Search NASA⌕ Search

SEARCH · Search NASA

Results for “sparse data representation”

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 145 records · Page 8

A comparative study of discrete fracture network and equivalent continuum models for simulating flow and transport in the far field of a hypothetical nuclear waste repository in crystalline host rock

One of the major challenges of simulating flow and transport in the far field of a geologic repository in crystalline host rock is related to reproducing the properties of the fracture network over the large volume of rock with sparse fracture characterization data. Various approaches have been developed to simulate flow and transport through the fractured rock. The approaches can be broadly divided into Discrete Fracture Network (DFN) and Equivalent Continuum Model (ECM). The DFN explicitly represents individual fractures, while the ECM uses fracture properties to determine equivalent continuum parameters. In this paper, we compare DFN and ECM in terms of upscaled observed transport properties through generic fracture networks. The major effort was directed on making the DFN and ECM approaches similar in their conceptual representations. This allows for separating differences related to the interpretation of the test conditions and parameters from the differences between the DFN and ECM approaches. The two models are compared using a benchmark test problem that is constructed to represent the far field (1 × 1 × 1 km 3 ) of a hypothetical repository in fractured crystalline rock. The test problem setting uses generic fracture properties that can be expected in crystalline rocks. The models are compared in terms of the: 1) effective permeability of the domain, and 2) nonreactive solute breakthrough curves through the domain. The principal differences between the models are mesh size, network connectivity, matrix diffusion and anisotropy. We demonstrate how these differences affect the flow and transport. Finally, we identify the factors that should be taken in consideration when selecting an approach most suitable for the site-specific conditions.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties

Abstract Identification of a heterogeneous conductivity field and reconstruction of a contaminant release history are key aspects of subsurface remediation. These two goals are achieved by combining model predictions with sparse and noisy hydraulic head and concentration measurements. Solution of this inverse problem is notoriously difficult due to, in part, high dimensionality of the parameter space and high computational cost of repeated forward solves. We use a convolutional adversarial autoencoder (CAAE) to parameterize a heterogeneous non‐Gaussian conductivity field via a low‐dimensional latent representation. A three‐dimensional dense convolutional encoder‐decoder (DenseED) network serves as a forward surrogate of the flow and transport model. The CAAE‐DenseED surrogate is fed into the ensemble smoother with multiple data assimilation (ESMDA) algorithm to sample from the Bayesian posterior distribution of the unknown parameters, forming a CAAE‐DenseED‐ESMDA inversion framework. The resulting CAAE‐DenseED‐ESMDA inversion strategy is used to identify a three‐dimensional contaminant source and conductivity field. A comparison of the inversion results from CAAE‐ESMDA with physical flow and transport simulator and from CAAE‐DenseED‐ESMDA shows that the latter yields accurate reconstruction results at the fraction of the computational cost of the former.

Zhou, Zitong↗

Nonsymmetrized hyperspherical harmonic basis for an A-body system

The use of the hyperspherical harmonic (HH) basis in the description of bound states in an A-body system composed of identical particles is normally preceded by a symmetrization procedure in which the statistic of the system is taken into account. This preliminary step is not strictly necessary; the direct use of the HH basis is possible, even if the basis does not have a well-defined behavior under particle permutations. In fact, after the diagonalization of the Hamiltonian matrix, the eigenvectors reflect the symmetries present in it. They have well-defined symmetry under particle permutation and identification of the physical states is possible, as shown here in specific cases. The problem related to the large degeneration of the basis is circumvented by constructing the Hamiltonian matrix as a sum of products of sparse matrices. This particular representation of the Hamiltonian is well suited for a numerical iterative diagonalization, where only the action of the matrix on a vector is needed. As an example we compute bound states for systems with A=3-6 particles interacting through a short-range central interaction. We also consider the case in which the potential is restricted to act in relative s waves with and without the inclusion of the Coulomb potential. This very simple model predicts results in qualitative good agreement with the experimental data and it represents the first step in a project dedicated to the use of the HH basis to describe bound and low-energy scattering states in light nuclei.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that poses the problem of learning low-dimensional model terms as a regression of state space data and corresponding time derivatives by minimizing the residual of reduced system equations. Standard operator inference models perform well with accurate training data that are dense in time, but producing stable and accurate models when the state data are noisy and/or sparse in time remains a challenge. Another challenge is the lack of uncertainty estimation for the predictions from the operator inference models. Our approach addresses these challenges by incorporating Gaussian process surrogates into the operator inference framework to (1) probabilistically describe uncertainties in the state predictions and (2) procure analytical time derivative estimates with quantified uncertainties. The formulation leads to a generalized least-squares regression and, ultimately, reduced-order models that are described probabilistically with a closed-form expression for the posterior distribution of the operators. The resulting probabilistic surrogate model propagates uncertainties from the observed state data to reduced-order predictions. Furthermore, we demonstrate the method is effective for constructing low-dimensional models of two nonlinear partial differential equations representing a compressible flow and a nonlinear diffusion–reaction process, as well as for estimating the parameters of a low-dimensional system of nonlinear ordinary differential equations representing compartmental models in epidemiology.

