Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “predictive mapping”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

High-throughput reaction discovery for Cs–Pb–Br nanocrystal synthesis

High-throughput reaction discovery is necessary to understand complex reaction spaces for inorganic nanocrystal synthesis. Here, we implemented a high-throughput continuous flow millifluidic reactor to perform reaction discovery for Cs–Pb–Br nanocrystal synthesis using a ligand assisted reprecipitation (LARP)-type approach. 3D-printed flow resistors enable the screening of up to 16 different mixing ratios within a single 90 s run, allowing for >270 different precursor concentration ratios to be quickly tested to explore the phase space that results in CsPbBr 3 , Cs 4 PbBr 6 , a biphasic mixture, or no product. To construct a full phase map from these high-throughput experiments, a neural network was trained and validated to predict the product composition (~500 000 points in precursor concentration space). The phase map predicts product composition/phase as a function of Cs–Pb–Br feed ratio. As a result, this approach demonstrates how high-throughput flow chemistry can be used in tandem with machine learning to rapidly explore nanocrystal reaction spaces in flow.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Predicting Switchgrass Biomass Yields Using a Spectral Vegetation Index Derived from Multispectral Satellite Imagery

Successful scaling of perennial bioenergy crop production requires a landscape design that optimizes the benefits of finite lands for people, communities, and environments. Utilizing marginal areas is the key to sustainable bioenergy crop production (Ssegane et al., 2015, 2016). Marginal areas are often small-sized lands and unevenly distributed across the agricultural landscape (Ssegane et al., 2016); thus, a systematic, semi-automated remote sensing method is needed as an effective means of estimating bioenergy crop yields across landscapes. Argonne National Laboratory (Argonne) is currently developing a tool, Scaling Up Perennial Bioenergy Economics and Ecosystem Services Tool (SUPERBEEST), to identify marginal agricultural lands and quantify environmental and economic effects of perennial bioenergy crop production systems. The tool aims to provide users a path to foster the sustainable and productive integration of bioenergy crops in the Midwestern agricultural landscape. Reliable, cost-effective, and timely estimation of bioenergy crop yields using remote sensing would help calculate and track the success of integrated bioenergy crops in the landscape for those communities. Argonne previously conducted feasibility studies for estimating biomass yields for bioenergy feedstock, corn and perennial grass using spectral vegetation indices (SVIs)1 derived from optical imagery (Hamada et al., 2015, 2021). In both studies, SVIs, more specifically those sensitive to plant chlorophyll or nitrogen contents, showed potential for estimating or predicting biomass yields with a correlation of determination (R2) ranging from 0.54 to 0.96, indicating a value for further investigation as a viable means of quantifying bioenergy feedstock production across large landscapes. Thus, the goal of this study is to evaluate the feasibility of use of SVIs as a means of estimating or predicting switchgrass biomass yields at harvest using publicly available multispectral satellite imagery. The feasibility analysis was performed using four study areas of mature switchgrass located in Virginia. Objectives are to (1) examine the SVIs and establish their relationships with switchgrass biomass yields at harvest, (2) develop a parsimonious image processing model for predicting at-harvest yields by applying the relationships with the most promising spectral index and (3) map switchgrass yields predicted by the image processing model across the study sites. The calibration to field data will rely on switchgrass biomass yields determined by the baling method, representing a potential challenge to the analysis but an important practical aspect for future applications. With this research design, the study aimed to gain insights into enabling remote sensing-based estimation of bioenergy crop yields in a reliable, cost- effective, and timely manner across large, heterogeneous landscapes.

09 BIOMASS FUELS↗
DOE OSTI2024

Automated Grain Boundary (GB) Segmentation and Microstructural Analysis in 347H Stainless Steel Using Deep Learning and Multimodal Microscopy

