Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “explainable neural networks”

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 181 records · Page 10
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Aeroacoustic Characterization of Optimum Hovering Rotors using Artificial Neural Networks

This work illustrates the use of artificial neural network modeling in the aerodynamic and aeroacoustic characterization of optimum hovering rotors over a broad range of design and operating conditions. Design of Experiments was used to create input feature spaces over eight input factors: the number of rotor blades, rotor radius, rotor rotation rate, design thrust condition, collective pitch, airfoil camber, the location of maximum camber, and the airfoil thickness. A low-fidelity tool chain was then used at the discrete data points defined by the designed input feature spaces to analytically design optimum hovering rotors and simulate aerodynamic and aeroacoustic quantities. This allowed for the generation of data sets over which to train and test the artificial neural network prediction models. Prediction models were trained over the data sets for the actual thrust generated by the rotor, power loading, tonal thickness and loading noise at the fundamental blade passage frequency, and broadband self-noise at seventeen one-third octave bands between 1 kHz and 40 kHz. These prediction models were validated by testing over data previously unseen by the models to quantify their capability for generalization to new data within the design feature space. The models were then used to study the effect each input feature had on the aeroacoustics and aerodynamics of optimum hovering rotors and physical insights were concluded to further explain the effect of each input. This characterization study showed that tonal noise and power loading were most sensitive to the number of rotor blades and the rotor rotation rate and that broadband noise was most sensitive to collective pitch and the design thrust condition.

Christopher S Thurman↗
DOE OSTI2021

Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks

Tomographic background oriented Schlieren (Tomo-BOS) imaging measures density or temperature fields in three dimensions using multiple camera BOS projections, and is particularly useful for instantaneous flow visualizations of complex fluid dynamics problems. We propose a new method based on physics-informed neural networks (PINNs) to infer the full continuous three-dimensional (3-D) velocity and pressure fields from snapshots of 3-D temperature fields obtained by Tomo-BOS imaging. The PINNs seamlessly integrate the underlying physics of the observed fluid flow and the visualization data, hence enabling the inference of latent quantities using limited experimental data. In this hidden fluid mechanics paradigm, we train the neural network by minimizing a loss function composed of a data mismatch term and residual terms associated with the coupled Navier–Stokes and heat transfer equations. We first quantify the accuracy of the proposed method based on a two-dimensional synthetic data set for buoyancy-driven flow, and subsequently apply it to the Tomo-BOS data set, where we are able to infer the instantaneous velocity and pressure fields of the flow over an espresso cup based only on the temperature field provided by the Tomo-BOS imaging. Moreover, we conduct an independent PIV experiment to validate the PINN inference for the unsteady velocity field at a centre plane. To explain the observed flow physics, we also perform systematic PINN simulations at different Reynolds and Richardson numbers and quantify the variations in velocity and pressure fields. Furthermore, the results in this paper indicate that the proposed deep learning technique can become a promising direction in experimental fluid mechanics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Predicting wind-driven spatial deposition through simulated color images using deep autoencoders

Abstract For centuries, scientists have observed nature to understand the laws that govern the physical world. The traditional process of turning observations into physical understanding is slow. Imperfect models are constructed and tested to explain relationships in data. Powerful new algorithms can enable computers to learn physics by observing images and videos. Inspired by this idea, instead of training machine learning models using physical quantities, we used images, that is, pixel information. For this work, and as a proof of concept, the physics of interest are wind-driven spatial patterns. These phenomena include features in Aeolian dunes and volcanic ash deposition, wildfire smoke, and air pollution plumes. We use computer model simulations of spatial deposition patterns to approximate images from a hypothetical imaging device whose outputs are red, green, and blue (RGB) color images with channel values ranging from 0 to 255. In this paper, we explore deep convolutional neural network-based autoencoders to exploit relationships in wind-driven spatial patterns, which commonly occur in geosciences, and reduce their dimensionality. Reducing the data dimension size with an encoder enables training deep, fully connected neural network models linking geographic and meteorological scalar input quantities to the encoded space. Once this is achieved, full spatial patterns are reconstructed using the decoder. We demonstrate this approach on images of spatial deposition from a pollution source, where the encoder compresses the dimensionality to 0.02% of the original size, and the full predictive model performance on test data achieves a normalized root mean squared error of 8%, a figure of merit in space of 94% and a precision-recall area under the curve of 0.93.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1999