Data-driven model reduction↗

Improved Reanalysis and Prediction of Atmospheric Fields Over the Southern Ocean Using Campaign‐Based Radiosonde Observations

Abstract This study investigated the impact of radiosonde observations from the Southern Ocean obtained by the Australian R/V Aurora Australis on the ALERA2 experimental ensemble reanalysis data set and ensemble forecast experiment. An observing system experiment (OSE) that included additional ship‐launched radiosonde data captured the atmospheric structure over the Southern Ocean. ALERA2 without additional radiosondes had positive temperature biases exceeding 7 °C in the upper troposphere when low‐pressure cyclonic systems passed over the ship. The spread in the upper level was reduced by 15% in the OSE, which propagated downstream from the ship's position because of the sparse observing network over southern high latitudes. Comparison of two 63‐member ensemble forecast experiments initialized by ALERA2 and the OSE revealed that prediction of midlatitude cyclone tracks was improved by the realistic representation of upper‐level troughs in the OSE forecast. This confirms that additional radiosondes over the Southern Ocean reduce uncertainty and error in midlatitude cyclone forecasts.

54 ENVIRONMENTAL SCIENCES↗

WE-G-18A-04: 3D Dictionary Learning Based Statistical Iterative Reconstruction for Low-Dose Cone Beam CT Imaging

Purpose: To develop a 3D dictionary learning based statistical reconstruction algorithm on graphic processing units (GPU), to improve the quality of low-dose cone beam CT (CBCT) imaging with high efficiency. Methods: A 3D dictionary containing 256 small volumes (atoms) of 3x3x3 voxels was trained from a high quality volume image. During reconstruction, we utilized a Cholesky decomposition based orthogonal matching pursuit algorithm to find a sparse representation on this dictionary basis of each patch in the reconstructed image, in order to regularize the image quality. To accelerate the time-consuming sparse coding in the 3D case, we implemented our algorithm in a parallel fashion by taking advantage of the tremendous computational power of GPU. Evaluations are performed based on a head-neck patient case. FDK reconstruction with full dataset of 364 projections is used as the reference. We compared the proposed 3D dictionary learning based method with a tight frame (TF) based one using a subset data of 121 projections. The image qualities under different resolutions in z-direction, with or without statistical weighting are also studied. Results: Compared to the TF-based CBCT reconstruction, our experiments indicated that 3D dictionary learning based CBCT reconstruction is able to recover finer structures, to remove more streaking artifacts, and is less susceptible to blocky artifacts. It is also observed that statistical reconstruction approach is sensitive to inconsistency between the forward and backward projection operations in parallel computing. Using high a spatial resolution along z direction helps improving the algorithm robustness. Conclusion: 3D dictionary learning based CBCT reconstruction algorithm is able to sense the structural information while suppressing noise, and hence to achieve high quality reconstruction. The GPU realization of the whole algorithm offers a significant efficiency enhancement, making this algorithm more feasible for potential clinical application. A high zresolution is preferred to stabilize statistical iterative reconstruction. This work was supported in part by NIH(1R01CA154747-01), NSFC((No. 61172163), Research Fund for the Doctoral Program of Higher Education of China (No. 20110201110011), China Scholarship Council.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Efficient Implementation of an Optimal Interpolator for Large Spatial Data Sets

