Search NASA⌕ Search

SEARCH · Search NASA

Results for “Selective classification”

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 505 records · Page 28

Evaluation of data collection bias of third molar stages of mineralisation for age estimation in the living

Abstract Age assessment of the living is a fundamental procedure in the process of human identification, in order to guarantee fair treatment of individuals, which has ethical, civil, legal, and medical repercussions. The careful selection of the appropriate methods requires evaluation of several parameters: accuracy, precision of the method, as well as its reproducibility. The approach proposed by Mincer et al. adapted from Demirjian et al. exploring third molar mineralisation, is one of the most frequently considered for age estimation of the living. Thus, this work aims to assess potential bias in the data collection when applying the classification stages for dental mineralisation adapted by Mincer et al. A total of 102 orthopantomographs, of clinical origin, belonging to individuals aged between 12 and 25 years ($ \bar{\textit x} $ = 20.12 years, SD = 3.49 years; 65 females, 37 males, all of Portuguese nationality) were included and a retrospective analysis performed by five observers with different levels of experience (high, average, and basic). The performance and agreement between five observers were evaluated using Weighted Cohen’s Kappa and the Intraclass Correlation Coefficient. To access the influence of impaction on third molar classification, variables were tested using ordinal logistic regression Generalised Linear Model. It was observed that there were variations in the number of teeth identified among the observers, but the agreement levels ranged from moderate to substantial (0.4–0.8). Upon closer examination of the results, it was observed that although there were discernible differences between highly experienced observers and those with less experience, the gap was not as significant as initially hypothesised, and a greater disparity between the classifications of the upper (0.24–0.49) and lower third molars (>0.55) was observed. When bone superimposition is present, the classification process is not significantly influenced; however, variation in teeth angulation affects the assessment. The results suggest that with an efficient preparation, the level of experience as a factor can be overcome. Mincer and colleague's classification system can be replicated with ease and consistency, even though the classification of upper and lower third molars presents distinct challenges.

de Oliveira Santos, Inês (ORCID:0000000267324347)↗

Report for Development of a Census Array and Evaluation of the Array to Detect Biothreat Agents and Environmental Samples for DHS

The objective of this project is to provide DHS a comprehensive evaluation of the current genomic technologies including genotyping, Taqman PCR, multiple locus variable tandem repeat analysis (MLVA), microarray and high-throughput DNA sequencing in the analysis of biothreat agents from complex environmental samples. This report focuses on the design, testing and results of samples on the Census Array. We designed a Census/Detection Array to detect all sequenced viruses (including phage), bacteria (eubacteria), and plasmids. Family-specific probes were selected for all sequenced viral and bacterial complete genomes, segments, and plasmids. Probes were designed to tolerate some sequence variation to enable detection of divergent species with homology to sequenced organisms, and to be unique relative to the human genome. A combination of 'detection' probes with high levels of conservation within a family plus 'census' probes targeting strain/isolate specific regions enabled detection and taxonomic classification from the level of family down to the strain. The array has wider coverage of bacterial and viral targets based on more recent sequence data and more probes per target than other microbial detection/discovery arrays in the literature. We tested the array with purified bacterial and viral DNA/RNA samples, artificial mixes of known bacterial/viral samples, spiked DNA against complex background including BW aerosol samples and soil samples, and environmental samples to evaluate the array's sensitivity and forensic capability. The data were analyzed using our novel maximum likelihood software. For most of the organisms tested, we have achieved at least species level discrimination.