Comparisons of Upper Tropospheric Humidity Retrievals from TOVS and METEOSAT

Two different methods for retrieving Upper Tropospheric Humidities (UTH) from the TOVS (TIROS Operational Vertical Sounder) instruments aboard NOAA polar orbiting satellites are presented and compared. The first one, from the Environmental Technology Laboratory, computed by J. Bates and D. Jackson (hereafter BJ method), estimates UTH from a simplified radiative transfer analysis of the upper tropospheric infrared water vapor channel at wavelength measured by HIRS (6.3 micrometer). The second one results from a neural network analysis of the TOVS (HIRS and MSU) data developed at, the Laboratoire de Meteorologie Dynamique (hereafter the 3I (Improved Initialization Inversion) method). Although the two methods give very similar retrievals in temperate regions (30-60 N and S), an absolute bias up to 16% appears in the convective zone of the tropics. The two datasets have also been compared with UTH retrievals from infrared radiance measurements in the 6.3 micrometer channel from the geostationary satellite METEOSAT (hereafter MET method). The METEOSAT retrievals are systematically drier than the TOVS-based results by an absolute bias between 5 and 25%. Despite the biases, the spatial and temporal correlations are very good. The purpose of this study is to explain the deviations observed between the three datasets. The sensitivity of UTH to air temperature and humidity profiles is analysed as are the clouds effects. Overall, the comparison of the three retrievals gives an assessment of the current uncertainties in water vapor amounts in the upper troposphere as determined from NOAA and METEOSAT satellites.

Escoffier, C.↗
DOE OSTI2021

Investigations of water/oxide interfaces by molecular dynamics simulations

Water/oxide interfaces are ubiquitous on earth and show significant influence on many chemical processes. For example, understanding water and solute adsorption as well as catalytic water splitting can help build better fuel cells and solar cells to overcome our looming energy crisis; the interaction between biomolecules and water/oxide interfaces is one hypothesis to explain the origin of life. However, knowledge in this area is still limited due to the difficulty of studying water/solid interfaces. As a result, research using increasingly sophisticated experimental techniques and computational simulations has been carried out in recent years. Although it is difficult for experimental techniques to provide detailed microscopic structural information, molecular dynamics (MD) simulations have satisfactory performance. In this report, we discuss classical and ab initio MD simulations of water/oxide interfaces. Generally, we are interested in the following questions: How do solid surfaces perturb interfacial water structure? How do interfacial water molecules and adsorbed solutes affect solid surfaces and how do interfacial environments affect solvent and solute behavior? Finally, we discuss progress in the application of neural network potential based MD simulations, which offer a promising future because this approach has already enabled ab initio level accuracy for very large systems and long trajectories.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRSDate not supplied

Statistical learning framework for safety and failure analysis of a DNN-based autonomous aircraft system

Deep Neural Networks (DNNs) and Machine Learning technology is increasingly used for safety-critical applications in the Aerospace domain. To ensure safe operations, the DNN and the system must undergo rigorous verification and validation, including advanced statistical analyses. Performance and safety of the DNN and system behavior must not only be analyzed for the nominal case, but under numerous off-nominal and failure cases. In this paper we will describe how our statistical learning framework SYSAI can efficiently perform such analyses using the tool’s unique combination of advanced learning modeling and statistical analysis techniques. SYSAI can effectively explore the high-dimensional state and failure space of the system under test; geometrical shape detection of safety regions and boundaries support explainability of the results to the designer. In this paper, we report experiments and results obtained with a vision-based DNN control system (ACT) that is capable of autonomously steering an aircraft down a runway.

Yuning He↗
DOE OSTI2024

Development of a Full-Scale Connected U-Net for Reflectivity Inpainting in Spaceborne Radar Blind Zones

CloudSat’s Cloud Profiling Radar is a valuable tool for remotely monitoring high-latitude snowfall, but its ability to observe hydrometeor activity near the Earth’s surface is limited by a radar blind zone caused by ground clutter contamination. This study presents the development of a deeply supervised U-Net-style convolutional neural network to predict cold season reflectivity profiles within the blind zone at two Arctic locations. The network learns to predict the presence and intensity of near-surface hydrometeors by coupling latent features encoded in blind zone-aloft clouds with additional context from collocated atmospheric state variables (i.e., temperature, specific humidity, and wind speed). Results show that the U-Net predictions outperform traditional linear extrapolation methods, with low mean absolute error, a 38% higher Sørensen–Dice coefficient, and vertical reflectivity distributions 60% closer to observed values. The U-Net is also able to detect the presence of near-surface cloud with a critical success index (CSI) of 72% and cases of shallow cumuliform snowfall and virga with 18% higher CSI values compared to linear methods. An explainability analysis shows that reflectivity information throughout the scene, especially at cloud edges and at the 1.2-km blind zone threshold, along with atmospheric state variables near the tropopause, are the most significant contributors to model skill. This surface-trained generative inpainting technique has the potential to enhance current and future remote sensing precipitation missions by providing a better understanding of the nonlinear relationship between blind zone reflectivity values and the surrounding atmospheric state.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Learning Global Proliferation Expertise Evolution Using AI-Driven Analytics and Public Information

