Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Data Reasoning”

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 811 records · Page 45
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Assessment and Simulation of Particulate Transport for Delivery of Solid Amendments into the Subsurface: FY25 Status Report

For particulate-based amendments to be viable for field-scale remediation at the Hanford Site (e.g., the 200 DV-1 Operable Unit), amendment particles need to be delivered a reasonable distance away from an injection well to provide cost effective in situ treatment. Field-scale particle transport models can estimate spatial deposition of amendment particles in the subsurface, which is critical for developing an overall remediation strategy. However, field-scale particle simulations are currently limited due to insufficient simulation capability and a lack of experimental data to validate and parameterize particle transport models. During this fiscal year, the following progress has been made toward a field-scale particle transport modeling evaluation: (1) in addition to the two particle transport models implemented last FY, four additional particle transport models have been implemented within PFLOTRAN; (2) a Python-based pre-screening tool was finalized, enabling users to quickly estimate the particle radius of influence (ROI) for any given particle-amendment system; and (3) an initial compatibility assessment was completed using both particle transport simulations deployed through the pre-screening tool, in conjunction with general guidelines to (a) identify the most suitable amendment particle sizes for various Hanford sediments and (b) evaluate amendment-delivery fluid compatibility. The preliminary compatibility assessment revealed that for amendment delivery success to the various Hanford target formations, amendment particle sizes will likely need to be smaller than the amendment sizes tested in the DV-1 treatability study. It is recommended that amendment particles be decreased in size, or alternative smaller size amendments be obtained from the manufacture, prior to any further experimental testing. Also, preliminary testing suggests that xanthan gum may be the most broadly compatible delivery fluid. Planned laboratory experiments will be instrumental in validating and refining the PFLOTRAN particulate transport model formulations, ultimately enabling predictive capabilities to facilitate the design of field-scale amendment delivery systems. This work consists of acquiring new theoretical or experimental knowledge. The information associated with this report should not be used as design input or operating parameters without additional qualification.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

COVID-19 vaccination status, side effects, and perceptions among breast cancer survivors: a cross-sectional study in China

Introduction Breast cancer is the most prevalent malignancy in patients with coronavirus disease 2019 (COVID-19). However, vaccination data of this population are limited. Methods A cross-sectional study of COVID-19 vaccination was conducted in China. Multivariate logistic regression models were used to assess factors associated with COVID-19 vaccination status. Results Of 2,904 participants, 50.2% were vaccinated with acceptable side effects. Most of the participants received inactivated virus vaccines. The most common reason for vaccination was “fear of infection” (56.2%) and “workplace/government requirement” (33.1%). While the most common reason for nonvaccination was “worry that vaccines cause breast cancer progression or interfere with treatment” (72.9%) and “have concerns about side effects or safety” (39.6%). Patients who were employed (odds ratio, OR = 1.783, p = 0.015), had stage I disease at diagnosis (OR = 2.008, p = 0.019), thought vaccines could provide protection (OR = 1.774, p = 0.007), thought COVID-19 vaccines were safe, very safe, not safe, and very unsafe (OR = 2.074, p < 0.001; OR = 4.251, p < 0.001; OR = 2.075, p = 0.011; OR = 5.609, p = 0.003, respectively) were more likely to receive vaccination. Patients who were 1–3 years, 3–5 years, and more than 5 years after surgery (OR = 0.277, p < 0.001; OR = 0.277, p < 0.001, OR = 0.282, p < 0.001, respectively), had a history of food or drug allergies (OR = 0.579, p = 0.001), had recently undergone endocrine therapy (OR = 0.531, p < 0.001) were less likely to receive vaccination. Conclusion COVID-19 vaccination gap exists in breast cancer survivors, which could be filled by raising awareness and increasing confidence in vaccine safety during cancer treatment, particularly for the unemployed individuals.

