Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Learning with errors”

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 1,189 records · Page 66
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

TorbeamNN: machine learning-based steering of ECH mirrors on KSTAR

We have developed TorbeamNN: a machine learning surrogate model for the TORBEAM ray tracing code to predict electron cyclotron heating (ECH) and current drive locations in tokamak plasmas. TorbeamNN provides more than a 100 times speed-up compared to the highly optimized and simplified real-time implementation of TORBEAM without any reduction in accuracy compared to the offline, full fidelity TORBEAM code. The model was trained using KSTAR ECH mirror geometries and works for both O-mode and X-mode absorption. The TorbeamNN predictions have been validated both offline and real-time in experiment. TorbeamNN has been utilized to track an ECH absorption vertical position target in dynamic KSTAR plasmas as well as under varying toroidal mirror angles and with a minimal average tracking error of 0.5 cm.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Deep Learning-enhanced Block-Diagram Modeling of Solar Power Systems

Data-driven models of power system inverter-based resources are desired to run simulations faster than with detailed electromagnetic transient models, to hide proprietary design details, to support control system design applications, and to aggregate the effects of distributed energy resources. This paper applies a customized Hammerstein Wiener framework to train block diagram models from thousands of electromagnetic transient simulations or experimental test records. The block diagram models integrate with larger grid simulations as voltagecontrolled current sources or current-controlled voltage sources for several simulators. Guidelines for block architecture and training are presented. Three-phase balanced, three-phase unbalanced, and single-phase examples all achieve an acceptable root mean square error of no more than 0.05 per-unit.

Mcdermott, Thomas E. [Private consulting company]↗
DOE OSTI2024

Elliptically-Contoured Tensor-variate Distributions with Application to Image Learning

Statistical analysis of tensor-valued data has largely used the tensor-variate normal (TVN) distribution that may be inadequate for data arising from distributions with heavier or lighter tails. We study a general family of elliptically contoured (EC) TV distributions and derive its characterizations, moments, marginal, and conditional distributions. We describe procedures for maximum likelihood estimation from data that are (1) uncorrelated draws from an EC distribution, (2) from a scale mixture of the TVN distribution, and (3) from an underlying but unknown EC distribution, for which we extend Tyler’s robust estimator. A detailed simulation study highlights the benefits of choosing an EC distribution over the TVN for heavier-tailed data. We develop TV classification rules using discriminant analysis and EC errors and show that they better predict cats and dogs from images in the Animal Faces-HQ dataset than the TVN-based rules. A novel tensor-on-tensor regression and TV analysis of variance (TANOVA) framework under EC errors is also demonstrated to better characterize gender, age, and ethnic origin than the usual TVN-based TANOVA in the celebrated labeled faces of the wild dataset.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Idiomatic Correctness-Checking via Julienne in Fortran 2023

This paper presents a unified approach to unit testing and runtime assertion checking using Fortran 2023. The paper describes the support for our approach in the Julienne framework. Julienne leverages recent Fortran standards to implement object-oriented design patterns, support testing parallel programs, and implement functional programming patterns in order to craft idioms inspired by natural-language expressions. The presented idioms employ novel operators to write expressions that evaluate to a test-diagnosis object encapsulating two components: (1) the test outcome or assertion outcome and (2) an automatically generated diagnostic string. Two other novel aspects of the approach include (1) the ability to enforce assertions inside pure procedures and (2) the ability to output rich diagnostic information inside pure procedures during error termination when assertions fail. The latter capability mitigates against a reason that Fortran programmers commonly cite for not writing pure procedures: difficulty obtaining useful program output inside pure procedures when debugging code. This paper demonstrates how the adoption of the proposed idioms leads naturally to a unifying theme across two otherwise disparate technologies: unit testing and runtime assertion checking. Finally, this paper describes the usage of the Julienne testing framework for writing unit tests and assertions in the Matcha high-performance computing application and the Fiats deep learning library.