Austenitic 347H stainless steel offers superior mechanical properties and corrosion resistance required for extreme operating conditions such as high temperature. The change in microstructure due to composition and process variations is expected to impact material properties. Identifying microstructural features such as grain boundaries thus becomes an important task in the process-microstructure-properties loop. Applying convolutional neural network (CNN)-based deep learning models is a powerful technique to detect features from material micrographs in an automated manner. In contrast to microstructural classification, supervised CNN models for segmentation tasks require pixel-wise annotation labels. However, manual labeling of the images for the segmentation task poses a major bottleneck for generating training data and labels in a reliable and reproducible way within a reasonable timeframe. Microstructural characterization especially needs to be expedited for faster material discovery by changing alloy compositions. Here, in this study, we attempt to overcome such limitations by utilizing multimodal microscopy to generate labels directly instead of manual labeling. We combine scanning electron microscopy images of 347H stainless steel as training data and electron backscatter diffraction micrographs as pixel-wise labels for grain boundary detection as a semantic segmentation task. The viability of our method is evaluated by considering a set of deep CNN architectures. We demonstrate that despite producing instrumentation drift during data collection between two modes of microscopy, this method performs comparably to similar segmentation tasks that used manual labeling. Additionally, we find that naïve pixel-wise segmentation results in small gaps and missing boundaries in the predicted grain boundary map. By incorporating topological information during model training, the connectivity of the grain boundary network and segmentation performance is improved. Finally, our approach is validated by accurate computation on downstream tasks of predicting the underlying grain morphology distributions which are the ultimate quantities of interest for microstructural characterization.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Multi-head attention-based U-Nets for predicting protein domain boundaries using 1D sequence features and 2D distance maps

Abstract The information about the domain architecture of proteins is useful for studying protein structure and function. However, accurate prediction of protein domain boundaries (i.e., sequence regions separating two domains) from sequence remains a significant challenge. In this work, we develop a deep learning method based on multi-head U-Nets (called DistDom) to predict protein domain boundaries utilizing 1D sequence features and predicted 2D inter-residue distance map as input. The 1D features contain the evolutionary and physicochemical information of protein sequences, whereas the 2D distance map includes the structural information of proteins that was rarely used in domain boundary prediction before. The 1D and 2D features are processed by the 1D and 2D U-Nets respectively to generate hidden features. The hidden features are then used by the multi-head attention to predict the probability of each residue of a protein being in a domain boundary, leveraging both local and global information in the features. The residue-level domain boundary predictions can be used to classify proteins as single-domain or multi-domain proteins. It classifies the CASP14 single-domain and multi-domain targets at the accuracy of 75.9%, 13.28% more accurate than the state-of-the-art method. Tested on the CASP14 multi-domain protein targets with expert annotated domain boundaries, the average per-target F1 measure score of the domain boundary prediction by DistDom is 0.263, 29.56% higher than the state-of-the-art method.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Recurrent neural networks for short-term and long-term prediction of geothermal reservoirs

Accurate prediction of geothermal reservoir responses to alternative energy production scenarios is critical for optimizing the development of the underlying resources. While the conventional physics-based models offer a comprehensive prediction tool, data-driven models provide an efficient alternative to build fit-for-purpose predictive models by extracting and using the statistical patterns in the collected data to make predictions. The recurrent neural network (RNN) is a data-driven model that is commonly applied to predict time series sequences. This paper presents a variant of RNN that also utilizes the efficiency of convolutional neural networks (CNN) for the prediction of energy production from geothermal reservoirs. Specifically, a CNN–RNN architecture is developed that takes historical well controls as input (features) and their corresponding production response data as output (labels) to learn an input-output mapping that can predict the future well production responses/performance for any given future well control inputs. The model is paired with a labeling scheme to handle real field disturbances that create data gaps. In addition to the model structure, we introduce a thorough workflow for applying the model, which includes data pre-processing, feature selection, as well as different training strategies for short-term and long-term prediction. Finally, the performance and accuracy of the model are evaluated by applying it to multiple datasets, including a field reservoir model.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Ising-Traffic: Using Ising Machine Learning to Predict Traffic Congestion under Uncertainty

This paper addresses the challenges in accurate and realtime traffic congestion prediction with uncertainty by proposing Ising-Traffic, a novel quantum-inspired dual-model Ising based traffic prediction framework which delivers higher accuracy and lower latency than SOTA solutions. While traditional and deep learning methods face the trade-off between algorithm complexity and computational efficiency, our Ising-based method leverages Ising’s inherent and unique capability of finding the state of a system with the lowest energy and applying it to traffic prediction. In this work, traffic prediction under uncertainty is formulated into two separate Ising models: Reconstruct-Ising and Predict-Ising. Reconstruct-Ising is mapped onto modern Ising machine and handles uncertainty in traffic accurately with negligible latency and energy consumption, while Predict-Ising is mapped onto traditional processors and predicts future congestion precisely with only at most 1.8% computational demands of existing solutions. Our evaluation shows Ising-Traffic delivers on average 98× speedups and 5% accuracy improvement over SOTA.