Scattered data interpolation is a problem of interest in numerous areas such as electronic imaging, smooth surface modeling, and computational geometry. Our motivation arises from applications in geology and mining, which often involve large scattered data sets and a demand for high accuracy. The method of choice is ordinary kriging. This is because it is a best unbiased estimator. Unfortunately, this interpolant is computationally very expensive to compute exactly. For n scattered data points, computing the value of a single interpolant involves solving a dense linear system of size roughly n x n. This is infeasible for large n. In practice, kriging is solved approximately by local approaches that are based on considering only a relatively small'number of points that lie close to the query point. There are many problems with this local approach, however. The first is that determining the proper neighborhood size is tricky, and is usually solved by ad hoc methods such as selecting a fixed number of nearest neighbors or all the points lying within a fixed radius. Such fixed neighborhood sizes may not work well for all query points, depending on local density of the point distribution. Local methods also suffer from the problem that the resulting interpolant is not continuous. Meyer showed that while kriging produces smooth continues surfaces, it has zero order continuity along its borders. Thus, at interface boundaries where the neighborhood changes, the interpolant behaves discontinuously. Therefore, it is important to consider and solve the global system for each interpolant. However, solving such large dense systems for each query point is impractical. Recently a more principled approach to approximating kriging has been proposed based on a technique called covariance tapering. The problems arise from the fact that the covariance functions that are used in kriging have global support. Our implementations combine, utilize, and enhance a number of different approaches that have been introduced in literature for solving large linear systems for interpolation of scattered data points. For very large systems, exact methods such as Gaussian elimination are impractical since they require 0(n(exp 3)) time and 0(n(exp 2)) storage. As Billings et al. suggested, we use an iterative approach. In particular, we use the SYMMLQ method, for solving the large but sparse ordinary kriging systems that result from tapering. The main technical issue that need to be overcome in our algorithmic solution is that the points' covariance matrix for kriging should be symmetric positive definite. The goal of tapering is to obtain a sparse approximate representation of the covariance matrix while maintaining its positive definiteness. Furrer et al. used tapering to obtain a sparse linear system of the form Ax = b, where A is the tapered symmetric positive definite covariance matrix. Thus, Cholesky factorization could be used to solve their linear systems. They implemented an efficient sparse Cholesky decomposition method. They also showed if these tapers are used for a limited class of covariance models, the solution of the system converges to the solution of the original system. Matrix A in the ordinary kriging system, while symmetric, is not positive definite. Thus, their approach is not applicable to the ordinary kriging system. Therefore, we use tapering only to obtain a sparse linear system. Then, we use SYMMLQ to solve the ordinary kriging system. We show that solving large kriging systems becomes practical via tapering and iterative methods, and results in lower estimation errors compared to traditional local approaches, and significant memory savings compared to the original global system. We also developed a more efficient variant of the sparse SYMMLQ method for large ordinary kriging systems. This approach adaptively finds the correct local neighborhood for each query point in the interpolation process.

Memarsadeghi, Nargess↗

Detection of Modified Matrix Encoding Using Machine Learning and Compressed Sensing

In recent years, driven by the development of steganalysis methods, steganographic algorithms have been evolved rapidly with the ultimate goal of an unbreakable embedding procedure, resulting in recent steganographic algorithms with minimum distortions, exemplified by the recent family of Modified Matrix Encoding (MME) algorithms, which has shown to be most difficult to be detected. In this paper we propose a compressed sensing based on approach for intrinsic steganalysis to detect MME stego messages. Compressed sensing is a recently proposed mathematical framework to represent an image (in general, a signal) using a sparse representation relative to an overcomplete dictionary by minimizing the l1-norm of resulting coefficients. Here we first learn a dictionary from a training set so that the performance will be optimized using the KSVD algorithm; since JPEG images are processed by 8x8 blocks, the training examples are 8x8 patches, rather than the entire images and this increases the generalization of compressed sensing. For each 8x8 block, we compute its sparse representation using OMP (orthogonal matching pursuit) algorithm. Using computed sparse representations, we train a support vector machine (SVM) to classify 8x8 blocks into stego and non-stego classes. Then given an input image, we first divide it into 8x8 blocks. For each 8x8 block, we compute its sparse representation and classify it using the trained SVM. After all the 8x8 blocks are classified, the entire image is classified based on the majority rule of 8x8 block classification results. This allows us to achieve a robust decision even when 8x8 blocks can be classified only with relatively low accuracy. We have tested the proposed algorithm on two datasets (Corel-1000 dataset and a remote sensing image dataset) and have achieved 100% accuracy on classifying images, even though the accuracy of classifying 8x8 blocks is only 80.89%. Key Words Compressed Sensing, Sparcity, Data Dictionary, Steganography, steganalysis