Xu, Yali↗
DOE OSTI2021

A New Modeling Framework for Geothermal Operational Optimization with Machine Learning (GOOML)

Geothermal power plants are excellent resources for providing low carbon electricity generation with high reliability. However, many geothermal power plants could realize significant improvements in operational efficiency from the application of improved modeling software. Increased integration of digital twins into geothermal operations will not only enable engineers to better understand the complex interplay of components in larger systems but will also enable enhanced exploration of the operational space with the recent advances in artificial intelligence (AI) and machine learning (ML) tools. Such innovations in geothermal operational analysis have been deterred by several challenges, most notably, the challenge in applying idealized thermodynamic models to imperfect as-built systems with constant degradation of nominal performance. This paper presents GOOML: a new framework for Geothermal Operational Optimization with Machine Learning. By taking a hybrid data-driven thermodynamics approach, GOOML is able to accurately model the real-world performance characteristics of as-built geothermal systems. Further, GOOML can be readily integrated into the larger AI and ML ecosystem for true state-of-the-art optimization. This modeling framework has already been applied to several geothermal power plants and has provided reasonably accurate results in all cases. Therefore, we expect that the GOOML framework can be applied to any geothermal power plant around the world.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Camera settings and biome influence the accuracy of citizen science approaches to camera trap image classification

Scientists are increasingly using volunteer efforts of citizen scientists to classify images captured by motion-activated trail cameras. The rising popularity of citizen science reflects its potential to engage the public in conservation science and accelerate processing of the large volume of images generated by trail cameras. While image classification accuracy by citizen scientists can vary across species, the influence of other factors on accuracy is poorly understood. Inaccuracy diminishes the value of citizen science derived data and prompts the need for specific best-practice protocols to decrease error. We compare the accuracy between three programs that use crowdsourced citizen scientists to process images online: Snapshot Serengeti, Wildwatch Kenya, and AmazonCam Tambopata. We hypothesized that habitat type and camera settings would influence accuracy. To evaluate these factors, each photograph was circulated to multiple volunteers. All volunteer classifications were aggregated to a single best answer for each photograph using a plurality algorithm. Subsequently, a subset of these images underwent expert review and were compared to the citizen scientist results. Classification errors were categorized by the nature of the error (e.g., false species or false empty), and reason for the false classification (e.g., misidentification). Our results show that Snapshot Serengeti had the highest accuracy (97.9%), followed by AmazonCam Tambopata (93.5%), then Wildwatch Kenya (83.4%). Error type was influenced by habitat, with false empty images more prevalent in open-grassy habitat (27%) compared to woodlands (10%). For medium to large animal surveys across all habitat types, our results suggest that to significantly improve accuracy in crowdsourced projects, researchers should use a trail camera set up protocol with a burst of three consecutive photographs, a short field of view, and determine camera sensitivity settings based on in situ testing. Accuracy level comparisons such as this study can improve reliability of future citizen science projects, and subsequently encourage the increased use of such data.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

A differentiable approach to the maximum independent set problem using dataless neural networks

The success of machine learning solutions for reasoning about discrete structures has brought attention to its adoption within combinatorial optimization algorithms. Such approaches generally rely on supervised learning by leveraging datasets of the combinatorial structures of interest drawn from some distribution of problem instances. Reinforcement learning has also been employed to find such structures. Here, in this paper, we propose a different approach in that no data is required for training the neural networks that produce the solution. In this sense, what we present is not a machine learning solution, but rather one that is dependent on neural networks and where backpropagation is applied to a loss function defined by the structure of the neural network architecture as opposed to a training dataset. In particular, we reduce the popular combinatorial optimization problem of finding a maximum independent set to a neural network and employ a dataless training scheme to refine the parameters of the network such that those parameters yield the structure of interest. Additionally, we propose a universal graph reduction procedure to handle large-scale graphs. The reduction exploits community detection for graph partitioning and is applicable to any graph type and/or density. Experimental results on both real and synthetic graphs demonstrate that our proposed method performs on par or outperforms state-of-the-art learning-based methods in terms of the size of the found set without requiring any training data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Co-Design of Free-Space Metasurface Optical Neuromorphic Classifiers for High Performance

Classification of features in a scene typically requires conversion of the incoming photonic field into the electronic domain. Recently, an alternative approach has emerged whereby passive structured materials can perform classification tasks by directly using free-space propagation and diffraction of light. In this manuscript, we present a theoretical and computational study of such systems and establish the basic features that govern their performance. We show that system architecture, material structure, and input light field are intertwined and need to be co-designed to maximize classification accuracy. Our simulations show that a single layer metasurface can achieve classification accuracy better than conventional linear classifiers, with an order of magnitude fewer diffractive features than previously reported. For a wavelength λ, single layer metasurfaces of size 100λ × 100λ with an aperture density λ –2 achieve ~96% testing accuracy on the MNIST data set, for an optimized distance ~100λ to the output plane. This is enabled by an intrinsic nonlinearity in photodetection, despite the use of linear optical metamaterials. Furthermore, we find that once the system is optimized, the number of diffractive features is the main determinant of classification performance. The slow asymptotic scaling with the number of apertures suggests a reason why such systems may benefit from multiple layer designs. Finally, we show a trade-off between the number of apertures and fabrication noise.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Theoretical upper limits of the thermal conductivity of Si3N4