Detecting and anticipating global proliferation expertise and capability evolution from unstructured, noisy, and incomplete public data streams is a highly desired, but extremely challenging task. Here, in this article, we present our pioneering data-driven approach to support the non-proliferation mission to detect and explain the evolution of proliferation expertise and capability development globally from terabytes of publicly available information (PAI), focusing on our knowledge extraction pipeline and descriptive analytics. We first discuss how we fuse nine open-source data streams, including multilingual data, to convert 4 TB of unstructured data to structured knowledge and encode dynamically evolving proliferation expertise representations—content and context graphs. For this, we rely on natural language processing (NLP) and deep learning (DL) models to perform information extraction, topic modeling, and distributed text representation (aka embedding) learning. We then present interactive, usable, and explainable descriptive analytics to refine domain knowledge and present it in a human-understandable form. Finally, we introduce future work avenues that will leverage our dynamic knowledge representations and descriptive analytics to enable predictive and prescriptive inferences to achieve real-time domain understanding and contextual reasoning about global proliferation expertise and capability evolution.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2023

Data-driven predictions of the time remaining until critical global warming thresholds are reached

Leveraging artificial neural networks (ANNs) trained on climate model output, we use the spatial pattern of historical temperature observations to predict the time until critical global warming thresholds are reached. Although no observations are used during the training, validation, or testing, the ANNs accurately predict the timing of historical global warming from maps of historical annual temperature. The central estimate for the 1.5 °C global warming threshold is between 2033 and 2035, including a ±1σ range of 2028 to 2039 in the Intermediate (SSP2-4.5) climate forcing scenario, consistent with previous assessments. However, our data-driven approach also suggests a substantial probability of exceeding the 2 °C threshold even in the Low (SSP1-2.6) climate forcing scenario. While there are limitations to our approach, our results suggest a higher likelihood of reaching 2 °C in the Low scenario than indicated in some previous assessments—though the possibility that 2 °C could be avoided is not ruled out. Explainable AI methods reveal that the ANNs focus on particular geographic regions to predict the time until the global threshold is reached. Our framework provides a unique, data-driven approach for quantifying the signal of climate change in historical observations and for constraining the uncertainty in climate model projections. Given the substantial existing evidence of accelerating risks to natural and human systems at 1.5 °C and 2 °C, our results provide further evidence for high-impact climate change over the next three decades.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Understanding the Physics Representation of Deep Learning Models in Environmental Applications

Deep learning (DL) models have been popular in earth and environmental modeling and analysis, which exhibit huge potential in capturing and reconstructing the non-linearity of relevant environmental processes. They are extensively used as analytical tools or emulators for multiple domains (atmosphere, land surface, ocean, and biogeochemistry). Despite their success, their internal working mechanism remains largely unknown. Such a lack of knowledge hinders the identification of physically consistent models that are fully adaptive to non-stationary climate, as well as the development of physics-informed machine learning such as physics-informed neural network (PINN). To establish preliminary knowledge and framework of such physics representation evaluation, this project focuses on an improved understanding of DL models in the environmental applications. DL models are increasingly applied to environmental modeling and prediction. However, they have been evaluated mostly from a performance perspective, and there is a gap in understanding how they represent the known physics internally. Such knowledge is especially critical when applying DL models under climate change conditions, where new inputs are likely outside the ranges of the training datasets. In this project, we reveal how the known physical processes are represented within DL models from both statistical and mechanistic perspectives. Leveraging the traditional model evaluations that focus more on the accuracies of predictions, we establish a framework that examines both the accuracy and physics representation of DL models. This analysis framework can identify DL models that make the correct predictions based on correct physics, thus enhancing the existing explainable artificial intelligence (explainable-AI) portfolio. It lays a foundation for developing novel metrics to evaluate the emerging DL models in environmental applications. This knowledge also informs the development of physics-informed DL models by revealing the direct connections between the known physical processes and specific model components or structures.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Quantifying subsurface parameter and transport uncertainty using surrogate modelling and environmental tracers