Allen, Josef D↗

Assimilation of DAWN Doppler Wind Lidar Data During the 2017 Convective Processes Experiment (CPEX): Impact on Precipitation and Flow Structure

An improved representation of 3-D air motion and precipitation structure through forecast models and assimilation of observations is vital for improvements in weather forecasting capabilities. However, there are few independent data to properly validate a model forecast of precipitation structure when the underlying dynamics are evolving on short convective timescales. Using data from the JPL Ku/Ka-band Airborne Precipitation Radar (APR-2) and the 2 μmDoppler Aerosol Wind (DAWN) lidar collected during the2017 Convective Processes Experiment (CPEX), the NASA Unified Weather Research and Forecasting (WRF) Ensemble Data Assimilation System (EDAS) modeling system was used to quantify the impact of high-resolution sparsely sampled DAWN measurements on the analyzed variables and on the forecast when the DAWN winds were assimilated. Over-all, the assimilation of the DAWN wind profiles had a discernible impact on the wind field as well as the evolution and timing of the 3-D precipitation structure. Analysis of individual variables revealed that the assimilation of the DAWN winds resulted in important and coherent modifications of the environment. It led to an increase in the near-surface convergence, temperature, and water vapor, creating more favorable conditions for the development of convection exactly where it was observed (but not present in the control run). Comparison to APR-2 and observations by the Global Precipitation Measurement (GPM) satellite shows a much-improved forecast after the assimilation of the DAWN winds – development of precipitation where there was none, more organized precipitation where there was some, and a much more intense and organized cold pool, similar to the analysis of the dropsonde data. The onset of the vertical evolution of the precipitation showed similar radar-derived cloud-top heights, but delayed in time. While this investigation was limited to a single CPEX flight date, the investigation design is appropriate for further investigation of the impact of airborne Doppler wind lidar observations upon short-term convective precipitation forecasts

DAWN↗

Early Career Award: An Enabling Computational Framework for Uncertainty Assimilation and Propagation in Complex PDE Systems: Sparse and Low-rank Techniques (Final Report)

This project aims to develop a set of new theories, algorithms, and computational tools that enable ultra-scalable representation and propagation of high-dimensional uncertainties to circumvent the issue of curse-of-dimensionality. The research components are motivated by the fact that highly scalable algorithms are needed to achieve exascale performance for uncertainty quantification and predictive simulation at extreme scales. Although these developments are generic and applicable to a wide range of high-dimensional, complex, stochastic, partial-differential-equation (PDE) systems, this research effort will focus on predictive simulation of high-energy-density lithium batteries. To create knowledge about the precise failure mechanisms of these batteries and ultimately predict their performance and reliability, a truly data-driven, multi-scale, multi-physics framework is needed that allows studying (i) dominant sources of uncertainty in the governing physical models at all scales of relevance and (ii) the interface between the interchanging physics and scales. The impact of the planned mathematical and numerical advancements in prediction of high-dimensional uncertain systems will be broad across areas of engineering and science such as climate modeling, fusion energy, combustion, and nanoscience, among others.