Rouson, Damian↗
DOE OSTI2024

G2Aero Database of Airfoils - Curated Airfoils

This dataset contains a curated set of 19,164 airfoil shapes from various applications and the data-driven design space of separable shape tensors (PGA space), which can be used as a parameter space for machine-learning applications focused on airfoil shapes. We constructed the airfoil dataset in two main stages. First, we identified 13 baseline airfoils from the NREL 5MW and IEA 15MW reference wind turbines. We reparameterized these shapes using least-squares fits of 8-order CST parametrizations, which involve 18 coefficients. By uniformly perturbing all 18 CST coefficients by +/-20% around each baseline airfoil, we generated 1,000 unique airfoils. Each airfoil was sampled with 1,001 shape landmarks whose x-coordinates followed a cosine distribution along the chord. This process resulted in a total of 13,000 airfoil shapes, each with 1,001 landmarks. In the second phase, we gathered additional airfoils from the extensive BigFoil database, which consolidates data from sources such as the University of Illinois Urbana-Champaign (UIUC) airfoil database, the JavaFoil database, the NACA-TR-824 database, and others. We undertook a thorough pre-processing step to filter out shapes with sparse, noisy, or incomplete data. We also removed airfoils with sharp leading edge and those exceeding our threshold for trailing edge thickness. Additionally, we thinned out the collection of NACA airfoils-- parametric sweeps of NACA airfoils with increasing thickness and camber present in BigFoil database-- by selecting every fourth step in the parameter sweeps. Finally, we regularized the airfoils by reparametrizing them with an 8-order CST parametrization (with 1,001 shape landmarks with x coordinated following cosine distribution along the chord) and removing airfoils with high reconstruction errors. This data pre-processing resulted in a set of 6,164 airfoils. In total, our curated airfoil dataset comprises 19,164 airfoils, each with 1,001 landmarks, and is stored in the curated_airfoils.npz file. Using this curated airfoil dataset, we utilized the separable shape tensors framework to develop a data-driven parameterization of airfoils based on principal geodesic analysis (PGA) of separable shape tensors. This PGA space is provided in PGAspace.npz file.

airfoils↗
DOE OSTI2021

Machine Learning Self-Diffusion Prediction for Lennard-Jones Fluids in Pores

Predicting the diffusion coefficient of fluids under nanoconfinement is important for many applications including the extraction of shale gas from kerogen and product turnover in porous catalysts. Due to the large number of important variables, including pore shape and size, fluid temperature and density, and the fluid–wall interaction strength, simulating diffusion coefficients using molecular dynamics (MD) in a systematic study could prove to be prohibitively expensive. Here, we use machine learning models trained on a subset of MD data to predict the self-diffusion coefficients of Lennard-Jones fluids in pores. Our MD data set contains 2280 simulations of ideal slit pore, cylindrical pore, and hexagonal pore geometries. We use the forward feature selection method to determine the most useful features (i.e., descriptors) for developing an artificial neutral network (ANN) model with an emphasis on easily acquired features. Our model shows good predictive ability with a coefficient of determination (i.e., R 2 ) of ~0.99 and a mean squared error of ~2.9 × 10 –5 . Finally, we propose an alteration to our feature set that will allow the ANN model to be applied to nonideal pore geometries.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Solar Transposition Modeling via Deep Neural Networks With Sky Images

This article presents a notable advance toward the development of a new method of increasing the single-axis tracking photovoltaic (PV) system power output by improving the determination and near-term prediction of the optimum module tilt angle. The tilt angle of the plane receiving the greatest total irradiance changes with Sun position and atmospheric conditions including cloud formation and movement, aerosols, and particulate loading, as well as varying albedo within a module's field of view. In this article, we present a multi-input convolutional neural network that can create a profile of plane-of-array irradiance versus surface tilt angle over a full 180° arc from horizon to horizon. As input, the neural network uses the calculated solar position and clear-sky irradiance values, along with sky images. The target irradiance values are provided by the multiplanar irradiance sensor (MPIS). In order to account for varying irradiance conditions, the MPIS signal is normalized by the theoretical clear-sky global horizontal irradiance. Using this information, the neural network outputs an N -dimensional vector, where N is the number of points to approximate the MPIS curve via Fourier resampling. The output vector of the model is smoothed with a Gaussian kernel to account for error in the downsamping and subsequent upsampling steps, as well as to smooth the unconstrained output of the model. Furthermore, these profiles may be used to perform near-term prediction of angular irradiance, which can then inform the movement of a PV tracker.