traffic flow control, Ising↗
DOE OSTI2022

Integrating data types to estimate spatial patterns of avian migration across the Western Hemisphere

For many avian species, spatial migration patterns remain largely undescribed, especially across hemispheric extents. Recent advancements in tracking technologies and high-resolution species distribution models (i.e., eBird Status and Trends products) provide new insights into migratory bird movements and offer a promising opportunity for integrating independent data sources to describe avian migration. Here, we present a three-stage modeling framework for estimating spatial patterns of avian migration. First, we integrate tracking and band re-encounter data to quantify migratory connectivity, defined as the relative proportions of individuals migrating between breeding and nonbreeding regions. Next, we use estimated connectivity proportions along with eBird occurrence probabilities to produce probabilistic least-cost path (LCP) indices. In a final step, we use generalized additive mixed models (GAMMs) both to evaluate the ability of LCP indices to accurately predict (i.e., as a covariate) observed locations derived from tracking and band re-encounter data sets versus pseudo-absence locations during migratory periods and to create a fully integrated (i.e., eBird occurrence, LCP, and tracking/band re-encounter data) spatial prediction index for mapping species-specific seasonal migrations. To illustrate this approach, we apply this framework to describe seasonal migrations of 12 bird species across the Western Hemisphere during pre- and postbreeding migratory periods (i.e., spring and fall, respectively). We found that including LCP indices with eBird occurrence in GAMMs generally improved the ability to accurately predict observed migratory locations compared to models with eBird occurrence alone. Using three performance metrics, the eBird + LCP model demonstrated equivalent or superior fit relative to the eBird-only model for 22 of 24 species–season GAMMs. In particular, the integrated index filled in spatial gaps for species with over-water movements and those that migrated over land where there were few eBird sightings and, thus, low predictive ability of eBird occurrence probabilities (e.g., Amazonian rainforest in South America). This methodology of combining individual-based seasonal movement data with temporally dynamic species distribution models provides a comprehensive approach to integrating multiple data types to describe broad-scale spatial patterns of animal movement. Further development and customization of this approach will continue to advance knowledge about the full annual cycle and conservation of migratory birds.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Topological network analysis of patient similarity for precision management of acute blood pressure in spinal cord injury

Background: Predicting neurological recovery after spinal cord injury (SCI) is challenging. Using topological data analysis, we have previously shown that mean arterial pressure (MAP) during SCI surgery predicts long-term functional recovery in rodent models, motivating the present multicenter study in patients. Methods: Intra-operative monitoring records and neurological outcome data were extracted (n = 118 patients). We built a similarity network of patients from a low-dimensional space embedded using a non-linear algorithm, Isomap, and ensured topological extraction using persistent homology metrics. Confirmatory analysis was conducted through regression methods. Results: Network analysis suggested that time outside of an optimum MAP range (hypotension or hypertension) during surgery was associated with lower likelihood of neurological recovery at hospital discharge. Logistic and LASSO (least absolute shrinkage and selection operator) regression confirmed these findings, revealing an optimal MAP range of 76–[104-117] mmHg associated with neurological recovery. Conclusions: We show that deviation from this optimal MAP range during SCI surgery predicts lower probability of neurological recovery and suggest new targets for therapeutic intervention. Funding: NIH/NINDS: R01NS088475 (ARF); R01NS122888 (ARF); UH3NS106899 (ARF); Department of Veterans Affairs: 1I01RX002245 (ARF), I01RX002787 (ARF); Wings for Life Foundation (ATE, ARF); Craig H. Neilsen Foundation (ARF); and DOD: SC150198 (MSB); SC190233 (MSB); DOE: DE-AC02-05CH11231 (DM).

