ and $4_1^+$) in 16 C have been measured, employing the Gammasphere and Microball detector arrays, as key observables to test and refine ab initio calculations based on interactions developed within chiral Effective Field Theory. The presented experimental constraints to these lifetimes of $\tau ({2_2^+}) = [244, 446]\,~\textrm{fs}$ and $\tau ({4_1^+}) = [1.8, 4]\,~\textrm{ps}$, combined with previous results on the lifetime of the $2_1^+$ state of 16 C, provide a rather complete set of key observables to benchmark the theoretical developments. We present No-Core Shell-Model calculations using state-of-the-art chiral 2- (NN) and 3-nucleon (3N) interactions at next-to-next-to-next-to-leading order for both the NN and the 3N contributions and a generalized natural-orbital basis (instead of the conventional harmonic-oscillator single-particle basis) which reproduce, for the first time, the experimental findings remarkably well. The level of agreement of the new calculations as compared to the CD-Bonn meson-exchange NN interaction is notable and presents a critical benchmark for theory.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Heavy-ion physics at the LHC

Heavy-ion collisions have been part of the programme of the LHC since its conception. The main nucleus–nucleus system is 208 82 + Pb + 208 82 + Pb . During the Runs 1 and 2, the LHC provided Pb+Pb collisions with centre-of-mass energy per nucleon pair √ s NN = 2.76 and 5.02 TeV, Xe+Xe with √ s NN = 5.44 TeV, and p+Pb with √ s NN = 5.02 and 8.16 TeV. The LHC performance with heavy-ion beams is described in Ref. 1. The ALICE detector was conceived to be dedicated to the study of heavy-ion collisions. The ATLAS and CMS experiments participated in the programme since the very beginning, and the LHCb experiment participated since the end of Run 1. Figure 1 shows event displays of Pb+Pb collisions from the four experiments.

Audurier, Benjamin↗
DOE OSTI2020

Systematic investigation of the particle spectra in heavy-ion collisions at the Large Hadron Collider

We investigate the charged particle spectra produced in the heavy-ion collisions at nine centralities from different systems, i.e. Pb+Pb at √ s NN = 2.76 TeV and 5.02 TeV as well as Xe+Xe at √ s NN = 5.44 TeV, at Large Hadron Collider (LHC) using one empirical formula inspired by the stationary solution of the Fokker-Planck equation, dubbed as the generalized Fokker-Planck solution (GFPS). Our results show that the GFPS can reproduce the experimental particle spectrum up to transverse momentum pT about 45 GeV/c with the maximum discrepancy 30% covering 10 orders of magnitude. Here, the discrepancy between the data and the results from the GFPS decreases to 15% when the maximum of the charged particle transverse momentum is cut to 20 GeV/c. We confirmed that the Tsallis distribution derived from the non-extensive statistics, which can reproduce the particle spectra produced in small collision systems, such as p+p, up to few hundreds GeV/c, can only apply to systematically study the particle spectra up to 8 GeV/c in A+A collisions at LHC, as pointed out in the study of identified particle spectra in Pb+Pb collisions at √ s NN = 2.76 TeV. A brief discussion on GFPS is also given.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Latent Space Simulation for Carbon Capture Design Optimization

The CO2 capture efficiency in solvent-based carbon capture systems (CCSs) critically depends on the gas-solvent interfacial area (IA), making maximization of IA a foundational challenge in CCS design. While the IA associated with a particular CCS design can be estimated via a computational fluid dynamics (CFD) simulation, using CFD to derive the IAs associated with numerous CCS designs is prohibitively costly. However, previous works such as Deep Fluids (Kim et al., 2019) show that large simulation speed-ups and low error are achievable by replacing CFD simulators with neural-network (NN) surrogates that mimic the CFD simulation process. This raises the possibility for a fast, accurate replacement for a CFD simulator, and thus computationally feasible IA-based CCS-design optimization. As such, here, we explore whether an existing NN-surrogate approach (and variants we develop) can successfully be applied to our complex carbon-capture CFD simulations, with the ultimate goal of obtaining a fast and accurate simulator for our CCS-design application. Our experiments build on the Deep Fluids approach and find that resulting surrogates can produce large speed ups (4000x) while maintaining IA relative errors as low as 4% on unseen CCS configurations (interpolating between configurations seen during training). Thus, despite less faithfulness to the underlying physics of the problem, NN surrogates may be a promising tool for our CCS design optimization problem. Notably, though, the Deep Fluids approach has limitations for our application (such as model non-transferability to CCS-packing changes), which we discuss. We conclude with potential directions for future work that may, like innovations we introduced here (e.g., transformer-based dynamics prediction), improve performance on our complicated dataset of CCS CFD simulations.

AI Surrogate Simulation, Carbon Capture, design op↗
DOE OSTI2024

Neutral rhenium(i) tricarbonyl complexes with sulfur-donor ligands: anti-proliferative activity and cellular localization

Rhenium(I) tricarbonyl complexes are widely studied for their cell imaging properties and anticancer and anti-microbial activities, but the complexes with S-donor ligands remain relatively unexplored. A series of six fac-[Re(NN)(CO) 3 (SR)] complexes, where (NN) is 2,2'-bipyridyl (bipy) or 1,10-phenanthroline (phen), and RSH is a series of thiocarboxylic acid methyl esters, have been synthesized and characterized. Cellular uptake and anti-proliferative activities of these complexes in human breast cancer cell lines (MDA-MB-231 and MCF-7) were generally lower than those of the previously described fac-[Re(NN)(CO) 3 (OH 2 )] + complexes; however, one of the complexes, fac-[Re(CO) 3 (phen)(SC(Ph)CH 2 C(O)OMe))] (3b), was active (IC 50 ~ 10 μM at 72 h treatment) in thiol-depleted MDA-MB-231 cells. Moreover, unlike fac- [Re(CO) 3 (phen)(OH 2 )] + , this complex did not lose activity in the presence of extracellular glutathione. Taken together these properties show promise for further development of 3b and its analogues as potential anti-cancer drugs for co-treatment with thiol-depleting agents. Conversely, the stable and non-toxic complex, fac-[Re(bipy)(CO) 3 (SC(Me)C(O)OMe)] (1a), predominantly localized in the lysosomes of MDA-MB-231 cells, as shown by live cell confocal microscopy (λ ex = 405 nm, λ em = 470-570 nm). It is strongly localized in a subset of lysosomes (25 μM Re, 4 h treatment), as shown by co-localization with a Lysotracker dye. Longer treatment times with 1a (25 μM Re for 48 h) resulted in partial migration of the probe into the mitochondria, as shown by co-localization with a Mitotracker dye. These properties make complex 1a an attractive target for further development as an organelle probe for multimodal imaging, including phosphorescence, carbonyl tag for vibrational spectroscopy, and Re tag for X-ray fluorescence microscopy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
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↗