97 MATHEMATICS AND COMPUTING↗

Recognition of simple visual images using a sparse distributed memory: Some implementations and experiments

Previously, a method was described of representing a class of simple visual images so that they could be used with a Sparse Distributed Memory (SDM). Herein, two possible implementations are described of a SDM, for which these images, suitably encoded, will serve both as addresses to the memory and as data to be stored in the memory. A key feature of both implementations is that a pattern that is represented as an unordered set with a variable number of members can be used as an address to the memory. In the 1st model, an image is encoded as a 9072 bit string to be used as a read or write address; the bit string may also be used as data to be stored in the memory. Another representation, in which an image is encoded as a 256 bit string, may be used with either model as data to be stored in the memory, but not as an address. In the 2nd model, an image is not represented as a vector of fixed length to be used as an address. Instead, a rule is given for determining which memory locations are to be activated in response to an encoded image. This activation rule treats the pieces of an image as an unordered set. With this model, the memory can be simulated, based on a method of computing the approximate result of a read operation.

Jaeckel, Louis A.↗

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

AIVT: Inference of turbulent thermal convection from measured 3D velocity data by physics-informed Kolmogorov-Arnold networks

We propose the artificial intelligence velocimetry-thermometry (AIVT) method to reconstruct a continuous and differentiable representation of the temperature and velocity in turbulent convection from measured three-dimensional (3D) velocity data. AIVT is based on physics-informed Kolmogorov-Arnold networks and trained by optimizing a loss function that minimizes residuals of the velocity data, boundary conditions, and governing equations. We apply AIVT to a set of simultaneously measured 3D temperature and velocity data of Rayleigh-Bénard convection, obtained by combining particle image thermometry and Lagrangian particle tracking. This enables us to directly compare machine learning results to true volumetric, simultaneous temperature and velocity measurements. We demonstrate that AIVT can reconstruct and infer continuous, instantaneous velocity and temperature fields and their gradients from sparse experimental data at a high resolution, providing an additional approach for understanding thermal turbulence.

Science & Technology - Other Topics↗

Data Mining and Optimization Tools for Developing Engine Parameters Tools

This project was awarded for understanding the problem and developing a plan for Data Mining tools for use in designing and implementing an Engine Condition Monitoring System. From the total budget of $5,000, Tricia and I studied the problem domain for developing ail Engine Condition Monitoring system using the sparse and non-standardized datasets to be available through a consortium at NASA Lewis Research Center. We visited NASA three times to discuss additional issues related to dataset which was not made available to us. We discussed and developed a general framework of data mining and optimization tools to extract useful information from sparse and non-standard datasets. These discussions lead to the training of Tricia Erhardt to develop Genetic Algorithm based search programs which were written in C++ and used to demonstrate the capability of GA algorithm in searching an optimal solution in noisy datasets. From the study and discussion with NASA LERC personnel, we then prepared a proposal, which is being submitted to NASA for future work for the development of data mining algorithms for engine conditional monitoring. The proposed set of algorithm uses wavelet processing for creating multi-resolution pyramid of the data for GA based multi-resolution optimal search. Wavelet processing is proposed to create a coarse resolution representation of data providing two advantages in GA based search: 1. We will have less data to begin with to make search sub-spaces. 2. It will have robustness against the noise because at every level of wavelet based decomposition, we will be decomposing the signal into low pass and high pass filters.

Dhawan, Atam P.↗

Compact video content representation for video coding using low multi-linear tensor rank approximation with dynamic core tensor order

Tensor is a multi-way representation of an entity that is widely used in many applications of mathematics and physics. The wide range of tensor algebra operations attract the researchers of graphical and vision field to identify unique methods for various applications such as segmentation, compression, indexing and so on. In this paper, low multi-linear rank approximation of a tensor is used for decomposition so as to perform compression on a video that is represented as a 4D tensor. Thus, the encoder has blocks for (1) multilinear rank approximation method so as to aid decomposition, (2) sparsity removal of residual data to reduce the required memory storage to a small level, (3) quantization on the sparse less residual data and (4) LZ77 dictionary coding for the video. The decoder uses a tensor reconstruction block along with residual error correction block that reduces loss/error in the reconstructed video. The size of core tensor is an important factor in rank approximation. It is identified at run time depending on the video contents. This size is determined adaptively using Tikhonov’s regularization method. The best value of core tensor size is identified with the corner of L-curve which preserves the video contents from heavy loss/error. Experimental results of the proposed work on comparison with H.264/AVC compression method indicate that the proposed method achieves up to 10% improvement in compression ratio with the least amount of loss and a maximum signal to noise ratio of 0.14. The proposed system gives better compression ratio than H.265 for videos with more number of frames without compromising quality.