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Mapping Post-Climate Change Biogeographical Regions with Deep Latent Variable Models

Forecasting future changes to biodiversity due to shifts in climate is challenging due to nonlinear interactions between species as recorded in their presence/absence data. This work proposes using variational autoencoders with environmental covariates to identify low-dimensional structure in species’ joint co-occurrence patterns and leveraging this simplified representation to provide multivariate predictions of their habitat extent under future climate scenarios. We pursue a latent space clustering approach to map biogeographical regions of frequently co-occurring species and apply this methodology to a dataset from northern Belgium, generating predictive maps illustrating how these regions may expand or contract with changing temperature under a future climate scenario.

Krapu, Chris↗
DOE OSTI2023

A Fusion of Geothermal and InSAR Data with Machine Learning for Enhanced Deformation Forecasting at the Geysers

The Geysers geothermal field in California is experiencing land subsidence due to the seismic and geothermal activities taking place. This poses a risk not only to the underlying infrastructure but also to the groundwater level which would reduce the water availability for the local community. Because of this, it is crucial to monitor and assess the surface deformation occurring and adjust geothermal operations accordingly. In this study, we examine the correlation between the geothermal injection and production rates as well as the seismic activity in the area, and we show the high correlation between the injection rate and the number of earthquakes. This motivates the use of this data in a machine learning model that would predict future deformation maps. First, we build a model that uses interferometric synthetic aperture radar (InSAR) images that have been processed and turned into a deformation time series using LiCSBAS, an open-source InSAR time series package, and evaluate the performance against a linear baseline model. The model includes both convolutional neural network (CNN) layers as well as long short-term memory (LSTM) layers and is able to improve upon the baseline model based on a mean squared error metric. Then, after getting preprocessed, we incorporate the geothermal data by adding them as additional inputs to the model. This new model was able to outperform both the baseline and the previous version of the model that uses only InSAR data, motivating the use of machine learning models as well as geothermal data in assessing and predicting future deformation at The Geysers as part of hazard mitigation models which would then be used as fundamental tools for informed decision making when it comes to adjusting geothermal operations.

Yazbeck, Joe (ORCID:0000000302235260)↗
DOE OSTI2026

Latent heat thermal energy storage performance maps enabling fast & accurate building energy simulations

Thermal energy storage (TES) using phase change materials (PCMs) has gained attention as an effective approach to manage energy demand fluctuations and shift peak building loads. PCM embedded heat exchangers (PCM-HXs) offer high energy storage density and low temperature variation during phase change, being suitable for load-shifting applications. However, this component is typically evaluated using computationally expensive methods, which present significant challenges when the ultimate goal is to assess the performance of PCM-HX integrated thermal energy storage systems in the full building context. In this paper, we present a methodology to generate highly accurate and computationally efficient PCM-HX performance maps which can be easily integrated into building energy simulation tools to analyze the feasibility of space conditioning systems with latent heat PCM-based TES. The performance maps are generated using a computationally efficient PCM-HX simulation tool based on a Generalized Resistance-Capacitance Model (GRCM) which can simulate arbitrary PCM-HXs with high accuracy and significantly less computational effort compared to full CFD simulations. The methodology was verified for a case study considering a 5-ton (~17.5 kW) air-to-water heat pump-thermal energy storage system (HP-TES), which was co-simulated in Modelica for a DOE prototype small-office building in Vienna, Austria, using Spawn of EnergyPlus™. The TES performance maps provided accurate predictions of PCM-HX behavior when used as Modelica component, with deviations within 2-4% while also achieving at least 103 computational time reduction. Leveraging this faster prediction capability, four PCMs with different melting temperatures for cooling (12°C, 16°C) and heating (31°C, 36°C) were assessed to investigate their impact on system performance. This work highlights the importance of robust PCM-HX models for efficient and high-fidelity building-level simulations, presenting new opportunities for advanced control strategy development and parametric analysis of TES configurations in a computationally efficient manner

Modelica Building Simulations↗
DOE OSTI2021

AI-Batt (Autonomous Identification of Battery Life Models) [SWR 21-36]