59 BASIC BIOLOGICAL SCIENCES↗

Toward Complete Merger Identification at Cosmic Noon with Deep Learning

As we enter the era of large imaging surveys such as Roman, Rubin, and Euclid, a deeper understanding of potential biases and selection effects in optical astronomical catalogs created with the use of ML-based methods is paramount. This work focuses on a deeper understanding of the performance and limitations of deep learning-based classifiers as tools for galaxy merger identification. We train a ConvNeXT-Pico model on mock HST CANDELS images from the IllustrisTNG50 simulation. Our focus is on a more challenging classification of galaxy mergers and non-mergers at higher redshifts 1 < z < 1.5, including minor mergers and lower mass galaxies down to the stellar mass of 108M⊙. We demonstrate, for the first time, that a deep learning model, such as the one developed in this work, can successfully identify even minor and low mass mergers even at these redshifts. Our model achieves overall accuracy, purity, and completeness of over 73%. We show that some galaxy mergers can only be identified from certain observation angles, leading to a potential upper limit in overall accuracy. Using Grad-CAMs and UMAPs, we more deeply examine the performance and observe a visible gradient in the latent space with stellar mass and specific star formation rate, but no visible gradient with merger mass ratio or merger stage.

Schechter, Aimee L. [U. Colorado, Boulder]↗

Compositing and Characterization of SE Quadrant Waste Exemplars

This report outlines the experimental investigation and characterization of transport properties in Hanford SE quadrant High-Level Waste (HLW). The goal of the study was to establish baseline behaviors of bulk composite rheology and settling characteristics to facilitate waste treatment process design for the Waste Treatment and Immobilization Plant (WTP) and avoid waste conditions and properties favorable to bubble cascade gas release events. The study focused on two major objectives: 1) identifying, obtaining, and preparing relevant Hanford tank waste samples for evaluation and 2) quantifying the “as-received” rheology and transport properties of the samples. Twenty-three centrifuged core segments originating from tanks AN-101, AN-106, and AW-105 were selected based on compositional relevance to SE quadrant PUREX cladding waste. These materials were composited into five waste composites enriched with target analytes: aluminum (Al), iron (Fe), phosphate (PO 4 ), uranium (U), and zirconium (Zr). Physical property and transport testing examined particle size distributions, bulk densities, settling behaviors, rheological properties, shear strengths, and just-suspended mixing speeds (NJS). Testing revealed two distinct composite classifications based on rheological characteristics: non-Newtonian composites (Fe and PO 4 ) and Newtonian composites (Al, U, and Zr). The Fe and PO 4 composites exhibited slow settling rates and reduced mobilization proclivity, attributable to strong particle-particle interactions and the formation of yield structures within non-Newtonian slurries. In contrast, the Al, U, and Zr composites displayed rapid settling and dense compaction behaviors, indicative of minimal structuring and interactions. Shear strengths for all composites were generally low relative to prior studies of SE quadrant waste, with only the U composite showing elevated strength approaching values reported in previous literature. Repeat shear strength measurements revealed contributions from dense granular material in the U composite and stronger cohesive properties in the Al composite. Settling data highlighted hindered settling behavior, with rates falling more than one order of magnitude below estimates based on Stokes’ law and rate decreasing as composite UDS content increased. NJS testing demonstrated different mobilization behaviors between cohesive and granular composites. The Fe composite required the highest mixing rate for resuspension, while the Al composite was the easiest to resuspend. Comparison of measured NJS against predictions made using the Zwietering correlation suggests non-Newtonian behavior alters resuspension mechanics, rendering non-Newtonian systems more stable against resuspension lift forces relative to their granular counterparts.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Toward Complete Merger Identification at Cosmic Noon with Deep Learning

As we enter the era of large imaging surveys such as $\textit{Roman}$, Rubin, and $\textit{Euclid}$, a deeper understanding of potential biases and selection effects in optical astronomical catalogs created with the use of ML-based methods is paramount. This work focuses on a deeper understanding of the performance and limitations of deep learning-based classifiers as tools for galaxy merger identification. We train a ResNet18 model on mock Hubble Space Telescope CANDELS images from the IllustrisTNG50 simulation. Our focus is on a more challenging classification of galaxy mergers and nonmergers at higher redshifts $1

Schechter, Aimee [Colorado U.] (ORCID:000000017120↗

Enhancing Critical Infrastructure and Key Resources (CIKR) Level-0 Physical Process Security Using Field Device Distinct Native Attribute Features