Here, we combine physics-based groundwater reactive transport modelling with machine-learning techniques to quantify hydrogeological model and solute transport predictive uncertainties. We train an artificial neural network (ANN) on a dataset of groundwater hydraulic heads and 3 H concentrations generated using a high-fidelity groundwater reactive transport model. Using the trained ANN as a surrogate model to reproduce the input–output response of the high-fidelity reactive transport model, we quantify the posterior distributions of hydrogeological parameters and hydraulic forcing conditions using Markov chain Monte Carlo calibration against field observations of groundwater hydraulic heads and 3 H concentrations. We demonstrate the methodology with a model application that predicts Chlorofluorocarbon-12 (CFC-12) solute transport at a contaminated field site in Wyoming, United States. Our results show that including 3 H observations in the calibration dataset reduced the uncertainty in the estimated permeability field and infiltration rates, compared to calibration against hydraulic heads alone. However, predictive uncertainty quantification shows that CFC-12 transport predictions conditioned to the parameter posterior distributions cannot reproduce the field measurements. We found that calibrating the model to hydraulic head and 3 H observations results in groundwater mean ages that are too large to explain the observed CFC-12 concentrations. The coupling of the physics-based reactive transport model with the machine-learning surrogate model allows us to efficiently quantify model parameter and predictive uncertainties, which is typically computationally intractable using reactive transport models alone.

58 GEOSCIENCES↗
DOE OSTI2024

Characterizing climate pathways using feature importance on echo state networks

The 2022 National Defense Strategy of the United States listed climate change as a serious threat to national security. Climate intervention methods, such as stratospheric aerosol injection, have been proposed as mitigation strategies, but the downstream effects of such actions on a complex climate system are not well understood. The development of algorithmic techniques for quantifying relationships between source and impact variables related to a climate event (i.e., a climate pathway) would help inform policy decisions. Data-driven deep learning models have become powerful tools for modeling highly nonlinear relationships and may provide a route to characterize climate variable relationships. In this paper, we explore the use of an echo state network (ESN) for characterizing climate pathways. ESNs are a computationally efficient neural network variation designed for temporal data, and recent work proposes ESNs as a useful tool for forecasting spatiotemporal climate data. However, ESNs are noninterpretable black-box models along with other neural networks. The lack of model transparency poses a hurdle for understanding variable relationships. We address this issue by developing feature importance methods for ESNs in the context of spatiotemporal data to quantify variable relationships captured by the model. We conduct a simulation study to assess and compare the feature importance techniques, and we demonstrate the approach on reanalysis climate data. In the climate application, we consider a time period that includes the 1991 volcanic eruption of Mount Pinatubo. This event was a significant stratospheric aerosol injection, which acts as a proxy for an anthropogenic stratospheric aerosol injection. Furthermore, we are able to use the proposed approach to characterize relationships between pathway variables associated with this event that agree with relationships previously identified by climate scientists.

black-box models↗
DOE OSTI2022

Fraction of broad absorption line quasars in different radio morphologies

ABSTRACT In this study, we investigated the orientation model of Broad Absorption Line (BAL) quasars using a sample of sources that are common in Sloan Digital Sky Survey (SDSS) Data Release (DR)-16 quasar catalogue and Very Large Array (VLA)-Faint Images of the Radio Sky at Twenty Centimeters (FIRST) survey. Using the radio cut-out images from the FIRST survey, we first designed a deep-learning model using convolutional neural networks (CNN) to classify the quasar radio morphologies into the core-only, young jet, single lobe, or triples. These radio morphologies are further sub-classified into core-dominated and lobe-dominated sources. The CNN models can classify the sources with a high precision of >98 ${{\ \rm per\ cent}}$ for all the morphological sub-classes. The average BAL fraction in the resolved core, core-dominated, and lobe-dominated quasars are consistent with the BAL fraction inferred from radio and infrared surveys. We also present the distribution of BAL quasars as a function of quasar orientation by using the radio core-dominance as an orientation indicator. A similar analysis is performed for HiBALs, LoBALs, and FeLoBALs. All the radio morphological sub-classes and BAL sub-classes show an increase in BAL fraction at high orientation angles of the jets with respect to the line of sight. Our analysis suggests that BAL quasars are more likely to be found in viewing angles close to the equatorial plane of the quasar. However, a pure orientation model is inadequate, and a combination of orientation and evolution is probably the best way to explain the complete BAL phenomena.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1997