Autonomous Identification of Battery Life Models (AI-Batt) AI-Batt is a MATLAB code base for developing lifetime models for batteries from accelerated aging data. The code base provides many functions for processing, visualizing, and modeling battery aging data, making the data processing, exploration, and modeling workflow substantially faster. These tools are tailored for working with battery aging data sets, which usually consist of many separate time-series for each cell, with many test conditions and possible replicates at each condition, which makes it difficult to simply process or visualize the data set. Complex modeling tasks, such as cross-validation, sensitivity analysis, and uncertainty quantification have been implemented to enable thorough statistical investigation of model predictions. Additionally, several machine-learning algorithms are implemented to autonomously identify suitable models via symbolic regression. Data processing functions automatically cast data from the struct data type, which is commonly used to store experimental data, but is not an acceptable input for most algorithms, to the table data type, which can be easily used as input to any optimization algorithm. Also, the data can be separated into time-invariant and time-variant data tables, which is helpful for exploring the data set as well as developing separate models for time-variant and time-invariant aging mechanisms. For example, in aging tests with constant temperature, temperature is a time-invariant experimental condition. Visualization tools enable plotting of data, model fits, and model simulations possible with single-line function calls, empowering data exploration of complex data sets with both time-varying and time-invariant trends. Plots can be automatically generated for the whole data set, or separated by data group (groups of test replicates) or individual data series. Data points or data series can be automatically colored by the value of a variable with a variety of color maps, and model predictions can also be colored by the value of a fit statistic. Comparisons between data sets and the predictions/simulations of different models on the same data set can be easily plotted as well. Distributions of parameter values from bootstrap resampling can be plotted to visualize the reliability of parameter estimation, or determine any correlations between parameters. Modeling tools handle the complex task of creating and parsing symbolic equations for modeling battery lifetime. Equations are parsed to grab relevant data variables, parameter values, or specified sub-models for input into optimization, evaluation, or simulation functions. Models can be optimized locally (one set of parameters for each data series), bi-level (some parameters shared across the data set), or globally (single set of parameters for all data). Functions implementing symbolic regression algorithms help users to discover effective model equations, even in poorly sampled, high-dimensional data.

Smith, Kandler↗
DOE OSTI2023

Explainable deep learning for insights in El Niño and river flows

The El Niño Southern Oscillation (ENSO) is a semi-periodic fluctuation in sea surface temperature (SST) over the tropical central and eastern Pacific Ocean that influences interannual variability in regional hydrology across the world through long-range dependence or teleconnections. Recent research has demonstrated the value of Deep Learning (DL) methods for improving ENSO prediction as well as Complex Networks (CN) for understanding teleconnections. However, gaps in predictive understanding of ENSO-driven river flows include the black box nature of DL, the use of simple ENSO indices to describe a complex phenomenon and translating DL-based ENSO predictions to river flow predictions. Here we show that eXplainable DL (XDL) methods, based on saliency maps, can extract interpretable predictive information contained in global SST and discover SST information regions and dependence structures relevant for river flows which, in tandem with climate network constructions, enable improved predictive understanding. Our results reveal additional information content in global SST beyond ENSO indices, develop understanding of how SSTs influence river flows, and generate improved river flow prediction, including uncertainty estimation. Observations, reanalysis data, and earth system model simulations are used to demonstrate the value of the XDL-CN based methods for future interannual and decadal scale climate projections.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

Band gap predictions of double perovskite oxides using machine learning

Abstract The compositional and structural variety inherent to oxide perovskites spawn wide-ranging applications. In perovskites, the band gap E g , a key material parameter for these applications, can be optimally controlled by varying the composition. Here, we implement a hierarchical screening process in which two cross-validated and predictive machine learning models for band gap classification and regression, trained using exhaustive datasets that span 68 elements of the periodic table, are applied sequentially. The classification model separates wide band gap materials, with E g ≥ 0.5 eV, from materials which have zero or relatively small band gaps, namely E g < 0.5 eV, and the second regression model quantitatively predicts the gap value of the wide band gap compounds. The study down-selects 13,589 cubic oxide perovskite compositions that are predicted to be experimentally formable, thermodynamically stable, and have a wide band gap. Of these, a subset of 310 compounds, which are predicted to be stable and formable with a confidence greater than 90%, are identified for further investigation. Our models are methodically analyzed via performance metrics and inter-dependence of model features to gain physical insight into the band gap prediction problem. Design maps to identify the variation of band gap with substitution of different elements are also presented.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Chemical signature characterization with hyperspectral imagery: novel deep learning model architectures and physically-motivated data augmentation techniques