Silicon nitride (Si3N4) is a promising substrate for high-power electronics due to its superior mechanical properties and potential outstanding thermal conductivity (κ). As experiments keep pushing the upper limit of κ of Si3N4, it is believed that it can reach 450 W/mK, similar to SiC, based on classical models and molecular dynamics simulations. In this work, we reveal from first principles that the theoretical κ upper limits of β-Si3N4 are only 169 and 57 W/mK along the c and a axes at room temperature, respectively. Those of α-Si3N4 are about 116 and 87 W/mK, respectively. The predicted temperature-dependent κ matches well with the highest available experimental data, which supports the accuracy of our calculations, and suggests that the κ upper limit of Si3N4 has already been reached in the experiment. Compared to other promising semiconductors (e.g., SiC, AlN, and GaN), Si3N4 has a much lower κ than expected even though the chemical bonding and mechanical strengths are close or even stronger. We find the underlying reason is that Si3N4 has much lower phonon lifetimes and mean free paths (<0.5 μm) due to the larger three-phonon scattering phase space and stronger anharmonicity. Interestingly, we find that the larger unit cell (with more basis atoms) that leads to a smaller fraction of acoustic phonons is not the reason for lower κ. Grain size-dependent κ indicates that the grain boundary scattering plays a negligible role in most experimental samples. This work clarifies the theoretical κ upper limits of Si3N4 and can guide experimental research.

Physics↗
DOE OSTI2022

Simulation of the High Temperature Test Facility (HTTF) Core Using the 2D Ring Model with SAM

A two-dimensional ring model is developed with SAM to model the core of the High Temperature Test Facility (HTTF) at the system level. The ring model simplifies the complex structure of the HTTF core by converting the hexagonal rows of heaters and flow channels into layers of concentric annular rings. The ring model is first compared against a 3D-1D model where the solid structures are fully resolved in three dimensions while the fluid structures are modeled as one-dimensional flows. Comparison between the 3D-1D and the ring models shows that the latter can predict major parameters reasonably well under steady-state normal operating condition, but the heater temperatures are underpredicted. Adjustment is made to the effective thermal conductivity of the ceramic core of the ring model to improve the heater temperature predictions. Furthermore, the ring model is also used to simulate a transient Pressurized Conduction Cooldown (PCC) condition and is benchmarked with the experimental data from the HTTF Test PG-27. Good agreement is obtained between the experimental data and the predictions by the ring model.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

An Analysis of Grid Operator Survey Responses: Inexperience, Workload and Fatigue in the Control Room

Although a wide array of tools and technologies have been developed over the last decade to support power grid operators, deployment of these tools has been less successful. One reason for unsuccessful deployment may be an inadequate understanding of the factors that contribute to operator error in the control room. An analysis of operators’ current vulnerabilities may provide the baseline understanding needed to inform new technology integration. In an attempt to learn more about these vulnerabilities and their perceived impact on human error we collected and analyzed survey data from 20 electric grid control room operators. We asked survey respondents to consider the various operator, technology and interaction vulnerabilities that may arise during work in the control room and record their attitudes and experiences toward each. Results suggest operator inexperience, high mental workload and fatigue are the most common vulnerabilities experienced during a shift. Survey results were analyzed to explore these vulnerabilities in greater depth.