Emulating the Visual Receptive Field Properties of MST Neurons with a Template Model of Heading Estimation

We have previously proposed a computational neural-network model by which the complex patterns of retinal image motion generated during locomotion (optic flow) can be processed by specialized detectors acting as templates for specific instances of self-motion. The detectors in this template model respond to global optic flow by sampling image motion over a large portion of the visual field through networks of local motion sensors with properties similar to neurons found in the middle temporal (MT) area of primate extrastriate visual cortex. The model detectors were designed to extract self-translation (heading), self-rotation, as well as the scene layout (relative distances) ahead of a moving observer, and are arranged in cortical-like heading maps to perform this function. Heading estimation from optic flow has been postulated by some to be implemented within the medial superior temporal (MST) area. Others have questioned whether MST neurons can fulfill this role because some of their receptive-field properties appear inconsistent with a role in heading estimation. To resolve this issue, we systematically compared MST single-unit responses with the outputs of model detectors under matched stimulus conditions. We found that the basic physiological properties of MST neurons can be explained by the template model. We conclude that MST neurons are well suited to support heading estimation and that the template model provides an explicit set of testable hypotheses which can guide future exploration of MST and adjacent areas within the primate superior temporal sulcus.

Perrone, John A.↗
DOE OSTI2022

Decoding the protein–ligand interactions using parallel graph neural networks

Abstract Protein–ligand interactions (PLIs) are essential for biochemical functionality and their identification is crucial for estimating biophysical properties for rational therapeutic design. Currently, experimental characterization of these properties is the most accurate method, however, this is very time-consuming and labor-intensive. A number of computational methods have been developed in this context but most of the existing PLI prediction heavily depends on 2D protein sequence data. Here, we present a novel parallel graph neural network (GNN) to integrate knowledge representation and reasoning for PLI prediction to perform deep learning guided by expert knowledge and informed by 3D structural data. We develop two distinct GNN architectures: $$\hbox {GNN}_{\mathrm{F}}$$ GNN F is the base implementation that employs distinct featurization to enhance domain-awareness, while $$\hbox {GNN}_{\mathrm{P}}$$ GNN P is a novel implementation that can predict with no prior knowledge of the intermolecular interactions. The comprehensive evaluation demonstrated that GNN can successfully capture the binary interactions between ligand and protein’s 3D structure with 0.979 test accuracy for $$\hbox {GNN}_{\mathrm{F}}$$ GNN F and 0.958 for $$\hbox {GNN}_{\mathrm{P}}$$ GNN P for predicting activity of a protein–ligand complex. These models are further adapted for regression tasks to predict experimental binding affinities and $$\hbox {pIC}_{\mathrm{50}}$$ pIC 50 crucial for compound’s potency and efficacy. We achieve a Pearson correlation coefficient of 0.66 and 0.65 on experimental affinity and 0.50 and 0.51 on $$\hbox {pIC}_{\mathrm{50}}$$ pIC 50 with $$\hbox {GNN}_{\mathrm{F}}$$ GNN F and $$\hbox {GNN}_{\mathrm{P}}$$ GNN P , respectively, outperforming similar 2D sequence based models. Our method can serve as an interpretable and explainable artificial intelligence (AI) tool for predicted activity, potency, and biophysical properties of lead candidates. To this end, we show the utility of $$\hbox {GNN}_{\mathrm{P}}$$ GNN P on SARS-Cov-2 protein targets by screening a large compound library and comparing the prediction with the experimentally measured data.

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRSDate not supplied

The INSTEP Monitoring Network: Merging High-and-Low Cost Measurements to Characterize California Wildfires