42 ENGINEERING↗
DOE OSTI2020

An Applied Strategy for Using Empirical and Hybrid Models in Online Monitoring

The monitoring of plant equipment for failure prediction is one of the key contributors to operation and maintenance (O&M) costs for a nuclear power plant (NPP) because O&M monitoring depends on labor-intensive activities that are required to meet high equipment reliability standards. These activities rely primarily on humans for information gathering, condition diagnosis, and predictive analysis. Online monitoring aims to automate these activities by relying on sensors to replace human information gathering and machine learning to replace human analysis and decision making. To facilitate automated monitoring, a systematic strategy for anomaly detection is needed to optimally use the available sensor data, empirical models, and physics-supported models. This strategy is essential to provide credible reasoning on why and when an empirical (i.e., purely data-driven) versus hybrid (i.e., physics-supported) approach should be used and to determine the ideal mix of these two approaches for a defined anomaly detection scope. The extant methods usually adopt an ad hoc trial-and-error approach that, in addition to being time-consuming and costly, is also highly subjective; it is impacted by the background and the skill set of the personnel making the decisions. Thus, such an approach cannot guarantee an optimum outcome. This represents the motivation of the current research effort, which is focused on devising a scientifically supported strategy for the optimum selection of anomaly detection methods. This report presents a detailed assessment of the main anomaly detection techniques within the empirical or hybrid method streams. Empirical methods include pattern, statistical, and causal inference. Hybrid methods include the use of physics models to train and test data methods, reduce data dimensionality, reduce data-model complexity, augment data, and reduce empirical uncertainty; hybrid methods also include the use of data to tune physics models. The listed techniques within these two streams represent the vast majority of techniques performed for anomaly detection. Using the techniques as outcomes, a strategy was developed to enable a systematic decision-making process to lead to one of these techniques. The strategy is driven by key decision points related to data relevance, simple modeling feasibility, data inference, physics-modeling value, data dimensionality, physics knowledge, method of validation, performance, data availability and suitability for training and testing, cause-effect, entropy inference, and model fitting. Each of these decision points in the strategy is explained in detail in this report with examples, along with the scientific basis behind the decisions and outcomes in common and simplified terminology. The strategy is developed for use by any NPP staff with basic engineering or science knowledge. A user-friendly graphical state flow diagram was also developed as a visual presentation of the strategy. The strategy was tested and demonstrated through two pilot projects for the application of anomaly detection at an NPP. Each pilot had two use cases: an initial case in which certain decisions were made that resulted in one or more empirical techniques and a revised use case where one or more key decisions were modified resulting in using a set of hybrid methods.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

A Beginner's Guide to Power and Energy Measurement and Estimation for Computing and Machine Learning

Concerns about the environmental footprint of machine learning are increasing. While studies of energy use and emissions of ML models are a growing subfield, most ML researchers and developers still do not incorporate energy measurement as part of their work practices. While measuring energy is a crucial step towards reducing carbon footprint, it is also not straightforward. This paper introduces the main considerations necessary for making sound use of energy measurement tools and interpreting energy estimates, including the use of at-the-wall versus on-device measurements, sampling strategies and best practices, common sources of error, and proxy measures. It also contains practical tips and real-world scenarios that illustrate how these considerations come into play. It concludes with a call to action for improving the state of the art of measurement methods and standards for facilitating robust comparisons between diverse hardware and software environments.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Boosting Noise2Inverse via enhanced model selection for denoising computed tomography data

Synchrotron-based x-ray tomographic imaging enables the examination of the internal structure of materials at high spatial and temporal resolution. Experimental constraints can impose dose and time limits on the measurements, introducing a higher level of noise and artifacts in the reconstructed images. Deep learning has emerged as a powerful tool to remove noise from reconstructed images. Recently, the Noise2Inverse method was designed specifically for denoising reconstructed images without requiring paired noisy and clean images. This method creates multiple statistically independent reconstructions used to pair the data in which training involves transforming one reconstruction into the other, and vice versa. Originally designed to be used after a fixed number of epochs, we see in practice that this approach may not produce the optimal model and may unnecessarily waste computational resources. Therefore, we propose an alternative method of identifying the best model during training that aligns with the Noise2Inverse method. During validation, we compare the model output of the multiple reconstructions among each other. We hypothesize that the best model is the one that produces images with the highest similarity, implying a convergence in the predicted material properties and absorption values. To compare model outputs, we consider the absolute error, square error, structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and cosine similarity. We evaluate our method on two simulated tomography datasets and two, real-world, low-contrast, high-energy x-ray tomography datasets. We show our approach is more effective at determining the best model, up to an increase of 12.50% and 12.53% in SSIM and PSNR, respectively, while only requiring a fifth of the training time compared to the original approach.