Inexperience, Workload, Fatigue↗
DOE OSTI2021

Prediction of Leakage Current and Depletion Voltage in Silicon Detectors Under Extraterrestrial Radiation Conditions

Silicon detection is a mature technology for registering the passage of charged particles. At the same time it continues to evolve toward increasing radiation tolerance as well as precision and adaptability. For these reasons it is likely to remain a critical element of detection of systems associated with extraterrestrial exploration. Silicon sensor leakage current and depletion voltage depend on the integrated fluence received by the sensor and on its thermal history during and after the irradiation process. For minimal assumptions on shielding and hence on the particle energy spectrum, and using published data on Martian ground temperature, we predict the leakage current density and the depletion voltage, as a function of time, of silicon sensors in transit to and deployed continuously on the Mars surface for a duration of up to 28 Earth-years, for several sensor geometries and a worst-case temperature scenario.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Development of a Discrepancy Checker for the Digital Twin in a Supervisory Control System for a Thermal Energy Delivery System

Defined as a virtual representation of a physical object, process, or service, and used to support real-world decision-making, a digital twin (DT) can be utilized to combine classical and novel frameworks in sensors, state predictions, and multi-input/multi-output systems, and to enable optimal autonomous operations. However, a DT’s usefulness largely depends on its ability to adequately mirror the state of its physical counterpart, and this adequacy should be reflected by the level of uncertainty in the underlying simulation models when estimating and predicting quantities of interest (QOIs). Moreover, simulation models in a DT may involve multiple fidelities of representations—ranging from physics-based models to data-driven ones—but classical uncertainty quantification (UQ) methods struggle to handle numerous uncertainty sources, nor are they designed for real-time applications. This work presents a UQ-based discrepancy checking and diagnosis tool for a DT-based supervisory control system applied to a thermal energy delivery system (TEDS) at Idaho National Laboratory. The discrepancy checker was developed using metadata from an automated DT development process, and these metadata included different combinations of physical model forms and model parameters, training data and hyperparameters for surrogate models, and design parameters for supervisory control systems. Next, correlations between the uncertainty results and the metadata were established and then applied to the DT operations. The discrepancy checker evaluates the discrepancies between model predictions from virtual and sensor measurements and backtraces them to the corresponding major sources of uncertainty. The discrepancy checker showed reasonable performance in detecting discrepancies and diagnosing sources of uncertainty in testing scenarios.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Guiding Principles for Geochemical/Thermodynamic Model Development and Validation in Nuclear Waste Disposal: A Close Examination of Recent Thermodynamic Models for H + —Nd 3+ —NO 3 - (—Oxalate) Systems

Development of a defensible source-term model (STM), usually a thermodynamical model for radionuclide solubility calculations, is critical to a performance assessment (PA) of a geologic repository for nuclear waste disposal. Such a model is generally subjected to rigorous regulatory scrutiny. In this article, we highlight key guiding principles for STM model development and validation in nuclear waste management. We illustrate these principles by closely examining three recently developed thermodynamic models with the Pitzer formulism for aqueous H + —Nd 3+ —NO 3 - (—oxalate) systems in a reverse alphabetical order of the authors: the XW model developed by Xiong and Wang, the OWC model developed by Oakes et al., and the GLC model developed by Guignot et al., among which the XW model deals with trace activity coefficients for Nd(III), while the OWC and GLC models are for concentrated Nd(NO 3 ) 3 electrolyte solutions. The principles highlighted include the following: (1) Principle 1. Validation against independent experimental data: A model should be validated against experimental data or field observations that have not been used in the original model parameterization. We tested the XW model against multiple independent experimental data sets including electromotive force (EMF), solubility, water vapor, and water activity measurements. The results show that the XW model is accurate and valid for its intended use for predicting trace activity coefficients and therefore Nd solubility in repository environments. (2) Principle 2. Testing for relevant and sensitive variables: Solution pH is such a variable for an STM and easily acquirable. All three models are checked for their ability to predict pH conditions in Nd(NO 3 ) 3 electrolyte solutions. The OWC model fails to provide a reasonable estimate for solution pH conditions, thus casting serious doubt on its validity for a source-term calculation. In contrast, both the XW and GLC models predict close-to-neutral pH values, in agreement with experimental measurements. (3) Principle 3. Honoring physical constraints: Upon close examination, it is found that the Nd(III)-NO 3 association schema in the OWC model suffers from two shortcomings. Firstly, its second stepwise stability constant for Nd(NO 3 ) 2+ (log K 2 ) is much higher than the first stepwise stability constant for NdNO 3 2+ (log K 1 ), thus violating the general rule of (log K 2 –log K 1 ) < 0, or $\frac{K1}{K2}$>1. Secondly, the OWC model predicts abnormally high activity coefficients for Nd(NO 3 ) 2 + (up to ~900) as the concentration increases. (4) Principle 4. Minimizing degrees of freedom for model fitting: The OWC model with nine fitted parameters is compared with the GLC model with five fitted parameters, as both models apply to the concentrated region for Nd(NO 3 ) 3 electrolyte solutions. The latter appears superior to the former because the latter can fit osmotic coefficient data equally well with fewer model parameters. The work presented here thus illustrates the salient points of geochemical model development, selection, and validation in nuclear waste management.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2021