The high spectral resolution afforded by Hyperspectral Imaging (HSI) sensors is poised to bring unprecedented advancements to signature characterization applications. Thus far, much of the research in the machine learning field devoted to HSI applications has focused on a few specific tasks like land-use land-cover classification. In land classification tasks, spatial information is very important, and model architectures are often designed to leverage spatial contexts. However, it is unclear how well these spatially-tuned models will translate to tasks where spectral information is critical, like the detection and characterization of chemicals. In this work, we compare spectral models (inputs are 1D spectra) and spatial-spectral models (inputs are 3D cubes) in the context of predicting chemical concentration maps. We find that spatial-spectral models perform the best, though we find a wide range in performance across the different architectures tested. Additionally, we find that model performance is impacted by the availability of training data, particularly in scenarios where the training data doesn't fully capture the true variance of real-world conditions. We find that data augmentation can help mitigate sparse coverage of observed parameter space (e.g., seasonal or geographic variability in ground cover), and present augmentation strategies that are tailored to hyperspectral data.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2025

RatXcan: A framework for cross-species integration of genome-wide association and gene expression data

Genome-wide association studies (GWAS) have implicated specific alleles and genes as risk factors for numerous complex traits. However, translating GWAS results into biologically and therapeutically meaningful discoveries remains extremely challenging. Most GWAS results identify noncoding regions of the genome, suggesting that differences in gene regulation are the major driver of trait variability. To better integrate GWAS results with gene regulatory polymorphisms, we previously developed PrediXcan (also known as “transcriptome-wide association studies” orTWAS), which maps SNPs to predicted gene expression using GWAS data. In this study, we developed RatXcan, a framework that extends this methodology to outbred heterogeneous stock (HS) rats. RatXcan accounts for the close familial relationships among HS rats by modeling the relatedness with a random effect that encodes the genetic relatedness. RatXcan also corrects for polygenic-driven inflation because of the equivalence between a relatedness random effect and the infinitesimal polygenic model. To develop RatXcan, we trained transcript predictors for 8,934 genes using reference genotype and expression data from five rat brain regions. We found that the cis genetic architecture of gene expression in both rats and humans was sparse and similar across brain tissues. We tested the association between predicted expression in rats and two example traits (body length and BMI) using phenotype and genotype data from 5,401 densely genotyped HS rats and identified a significant enrichment between the genes associated with rat and human body length and BMI. Thus, RatXcan represents a valuable tool for identifying the relationship between gene expression and phenotypes across species and paves the way to explore shared biological mechanisms of complex traits.

Genetics & Heredity↗
DOE OSTI2022

Probabilistic Nanomagnetic Memories for Uncertain and Robust Machine Learning

This project evaluated the use of emerging spintronic memory devices for robust and efficient variational inference schemes. Variational inference (VI) schemes, which constrain the distribution for each weight to be a Gaussian distribution with a mean and standard deviation, are a tractable method for calculating posterior distributions of weights in a Bayesian neural network such that this neural network can also be trained using the powerful backpropagation algorithm. Our project focuses on domain-wall magnetic tunnel junctions (DW-MTJs), a powerful multi-functional spintronic synapse design that can achieve low power switching while also opening the pathway towards repeatable, analog operation using fabricated notches. Our initial efforts to employ DW-MTJs as an all-in-one stochastic synapse with both a mean and standard deviation didn’t end up meeting the quality metrics for hardware-friendly VI. In the future, new device stacks and methods for expressive anisotropy modification may make this idea still possible. However, as a fall back that immediately satisfies our requirements, we invented and detailed how the combination of a DW-MTJ synapse encoding the mean and a probabilistic Bayes-MTJ device, programmed via a ferroelectric or ionically modifiable layer, can robustly and expressively implement VI. This design includes a physics-informed small circuit model, that was scaled up to perform and demonstrate rigorous uncertainty quantification applications, up to and including small convolutional networks on a grayscale image classification task, and larger (Residual) networks implementing multi-channel image classification. Lastly, as these results and ideas all depend upon the idea of an inference application where weights (spintronic memory states) remain non-volatile, the retention of these synapses for the notched case was further interrogated. These investigations revealed and emphasized the importance of both notch geometry and anisotropy modification in order to further enhance the endurance of written spintronic states. In the near future, these results will be mapped to effective predictions for room temperature and elevated operation DW-MTJ memory retention, and experimentally verified when devices become available.

77 NANOSCIENCE AND NANOTECHNOLOGY↗