Here, the need for improved Critical Infrastructure and Key Resource (CIKR) security is unquestioned and there has been minimal emphasis on Level-0 (PHY Process) improvements. Wired Signal Distinct Native Attribute (WS-DNA) Fingerprinting is investigated here as a non-intrusive PHY-based security augmentation to support an envisioned layered security strategy. Results are based on experimental response collections from Highway Addressable Remote Transducer (HART) Differential Pressure Transmitter (DPT) devices from three manufacturers (Yokogawa, Honeywell, Endress+Hauer) installed in an automated process control system. Device discrimination is assessed using Time Domain (TD) and Slope-Based FSK (SB-FSK) fingerprints input to Multiple Discriminant Analysis, Maximum Likelihood (MDA/ML) and Random Forest (RndF) classifiers. For 12 different classes (two devices per manufacturer at two distinct set points), both classifiers performed reliably and achieved an arbitrary performance benchmark of average cross-class percent correct of %C > 90%. The least challenging cross-manufacturer results included near-perfect %C ≈ 100%, while the more challenging like-model (serial number) discrimination results included 90%< %C < 100%, with TD Fingerprinting marginally outperforming SB-FSK Fingerprinting; SB-FSK benefits from having less stringent response alignment and registration requirements. The RndF classifier was most beneficial and enabled reliable selection of dimensionally reduced fingerprint subsets that minimize data storage and computational requirements. The RndF selected feature sets contained 15% of the full-dimensional feature sets and only suffered a worst case %CΔ = 3% to 4% performance degradation.

60 APPLIED LIFE SCIENCES↗

Signature-Discovery Approach for Sample Matching of a Nerve-Agent Precursor using Liquid Chromatography–Mass Spectrometry, XCMS, and Chemometrics

This report demonstrates the use of bioinformatic and chemometric tools on liquid chromatography mass spectrometry (LC-MS) data for the discovery of ultra-trace forensic signatures for sample matching of various stocks of the nerve-agent precursor known as methylphosphonic dichloride (dichlor). The use of the bioinformatic tool known as XCMS was used to comprehensively search and find candidate LC-MS peaks in a known set of dichlor samples. These candidate peaks were down selected to a group of 34 impurity peaks. Hierarchal cluster analysis and factor analysis demonstrated the potential of these 34 impurities peaks for matching samples based on their stock source. Only one pair of dichlor stocks was not differentiated from one another. An acceptable chemometric approach for sample matching was determined to be variance scaling and signal averaging of normalized duplicate impurity profiles prior to classification by k-nearest neighbors. Using this approach, a test set of dichlor samples were all correctly matched to their source stock. The sample preparation and LC-MS method permitted the detection of dichlor impurities presumably in the parts-per-trillion (w/w). The detection of a common impurity in all dichlor stocks that were synthesized over a 14-year period and by different manufacturers was an unexpected discovery. Our described signature-discovery approach should be useful in the development of a forensic capability to help in criminal investigations following chemical attacks.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A Catalog of Candidate Double and Lensed Quasars from Gaia and WISE Data

Making use of strong correlations between closely separated multiple or double sources and photometric and astrometric metadata in Gaia Early Data Release 3 (EDR3), we generate a catalog of candidate double- and multiply imaged lensed quasars and active galactic nuclei (AGNs), comprising 3140 systems. It includes two partially overlapping parts: a sample of distant (redshifts mostly greater than 1) sources with perturbed data; and systems that have been resolved into separate components by Gaia at separations less than 2''. For the first part, which is roughly one-third of the published catalog, we synthesized 0.617 million redshifts using multiple machine-learning prediction and classification methods, using independent photometric and astrometric data from Gaia EDR3 and the Wide-field Infrared Survey Explorer, with accurate spectroscopic redshifts from the Sloan Digital Sky Survey (SDSS) as a training set. Using these synthetic redshifts, we estimate a 4.9% rate of interlopers with spectroscopic redshifts below 1 in this part of the catalog. Unresolved candidate double and dual AGNs and quasars are selected as sources with a marginally high BP/RP excess factor (phot_bp_rp_excess_factor), which is sensitive to source extent, limiting our search to high-redshift quasars. For the second part of the catalog, additional filters on measured parallax and near-neighbor statistics are applied to diminish the propagation of the remaining stellar contaminants. The estimated rate of the positives (double or multiple sources) is 98%, and the estimated rate of dual (physically related) quasars is greater than 54%. A few dozen serendipitously found objects of interest are discussed in more detail, including known and new lensed images, planetary nebulae, young IR stars of peculiar morphology, and quasars with catastrophic redshift errors in SDSS.