SMC 2021 : Analyzing Resource Utilization and User Behavior on Titan Supercomputer

Resource utilization statistics of submitted jobs on a supercomputer can help us understand how users from various scientific domains use HPC platforms and better design a job scheduler. We explore to generate insight regarding workload distribution and usage pattern domains from job scheduler trace, GPU failure information, and project-specific information collected from Titan supercomputer. Furthermore, we want to know how the scheduler performance varies over time and how the users' scheduling behavior changes following a system failure. These observations have the potential to provide valuable insight, which is helpful to prepare for system failures. These practices will help us develop and apply novel machine learning algorithms in understanding system behavior, requirement, and better scheduling of HPC systems. There are two datasets, RUR and GPU. RUR: This dataset is the job scheduler traces collected from the Titan supercomputerfrom 01/01/2015 to 07/31/2019 (2015.csv - 2019.csv). These were collected usingResource Utilization Report (RUR), a Cray-developed resource-usage data collectionand reporting system. It contains the usage information of its critical resources (CPU,Memory, GPU, and I/O) of each running job on Titan during that period [2]. ProjectAreas: Every job is associated with a project ID. TheProjectAreas.csvdatasetprovides a mapping of the project ID to its domain science. GPU: There have been some hardware-related issues in the GPUs in Titan that caused some GPUs to fail, sometimes irrecoverably during some job runs. This dataset provides information regarding these failures during the execution of the submitted jobs. GPUs on Titan are uniquely identified by a serial number (SN), and they are installed in a location. A GPU can be installed in a location, then removed from that location following a failure, and then re-installed in a different location after fixing the problem. If the failure can't be recovered, the GPU might be removed entirely from Titan. There are two prominent types of failures that resulted in the removal of GPUs from Titan: Double Bit Error (DBE) and Out of the Bus (OTB). The dataset (gc_full.csv) has the following fields: 1. SN : Serial number of a GPU 2. location : The location where it is installed 3. insert : The time when it was inserted into that location 4. remove : The time when it was removed from that location 5. duration : Amount of time the GPU spent in this location 6. out : If the device was taken out entirely w/o a re-installment into a new location. 7. event : If the GPU was taken out entirely, the reason for its removal. To learn more about this dataset, please refer to the git repositoryhttps://github.com/olcf/TitanGPULifeand the related publication [1]. References [1] George Ostrouchov, Don Maxwell, Rizwan A Ashraf, Christian Engelmann, MallikarjunShankar, and James H Rogers. Gpu lifetimes on titan supercomputer: Survival analysisand reliability. InSC20: International Conference for High Performance Computing,Networking, Storage and Analysis, pages 1-14. IEEE, 2020. [2] Feiyi Wang, Sarp Oral, Satyabrata Sen, and Neena Imam. Learning from five-yearresource-utilization data of titan system. In2019 IEEE International Conference onCluster Computing (CLUSTER), pages 1-6. IEEE, 2019.

42 ENGINEERING↗
DOE OSTI2021

Verification of Coupled Hydraulic Fracturing Simulators Using Laboratory-Scale Experiments

In this work, we aim to verify the predictions of the numerical simulators, which are used for designing field-scale hydraulic stimulation experiments. Although a strong theoretical understanding of this process has been gained over the past few decades, numerical predictions of fracture propagation in low-permeability rocks still remains a challenge. Against this background, we performed controlled laboratory-scale hydraulic fracturing experiments in granite samples, which not only provides high-quality experimental data but also a well-characterized experimental set-up. Using the experimental pressure responses and the final fracture sizes as benchmark, we compared the numerical predictions of two coupled hydraulic fracturing simulators—CSMP and GEOS. Both the simulators reproduced the experimental pressure behavior by implementing the physics of Linear Elastic Fracture Mechanics (LEFM) and lubrication theory within a reasonable degree of accuracy. The simulation results indicate that even in the very low-porosity (1–2 %) and low-permeability (10 -18 m 2 - 10 -19 m 2 ) crystalline rocks, which are usually the target of EGS, fluid-loss into the matrix and unsaturated flow impacts the formation breakdown pressure and the post-breakdown pressure trends. Therefore, underestimation of such parameters in numerical modeling can lead to significant underestimation of breakdown pressure. The simulation results also indicate the importance of implementing wellbore solvers for considering the effect of system compressibility and pressure drop due to friction in the injection line. The varying injection rate as a result of decompression at the instant of fracture initiation affects the fracture size, while the entry friction at the connection between the well and the initial notch may cause an increase in the measured breakdown pressure.