CT↗
DOE OSTI2025

One Million Open-source Cislunar Orbits

Cislunar space, encompassing the region from geosynchronous orbit to beyond the Moon, is poised to become a cornerstone for future exploration, scientific discovery, and national security. Missions in this region, spanning durations from weeks to decades, require robust infrastructure and reliable transit capabilities. The complex gravitational influences of the Moon, Sun, and planets, along with thermal radiation from Earth and the Sun, lead to significant trajectory deviations, resulting in kilometer-scale errors within days. Leveraging the high-performance computing resources at Lawrence Livermore National Laboratory (LLNL), we have simulated one million high-fidelity cislunar trajectories, now publicly available via LLNL’s Green Data Oasis and the Unified Data Library. Generated using the open-source Space Situational Awareness Python package, these trajectories match the precision of commercial tools such as AGI’s Systems Tool Kit and NASA’s General Mission Analysis Tool. This data set is a valuable resource for reference, statistical analysis of cislunar orbit populations, and training machine learning models for rapid orbit classification with minimal observational input. Preliminary analysis reveals stable bands in Keplerian element space, particularly around five geosynchronous radii across a range of inclinations and eccentricities. Beyond this threshold, the Moon’s influence disrupts most unassisted orbits, though co-orbiting L4/L5 Lunar Trojans persist throughout the six-year simulation.

Astronomy and AstroPhysics↗
DOE OSTI2024

A dynamic solvent chamber propagation estimation framework using RNN for warm solvent injection in heterogeneous reservoirs

Warm solvent injection (WSI), injecting low-temperature solvent into formations to reduce the viscosity of heavy oil, is a clean technology for heavy oil production through reducing greenhouse gas emissions and water usage. The success of WSI operation depends on the uniform development and propagation of solvent chambers in reservoirs. However, reservoir heterogeneity stemming from shale barriers plays a detrimental role in the conformance of solvent chamber development and oil production rate. In this work, we developed a novel recurrent neural network (RNN)-based framework with the capability of efficiently tracking and estimating the solvent chamber positions in heterogeneous reservoirs based on only production time-series data. The developed estimation model utilizes the “sequence-to-sequence" mapping methodology to correlate observed production time-series sequence and solvent chamber edge sequence via a long short-term memory (LSTM) algorithm. The trained RNN models exhibit high accuracy, evidenced by the predicted dynamic solvent chamber locations match the corresponding true locations from numerical simulation, with a high coefficient of determination (R 2 ) and a low mean squared error. Specifically, the achieved R 2 values exceed 0.98 on both the training and testing data. The developed RNN-based workflow was tested via several cases from both regularly- and irregularly-shaped shale barriers, and the results were promising. The predicted solvent chambers showed strong agreement with those obtained from numerical simulations. The major benefits of this workflow include reducing computational time and saving overall monitoring and tracking costs for conventional techniques. In conclusion, the present work would provide a good demonstration of the capability of practical integration of machine learning methods in solving engineering problems.

58 GEOSCIENCES↗
DOE OSTI2022

Epidural anesthesia needle guidance by forward-view endoscopic optical coherence tomography and deep learning

Epidural anesthesia requires injection of anesthetic into the epidural space in the spine. Accurate placement of the epidural needle is a major challenge. To address this, we developed a forward-view endoscopic optical coherence tomography (OCT) system for real-time imaging of the tissue in front of the needle tip during the puncture. We tested this OCT system in porcine backbones and developed a set of deep learning models to automatically process the imaging data for needle localization. A series of binary classification models were developed to recognize the five layers of the backbone, including fat, interspinous ligament, ligamentum flavum, epidural space, and spinal cord. The classification models provided an average classification accuracy of 96.65%. During puncture, it is important to maintain a safe distance between the needle tip and the dura mater. Regression models were developed to estimate that distance based on the OCT imaging data. Based on the Inception architecture, our models achieved a mean absolute percentage error of 3.05% ± 0.55%. Overall, our results validated the technical feasibility of using this novel imaging strategy to automatically recognize different tissue structures and measure the distances ahead of the needle tip during the epidural needle placement.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