79 ASTRONOMY AND ASTROPHYSICS↗

Array-Based Machine Learning for Functional Group Detection in Electron Ionization Mass Spectrometry

Mass spectrometry is a ubiquitous technique capable of complex chemical analysis. The fragmentation patterns that appear in mass spectrometry are an excellent target for artificial intelligence methods to automate and expedite the analysis of data to identify targets such as functional groups. To develop this approach, we trained models on electron ionization (a reproducible hard fragmentation technique) mass spectra so that not only the final model accuracies but also the reasoning behind model assignments could be evaluated. The convolutional neural network (CNN) models were trained on 2D images of the spectra using transfer learning of Inception V3, and the logistic regression models were trained using array-based data and Scikit Learn implementation in Python. Our training dataset consisted of 21,166 mass spectra from the United States’ National Institute of Standards and Technology (NIST) Webbook. The data was used to train models to identify functional groups, both specific (e.g., amines, esters) and generalized classifications (aromatics, oxygen-containing functional groups, and nitrogen-containing functional groups). We found that the highest final accuracies on identifying new data were observed using logistic regression rather than transfer learning on CNN models. It was also determined that the mass range most beneficial for functional group analysis is 0–100 m/z. We also found success in correctly identifying functional groups of example molecules selected from both the NIST database and experimental data. Beyond functional group analysis, we also have developed a methodology to identify impactful fragments for the accurate detection of the models’ targets. The results demonstrate a potential pathway for analyzing and screening substantial amounts of mass spectral data.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The population of hot subdwarf stars studied with Gaia: IV. Catalogues of hot subluminous stars based on Gaia EDR3

In light of substantial new discoveries of hot subdwarfs by ongoing spectroscopic surveys and the availability of the Gaia mission Early Data Release 3 (EDR3), we compiled new releases of two catalogues of hot subluminous stars: The data release 3 (DR3) catalogue of the known hot subdwarf stars contains 6616 unique sources and provides multi-band photometry, and astrometry from Gaia EDR3 as well as classifications based on spectroscopy and colours. This is an increase of 742 objects over the DR2 catalogue. This new catalogue provides atmospheric parameters for 3087 stars and radial velocities for 2791 stars from the literature. In addition, we have updated the Gaia Data Release 2 (DR2) catalogue of hot subluminous stars using the improved accuracy of the Gaia EDR3 data set together with updated quality and selection criteria to produce the Gaia EDR3 catalogue of 61 585 hot subluminous stars, representing an increase of 21 785 objects. Furthermore, the improvements in Gaia EDR3 astrometry and photometry compared to Gaia DR2 have enabled us to define more sophisticated selection functions. In particular, we improved hot subluminous star detection in the crowded regions of the Galactic plane as well as in the direction of the Magellanic Clouds by including sources with close apparent neighbours but with flux levels that dominate the neighbourhood.

79 ASTRONOMY AND ASTROPHYSICS↗

Design by analysis rules for ASME Section III, Division 5, Class B components

The current rules for elevated temperature ASME Section III, Division 5, Class B components, other than piping, were basically adapted from the Design-by-Rule approach for Section VIII, Division 1 vessels. A goal of the proposed new rules is to explicitly account for the design life and cyclic service while recognizing the less-rigorous requirements commensurate with lesser safety consideration. Further goals are to maximize the use of modern computational technology, for example finite element analysis in conjunction with reference stress concepts, and to avoid the need for stress classification. This paper summarizes the work done to address these issues. A summary of the design-by-analysis for primary loads, strain limit evaluation, and creep-fatigue damage assessment is presented. The proposed design-by-analysis creep-fatigue damage calculation approach uses a new elastic follow-up-based Isochronous Stress Strain Curve stress relaxation procedure. A set of sample problems are selected to validate the proposed design-by-analysis rules for creep-fatigue damage assessment. The proposed Class B rules are evaluated against the Class A elastic design rules and the experimental data obtained from a family of a simplified model test-based key-feature test results. The proposed Class B creep-fatigue damage assessment methodology yields conservative design cycles estimates compared to the experimental results.