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

Sensitivity of the simulation of passive neutron emission from UF 6 cylinders to the uncertainties in both 19 F(α,n) energy spectrum and thick target yield of 234 U in UF 6

Interest in safeguards verification measurements using passive thermal neutron counting to assay 235 U content in large 30B UF 6 canisters has grown in recent years. Here, the prohibitively high cost and impracticality of using reference 30B calibration cylinders extensively will likely make accurate simulations of increasing interest. Accuracy of the simulated response will define the confidence in the predicted response and the extent to which simulations can reasonably be relied upon. With 234 U driven 19 F(α, n) reactions being the main neutron source in low enriched UF 6 the uncertainties of the 19 F(α, n) energy spectrum and the thick target yield of 234 U in UF 6 propagate into the uncertainty in the predicted response and represent a major influence of basic nuclear data. Here sensitivity of the simulated total (Singles) and coincidence (Doubles) count rates are assessed for the Passive Neutron Enrichment Meter using six potential 19 F(α, n) neutron energy spectra over a range of enrichments and material distributions. The results indicate that variations in the Singles and Doubles due to simulated (α, n) neutron spectrum are less than 1.5% for this set of simulated neutron spectra, with dependence varying inversely with enrichment. Singles uncertainty is only slightly less than that of the thick target 19 F(α, n) yield corresponding to the primary neutron source, whereas the 19 F(α, n) yield dependence of the Doubles is reduced by the non-negligible 238 U(SF) coincident neutron emissions. Based on available thick target 19 F(α, n) yield estimates the uncertainty is on the order of 5%, establishing this as the main nuclear data limitation when simulating thermal neutron detectors response for 30B UF 6 storage cylinders. Based on these findings, it appears that the measurement and evaluation of the thick target 19 F(α, n) yield for uranium hexafluoride is due.

19F(α,n) neutron spectrum↗
DOE OSTI2020

Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability

Abstract Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of neural networks can enable the discovery of scientifically meaningful connections within geoscientific data. In particular, we use two methods for neural network interpretation called backward optimization and layerwise relevance propagation, both of which project the decision pathways of a network back onto the original input dimensions. To the best of our knowledge, LRP has not yet been applied to geoscientific research, and we believe it has great potential in this area. We show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network‐related geoscience research.

58 GEOSCIENCES↗
DOE OSTI2021

The effects of varying colour–luminosity relations on Type Ia supernova science

ABSTRACT The success of Type Ia supernova (SN Ia) distance standardization for cosmology relies on a single global linear relationship between their peak luminosity and colour, the β parameter. However, there are several pieces of evidence and physical reasons to believe that this relation is not universal and may change within different subgroups, or even among individual objects. In this work, we allow β to vary among subpopulations with different observed properties in the cosmological fits. Although the inferred cosmological parameters are consistent with previous studies that assume a single colour–luminosity relation, we find that the SN data favour non-universal distributions of β when split according to SN colour and/or host-galaxy mass. For galaxy mass, we obtain a β-step relation in which low β values occur in more massive galaxies, a trend that can be explained by differing dust reddening laws for two types of environments. For colour, we find that bluer/redder SNe Ia are consistent with a lower/larger β. This trend is explained with β being a combination of a low intrinsic colour–luminosity relation dominant in bluer SNe and a higher extrinsic reddening relation dominant at redder colours. The host-galaxy mass-step correction always provides better distance calibration, regardless of the multiple β approaches, and we suggest that it may come from a difference in intrinsic colour–luminosity properties of SNe Ia in two types of environments. Additionally, we find that blue SNe in low-mass environments are better standard candles than the others.

González-Gaitán, S. (ORCID:0000000195410317)↗