On the estimation of boundary layer heights: a machine learning approach

Abstract. The planetary boundary layer height (zi) is a key parameter used in atmospheric models for estimating the exchange of heat, momentum, and moisture between the surface and the free troposphere. Near-surface atmospheric and subsurface properties (such as soil temperature, relative humidity, etc.) are known to have an impact on zi. Nevertheless, precise relationships between these surface properties and zi are less well known and not easily discernible from the multi-year dataset. Machine learning approaches, such as random forest (RF), which use a multi-regression framework, help to decipher some of the physical processes linking surface-based characteristics to zi. In this study, a 4-year dataset from 2016 to 2019 at the Southern Great Plains site is used to develop and test a machine learning framework for estimating zi. Parameters derived from Doppler lidars are used in combination with over 20 different surface meteorological measurements as inputs to a RF model. The model is trained using radiosonde-derived zi values spanning the period from 2016 through 2018 and then evaluated using data from 2019. Results from 2019 showed significantly better agreement with the radiosonde compared to estimates derived from a thresholding technique using Doppler lidars only. Noteworthy improvements in daytime zi estimates were observed using the RF model, with a 50 % improvement in mean absolute error and an R2 of greater than 85 % compared to the Tucker method zi. We also explore the effect of zi uncertainty on convective velocity scaling and present preliminary comparisons between the RF model and zi estimates derived from atmospheric models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Scalability analysis of heavy-duty gas turbines using data-driven machine learning

With the increasing integration of variable renewable energy sources into power systems, the role of flexible power generation technologies like gas turbines (GT) in rapid grid balancing remains crucial. This sustained importance underscores the need for scaled and precise modeling of GT to ensure effective integration within evolving energy frameworks. While physics-driven GT models integrate thermodynamics, fluid dynamics, and combustion principles, they often rely on approximate mathematical representations to accommodate scaling that may not capture the actual complex dynamics for GTs and inertial effects associated to GTs with different ratings. In this study, a data-driven model is proposed using machine learning (ML) techniques to conduct GT scalability analysis and performance evaluation with high accuracy. The ML model, trained on data from various operating conditions and performance parameters, aims to uncover intricate relationships and patterns, resembling GT characteristics at different scales (ratings). The model is developed to capture complex system interaction and to adapt to changing operational scenarios at different capacities, providing valuable insights of power system dynamics. In this study, the real-time digital simulator platform was employed to generate training data for the ML model and assess its dynamic characteristics. The ultimate objective was to develop a detailed modeling framework based on governing equations and data-driven ML capable of predicting key performance indicators, in thermal systems such as GTs, including power output, speed, fuel consumption, and exhaust temperature under diverse operating conditions at different scales. The developed ML framework demonstrated high accuracy, with mean relative errors for GT power prediction, reference speed, exhaust temperature, and compressor pressure ratio (CPR) parameters consistently below 0.1% across typical load fluctuation scenarios. Maximum deviations were limited to approximately 0.5 K for exhaust temperature and 0.009 for CPR, underscoring the model’s ability to replicating dynamic GT behavior with high precision. The adaptability of the ML model enables its application across diverse operational conditions and its extension to other thermal systems. By leveraging advanced ML techniques, this study presents a robust and scalable modeling framework that enhances GT simulation precision, facilitating improved integration into evolving power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Efficient Bayesian inference with latent Hamiltonian neural networks in No-U-Turn Sampling