36 MATERIALS SCIENCE↗

Weather patterns and hydro-climatological precursors of extreme floods in Switzerland since 1868

The generation of 24 extreme floods in large catchments of the central Alps is analyzed from instrumental and documentary data, newly digitized observations of precipitation (DigiHom) and 20th Century Reanalysis (20CR) data. Extreme floods are determined by the 95th percentile of differences between an annual flood and a defined contemporary flood. For a selection of six events between 1868 and 1910, we describe preconditioning elements such as precipitation, temperature, and snow cover anomalies. Specific weather patterns are assessed through a subjective analysis of three-dimensional atmospheric circulation. A focus is placed on synoptic-scale features including mid-tropospheric ascent, low-level moisture transport, propagation of cyclones, and temperature anomalies. We propose a hydro-meteorological classification of all 24 investigated events according to flood-generating weather conditions. Key elements of the upper-level synoptic-scale flow are summarized by five types: (i) pivoting cut-off lows, (ii) elongated cut-off lows, (iii) elongated troughs, (iv) waves (with a kink), and (v) approximately zonal flow over the Alpine region. We found that the most extreme floods (as above, but ≥ 98th percentile) in Switzerland since 1868 were caused by the interaction of severe hydro-climatologic conditions with a flood-inducing weather situation. The 20CR data provide plausible synoptic-scale meteorological patterns leading to heavy precipitation. The proposed catalogue of weather patterns and hydro-climatologic precursors can give direction when anticipating the possibility of severe floods in the Alpine region.

Meteorology & Atmospheric Sciences↗

Smart sensor for online situational awareness in power grids

Waveforms in power grids typically reveal a certain pattern with specific features and peculiarities driven by the system operating conditions, internal and external uncertainties, etc. This prompts an observation of different types of waveforms at the measurement points (substations). An innovative next-generation smart sensor technology includes a measurement unit embedded with sophisticated analytics for power grid online surveillance and situational awareness. The smart sensor brings additional levels of smartness into the existing phasor measurement units (PMUs) and intelligent electronic devices (IEDs). It unlocks the full potential of advanced signal processing and machine learning for online power grid monitoring in a distributed paradigm. Within the smart sensor are several interconnected units for signal acquisition, feature extraction, machine learning-based event detection, and a suite of multiple measurement algorithms where the best-fit algorithm is selected in real-time based on the detected operating condition. Embedding such analytics within the sensors and closer to where the data is generated, the distributed intelligence mechanism mitigates the potential risks to communication failures and latencies, as well as malicious cyber threats, which would otherwise compromise the trustworthiness of the end-use applications in distant control centers. The smart sensor achieves a promising classification accuracy on multiple classes of prevailing conditions in the power grid and accordingly improves the measurement quality across the power grid.