Despite challenges with data quality and scope, low-cost sensor networks have skyrocketed in popularity over the last 15 years, making air quality data available on refined spatial scales. More recently, studies have leveraged both high and low-quality instruments to create stronger “hybrid” models, with most studies focusing on particulate matter. Low-cost measurements typically represent ground-level emissions only, providing context for human health issues from climate change-driven events such as wildfires. Since low-cost sensors’ capabilities are localized, daily events and microclimates tend to dominate the data rather than larger regional or atmospheric trends. Likewise, their low cost explains their high uncertainty. In contrast, some regulatory-grade instruments produce column measurements as well, providing reliable information on a broader scope. To bridge this gap while expanding into gas-phase measurements, we deployed 12 air quality sensor packages in California, USA during the 2022 wildfire season. These INSTEP (Inexpensive Network Sensor Technology Exploring Pollution) monitors measure carbon monoxide (CO), carbon dioxide (CO2), ozone (O3), nitrogen dioxide (NO2), and several hydrocarbons including methane (CH4) and formaldehyde (HCHO). Half of the monitors were co-located with remote sensing spectrometers: NASA Pandora and Total Column Carbon Observing Network (TCCON). The overlap in pollutants includes NO2, O3, and HCHO between the INSTEP monitors and the Pandora column measurements. TCCON covers column CO, CO2, and CH4, rounding out our comparison. Most of the monitors were distributed throughout the San Francisco Bay area, and an additional three were located within 100 km of Los Angeles. The sites ranged in geographic and population characteristics, including desert, mountainous, coastal, and urban locations. Since varying environmental conditions such as temperature and pressure are known to challenge sensor performance, we will apply newer sensor “calibration” techniques meant to combat this. We will normalize our sensor signals by z-scoring them prior to applying a single calibration model in the form of multivariate linear regression or an artificial neural network. While this technique has been validated for the hydrocarbon and ozone sensor types (metal oxide), it has not yet been tested on electrochemical and non-dispersive infrared sensors, which are also used in the INSTEP monitors. This will serve as a test to see if this normalization technique – or another – is most effective in accounting for environmental differences among sensors. Related data analysis efforts have found success with a variety of geospatial analysis techniques, including weighted network models in which high-quality instruments are given higher weights than their low-cost counterparts. Our preliminary analysis will focus on kriging, which uses a Gaussian algorithm to assign weights, providing estimated pollution levels at locations between monitors. Smoke trajectory and evolution will also be considered using both measurement types. We also aim to baseline subtract our emission estimates from each region to determine which portion of emissions are regional and local, further characterizing burn differences in northern and southern California fires. Future directions include using INSTEP jointly with TEMPO satellite data, and mobile deployments on aircraft and uncrewed aerial vehicles (UAV).

Low-cost sensors↗
DOE OSTI2022

How Many Elements Matter?

Some studies of stars' multielement abundance distributions suggest at least 5–7 significant dimensions, but others show that many elemental abundances can be predicted to high accuracy from [Fe/H] and [Mg/Fe] (or [Fe/H] and age) alone. We show that both propositions can be, and are, simultaneously true. We adopt a machine-learning technique known as normalizing flow to reconstruct the probability distribution of Milky Way disk stars in the space of 15 elemental abundances measured by APOGEE. Conditioning on T eff and $\mathrm{log}\,g$ minimizes the differential systematics. After further conditioning on [Fe/H] and [Mg/Fe], the residual scatter for most abundances is σ [X/H] ≲ 0.02 dex, consistent with APOGEE's reported statistical uncertainties of ~0.01–0.015 dex and intrinsic scatter of 0.01–0.02 dex. Despite the small scatter, residual abundances display clear correlations between elements, which we show are too large to be explained by measurement uncertainties or by the finite sampling noise. We must condition on at least seven elements to reduce the correlations to a level consistent with the observational uncertainties. Our results demonstrate that cross-element correlations are a much more sensitive probe of a hidden structure than dispersion, and they can be measured precisely in a large sample even if the star-by-star measurement noise is comparable to the intrinsic scatter. We conclude that many elements have an independent story to tell, even for the mundane disk stars and elements produced by the core-collapse and Type Ia supernovae. The only way to learn these lessons is to measure the abundances directly, and not merely infer them.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRSDate not supplied

Concept-based Analysis of Neural Networks via Vision-Language Models

The analysis of vision-based deep neural networks (DNNs) is highly desirable but it is very challenging due to the difficulty of expressing formal specifications for vision tasks and the lack of efficient verification procedures. In this paper, we propose to leverage emerging multimodal, vision-language, foundation models (VLMs) as a lens through which we can reason about vision models. VLMs have been trained on a large body of images accompanied by their textual description, and are thus implicitly aware of high-level, human-understandable concepts describing the images. We describe a logical specification language Con spec designed to facilitate writing specifications in terms of these concepts. To define and formally check Con spec specifications, we build a map between the internal representations of a given vision model and a VLM, leading to an efficient verification procedure of natural-language properties for vision models. We demonstrate our techniques on a ResNet-based classifier trained on the RIVAL-10 dataset using CLIP as the multimodal model.

Large Vision Language Models↗