When sampling for Bayesian inference, one popular approach in the computational field is to use Hamiltonian Monte Carlo (HMC) and specifically the No-U-Turn Sampler (NUTS), which automatically decides the end time of the Hamiltonian trajectory. However, HMC and NUTS can require numerous numerical gradients of the target density and can prove slow in practice when relying on computationally expensive forward models. We propose Latent Hamiltonian neural networks (L-HNNs) with HMC and NUTS for solving Bayesian inference problems. Once trained, L-HNNs do not require numerical gradients of the target density during sampling, and hence numerous evaluations of the forward computational model. Moreover, L-HNNs satisfy important properties such as perfect time reversibility and Hamiltonian conservation, making them well-suited for use within HMC and NUTS because stationarity can be shown. We also propose the integration of L-HNNs in an online error monitoring scheme, in which numerical gradients of the target density are used for a few samples whenever the L-HNNs prediction errors are large. This online error monitor scheme prevents sample degeneracy in regions of low probability density and ensures robust uncertainty quantification. We demonstrate L-HNNs in NUTS with online error monitoring on several analytical examples involving complex, heavy-tailed, and high-local-curvature probability densities. We then demonstrate the applicability of L-HNNs in NUTS to two computational case studies, namely the Allen-Cahn stochastic partial differential equation and an elliptic partial differential equation with 25 and 50 inference parameters, respectively. Overall, the L-HNNs in NUTS with online error monitoring satisfactorily inferred these probability densities. In conclusion, compared to traditional NUTS, L-HNNs in NUTS with online error monitoring required 1–2 orders of magnitude fewer numerical gradients of the target density and improved the effective sample size (ESS) per gradient (which is a measure of both the sampling quality and the computational expense) by an order of magnitude.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

CAN-D: A Modular Four-Step Pipeline for Comprehensively Decoding Controller Area Network Data

Controller area networks (CANs) are a broadcast protocol for real-time communication of critical vehicle subsystems. Original equipment manufacturers of passenger vehicles hold secret their mappings of CAN data to vehicle signals, and these definitions vary according to make, model, and year. Without these mappings, the wealth of real-time vehicle information hidden in the CAN packets is uninterpretable, severely impeding vehicle-related research, including CAN cybersecurity and privacy studies, aftermarket tuning, efficiency and performance monitoring, and fault diagnosis to name a few. Guided by the four-part CAN signal definition, we present CAN-D (CAN-Decoder), a modular, four-step pipeline for identifying each signal's boundaries (start bit and length), endianness (byte ordering), signedness (bit-to-integer encoding), and by leveraging diagnostic standards, augmenting a subset of the extracted signals with meaningful, physical interpretation. En route to CAN-D, we provide a comprehensive review of the CAN signal reverse engineering research. All previous methods ignore endianness and signedness, rendering them incapable of decoding many standard CAN signal definitions. Incorporating endianness grows the search space from 128 to 4.72E21 signal tokenizations and introduces a web of changing dependencies. In response, we formulate, formally analyze, and provide an efficient solution to an optimization problem, allowing identification of the optimal set of signal boundaries and byte orderings. In addition, we provide two novel, state-of-the-art signal boundary classifiers—both of which are superior to previous approaches in precision and recall in three different test scenarios—and the first signedness classification algorithm, which exhibits a $>$ 97% F-score. Altogether, CAN-D is the only solution with the potential to extract any CAN signal that is also the state of the art. In evaluation on 10 vehicles of different makes, CAN-D's average $\ell ^1$ error is five times better (81% less) than all previous methods and exhibits lower average error, even when considering only signals that meet prior methods’ assumptions. Finally, CAN-D is implemented in lightweight hardware, allowing for an on-board diagnostic (OBD-II) plugin for real-time in-vehicle CAN decoding.

42 ENGINEERING↗
DOE OSTI2023

Fabrication-conscious neural network based inverse design of single-material variable-index multilayer films

Multilayer films with continuously varying indices for each layer have attracted great deal of attention due to their superior optical, mechanical, and thermal properties. However, difficulties in fabrication have limited their application and study in scientific literature compared to multilayer films with fixed index layers. In this work we propose a neural network based inverse design technique enabled by a differentiable analytical solver for realistic design and fabrication of single material variable-index multilayer films. This approach generates multilayer films with excellent performance under ideal conditions. We furthermore address the issue of how to translate these ideal designs into practical useful devices which will naturally suffer from growth imperfections. By integrating simulated systematic and random errors just as a deposition tool would into the optimization process, we demonstrated that the same neural network that produced the ideal device can be retrained to produce designs compensating for systematic deposition errors. Furthermore, the proposed approach corrects for systematic errors even in the presence of random fabrication imperfections. The results outlined in this paper provide a practical and experimentally viable approach for the design of single material multilayer film stacks for an extremely wide variety of practical applications with high performance.

36 MATERIALS SCIENCE↗