Dehghanian, Payman↗

Measuring photometric redshifts for high-redshift radio source surveys

With the advent of deep, all-sky radio surveys, the need for ancillary data to make the most of the new, high-quality radio data from surveys like the Evolutionary Map of the Universe (EMU), GaLactic and Extragalactic All-sky Murchison Widefield Array survey eXtended, Very Large Array Sky Survey, and LOFAR Two-metre Sky Survey is growing rapidly. Radio surveys produce significant numbers of Active Galactic Nuclei (AGNs) and have a significantly higher average redshift when compared with optical and infrared all-sky surveys. Thus, traditional methods of estimating redshift are challenged, with spectroscopic surveys not reaching the redshift depth of radio surveys, and AGNs making it difficult for template fitting methods to accurately model the source. Machine Learning (ML) methods have been used, but efforts have typically been directed towards optically selected samples, or samples at significantly lower redshift than expected from upcoming radio surveys. This work compiles and homogenises a radio-selected dataset from both the northern hemisphere (making use of Sloan Digital Sky Survey optical photometry) and southern hemisphere (making use of Dark Energy Survey optical photometry). We then test commonly used ML algorithms such as k-Nearest Neighbours (kNN), Random Forest, ANNz, and GPz on this monolithic radio-selected sample. We show that kNN has the lowest percentage of catastrophic outliers, providing the best match for the majority of science cases in the EMU survey. We note that the wider redshift range of the combined dataset used allows for estimation of sources up to z = 3 before random scatter begins to dominate. When binning the data into redshift bins and treating the problem as a classification problem, we are able to correctly identify ≈ 76% of the highest redshift sources—sources at redshift z > 2.51 —as being in either the highest bin (z > 2.51) or second highest (z = 2.25).

79 ASTRONOMY AND ASTROPHYSICS↗

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↗

Identification of Metal Stresses in Arabidopsis thaliana Using Hyperspectral Reflectance Imaging

Industrial accidents, such as the Fukushima and Chernobyl disasters, release harmful chemicals into the environment, covering large geographical areas. Natural flora may serve as biological sensors for detecting metal contamination, such as cesium. Spectral detection of plant stresses typically employs a few select wavelengths and often cannot distinguish between different stress phenotypes. In this study, we apply hyperspectral reflectance imaging in the visible and near-infrared along with multivariate curve resolution (MCR) analysis to identify unique spectral signatures of three stresses in Arabidopsis thaliana : salt, copper, and cesium. While all stress conditions result in common stress physiology, hyperspectral reflectance imaging and MCR analysis produced unique spectral signatures that enabled classification of each stress. As the level of potassium was previously shown to affect cesium stress in plants, the response of A. thaliana to cesium stress under variable levels of potassium was also investigated. Increased levels of potassium reduced the spectral response of A. thaliana to cesium and prevented changes to chloroplast cellular organization. While metal stress mechanisms may vary under different environmental conditions, this study demonstrates that hyperspectral reflectance imaging with MCR analysis can distinguish metal stress phenotypes, providing the potential to detect metal contamination across large geographical areas.

multivariate curve resolution↗

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 $\mu$m$^2$ 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$30e$^-$ and a total dispersion of $\sim$100e$^-$ 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$^2$ staying within the experimental constraints.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Explainable machine learning for incipient anomaly detection in compact molten salt heat exchanger with overlapping feature distributions

High-temperature molten salt-cooled reactors (MSCRs) are a promising next-generation nuclear technology option, offering efficient power conversion and inherent safety features. However, the reliability of these systems depends on the robust operation of heat exchangers (HXs), which are susceptible to failure due to temperature gradients and channel plugging caused by fluid freezing. Conventional monitoring methods, relying on inlet and outlet measurements, lack the spatial resolution needed to detect early-stage faults. We propose a novel design of a compact salt-to-salt matrix-type HX design consisting of interleaved arrays of parallel tubes, with integrated synthetic fiber optic distributed temperature sensing (DTS) to enable localized detection of incipient faults. To evaluate performance of this design, we generate high-fidelity synthetic data using heat transfer computational modeling to simulate channel plugging, and introduce sensor noise for realistic modeling of measurements. The dataset comprises of 97% normal operation and 3% anomaly cases, with each anomaly class representing 1% of the data. These early anomalies result in overlapping temperature profiles between normal and faulty channels, producing a non-separable dataset that challenges traditional classification techniques. We benchmark eight supervised machine learning (ML) models and demonstrate that XGBoost achieves the highest performance. To improve transparency, we develop an explainability framework combining Shapley values and partially ordered sets (POSETs) to quantify and structurally analyze feature importance. This approach identifies both dominant predictors and ambiguous feature relationships, enhancing trust and interpretability. Our results highlight the potential of combining DTS and explainable ML with intelligent feature selection to improve predictive maintenance and ensure operational resilience in advanced nuclear systems.

Prantikos, Konstantinos [Argonne National Laborato↗