97 MATHEMATICS AND COMPUTING↗

Graph theory inspired anomaly detection at the LHC

Designing model-independent anomaly detection algorithms for analyzing LHC data remains a central challenge in the search for new physics, due to the high dimensionality of collider events. In this work, we develop a graph autoencoder as an unsupervised, model-agnostic tool for anomaly detection, using the LHC Olympics dataset as a benchmark. By representing jet constituents as a graph, we introduce a method to systematically control the information available to the model through sparse graph constructions that serve as physically motivated inductive biases. Specifically, (1) we construct graph autoencoders based on locally rigid Laman graphs and globally rigid unique graphs, and (2) we explore the clustering of jet constituents into subjets to interpolate between high- and low-level input representations. We obtain the best performance, measured in terms of the Significance Improvement Characteristic curve for an intermediate level of subjet clustering and certain sparse unique graph constructions. We further investigate the role of graph connectivity in jet classification tasks. Our results demonstrate the potential of leveraging graph-theoretic insights to refine and increase the interpretability of machine learning tools for collider experiments.

Automation↗

Dynamic global vegetation models underestimate net CO 2 flux mean and inter-annual variability in dryland ecosystems

Despite their sparse vegetation, dryland regions exert a huge influence over global biogeochemical cycles because they cover more than 40% of the world surface (Schimel 2010 Science 327 418–9). It is thought that drylands dominate the inter-annual variability (IAV) and long-term trend in the global carbon (C) cycle (Poulter et al 2014 Nature 509 600–3, Ahlstrom et al 2015 Science 348 895–9, Zhang et al 2018 Glob. Change Biol. 24 3954–68). Projections of the global land C sink therefore rely on accurate representation of dryland C cycle processes; however, the dynamic global vegetation models (DGVMs) used in future projections have rarely been evaluated against dryland C flux data. Here, we carried out an evaluation of 14 DGVMs (TRENDY v7) against net ecosystem exchange (NEE) data from 12 dryland flux sites in the southwestern US encompassing a range of ecosystem types (forests, shrub- and grasslands). We find that all the models underestimate both mean annual C uptake/release as well as the magnitude of NEE IAV, suggesting that improvements in representing dryland regions may improve global C cycle projections. Across all models, the sensitivity and timing of ecosystem C uptake to plant available moisture was at fault. Spring biases in gross primary production (GPP) dominate the underestimate of mean annual NEE, whereas models' lack of GPP response to water availability in both spring and summer monsoon are responsible for inability to capture NEE IAV. Errors in GPP moisture sensitivity at high elevation forested sites were more prominent during the spring, while errors at the low elevation shrub and grass-dominated sites were more important during the monsoon. We propose a range of hypotheses for why model GPP does not respond sufficiently to changing water availability that can serve as a guide for future dryland DGVM developments. Our analysis suggests that improvements in modeling C cycle processes across more than a quarter of the Earth's land surface could be achieved by addressing the moisture sensitivity of dryland C uptake.

54 ENVIRONMENTAL SCIENCES↗

Design of Digital Twin Sensing Strategies Via Predictive Modeling and Interpretable Machine Learning

This work develops a methodology for sensor placement and dynamic sensor scheduling decisions for digital twins. The digital twin data assimilation is posed as a classification problem, and predictive models are used to train optimal classification trees that represent the map from observed data to estimated digital twin states. In addition to providing a rapid digital twin updating capability, the resulting classification trees yield an interpretable mathematical representation that can be queried to inform sensor placement and sensor scheduling decisions. The proposed approach is demonstrated for a structural digital twin of a 12 ft wingspan unmanned aerial vehicle. Offline, training data are generated by simulating scenarios using predictive reduced-order models of the vehicle in a range of structural states. Furthermore, these training data can be further augmented using experimental or other historical data. In operation, the trained classifier is applied to observational data from the physical vehicle, enabling rapid adaptation of the digital twin in response to changes in structural health. Within this context, we study the performance of the optimal tree classifiers and demonstrate how they enable explainable structural assessments from sparse sensor measurements and also inform optimal sensor placement.

47 OTHER INSTRUMENTATION↗