SEARCH · Engineering Papers
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.
Random forest code for predicting generalists and specialists from gene annotations for the paper "Genomic and ecological factors shaping specialism and generalism across an entire subphylum"
Constructing surrogate models for uncertainty quantification (UQ) on complex partial differential equations (PDEs) having inherently high-dimensional O(10 n ), n ≥ 2, stochastic inputs (e.g., forcing terms, boundary conditions, initial conditions) poses tremendous challenges. The “curse of dimensionality” can be addressed with suitable unsupervised learning techniques used as a pre-processing tool to encode inputs onto lower-dimensional subspaces while retaining its structural information and meaningful properties. In this work, we review and investigate thirteen dimension reduction methods including linear and nonlinear, spectral, blind source separation, convex and non-convex methods and utilize the resulting embeddings to construct a mapping to quantities of interest via polynomial chaos expansions (PCE). Here, we refer to the general proposed approach as manifold PCE (m-PCE), where manifold corresponds to the latent space resulting from any of the studied dimension reduction methods. To investigate the capabilities and limitations of these methods we conduct numerical tests for three physics-based systems (treated as black-boxes) having high-dimensional stochastic inputs of varying complexity modeled as both Gaussian and non-Gaussian random fields to investigate the effect of the intrinsic dimensionality of input data. We demonstrate both the advantages and limitations of the unsupervised learning methods and we conclude that a suitable m-PCE model provides a cost-effective approach compared to alternative algorithms proposed in the literature, including recently proposed expensive deep neural network-based surrogates and can be readily applied for high-dimensional UQ in stochastic PDEs.
Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.
In this paper, we introduce Masked Anomaly Detection (MAD), a general self-supervised learning task for multivariate time series anomaly detection. With the increasing availability of sensor data from industrial systems, being able to detecting anomalies from streams of multivariate time series data is of significant importance. Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned normal representations can empower anomaly detection as the model has learned to capture certain key underlying data regularities. A typical formulation is to learn a predictive model, i.e., use a window of time series data to predict future data values. In this paper, we propose an alternative self-supervised learning task. By randomly masking a portion of the inputs and training a model to estimate them using the remaining ones, MAD is an improvement over the traditional left-to-right next step prediction (NSP) task. Our experimental results demonstrate that MAD can achieve better anomaly detection rates over traditional NSP approaches when using exactly the same neural network (NN) base models, and can be modified to run as fast as NSP models during test time on the same hardware, thus making it an ideal upgrade for many existing NSP-based NN anomaly detection models.
In superconducting magnets, the irreversible transition of a portion of the conductor to resistive state is called a “quench.” Having large stored energy, magnets can be damaged by quenches due to localized heating, high voltage, or large force transients. Unfortunately, current quench protection systems can only detect a quench after it happens, and mitigating risks in Low Temperature Superconducting (LTS) accelerator magnets often requires fast response (down to ms). Additionally, protection of High Temperature Superconducting (HTS) magnets is still suffering from prohibitively slow quench detection. In this study, we lay the groundwork for a quench prediction system using an auto-encoder fully-connected deep neural network. After dynamically trained with data features extracted from acoustic sensors around the magnet, the system detects anomalous events seconds before the quench in most of our data. While the exact nature of the events is under investigation, we show that the system can “forecast” a quench before it happens under magnet training conditions through a randomized experiment. This opens up the way of integrated data processing, potentially leading to faster and better diagnostics and detection of magnet quenches
Medical imaging devices, such as X-ray machines, inherently produce images that suffer from visual noise. Our objectives were to (i.) determine the effect of image denoising on a medical image classification task, and (ii.) determine if there exists a correlation between image denoising performance and medical image classification performance. We performed the medical image classification task on chest X-rays using the DenseNet-121 convolutional neural network (CNN) and used the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics as the image denoising performance measures. We first found that different denoising methods can make a statistically significant difference in classification performance for select labels. We also found that denoising methods affect fine-tuned models more than randomly-initialized models and that fine-tuned models have significantly higher and more uniform performance than randomly-initialized models. Lastly, we found that there is no significant correlation between PSNR and SSIM values and classification performance for our task.
In this work, we present studies of track parameter reconstruction from raw information in CLAS12 detector's Drift Chambers, using Machine Learning (ML). We study the resolution of tracks reconstructed with different types of ML models/algorithms, including Multi-Layer Perceptron (MLP), Extremely Randomized Trees (ERT) and Gradient Boosting Trees (GBT) using simulated data. We find that the resulting ML model is capable of reconstructing track parameters (particle momentum, and polar and azimuthal angles) with accuracy similar to Hit Based (HB) tracking code, but $150$ times faster. Moreover, physics reactions can be identified using the particles reconstructed by the neural network in real-time (with a rate of about $34~kHz$) during experimental data collection. The developed model can be used in numerous applications, such as triggering specific physics reactions in real-time, detector performance monitoring, and real-time detector calibration.
SoilMERGE (SMERGE) is a root-zone soil moisture (RZSM) product that covers the entire continental United States and spans 1978 to 2019. Machine learning techniques, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Gradient Boost (GBoost) downscaled SMERGE to spatial resolutions straddling the field scale domain (100 to 3000 m). Study area was northern Oklahoma and southern Kansas. The coarse resolution of SMERGE (0.125 degree) limits this product’s utility. To validate downscaled results in situ data from four sources were used that included: United States Department of Energy Atmospheric Radiation Measurement (ARM) observatory, United States Climate Reference Network (USCRN), Soil Climate Analysis Network (SCAN), and Soil moisture Sensing Controller and oPtimal Estimator (SoilSCAPE). In addition, RZSM retrievals from NASA’s Airborne Microwave Observatory of Subcanopy and Surface (AirMOSS) campaign provided a nearly spatially continuous comparison. Three periods were examined: era 1 (2016 to 2019), era 2 (2012 to 2015), and era 3 (2003 to 2007). During eras 1 and 2, RF outperformed XGBoost and GBoost, whereas during era 3 no model dominated. Performance was better during eras 1 and 2 as opposed to the pre-L band era 3. Improvements across all eras, regions, and models realized from downscaling included an increase in correlation from 0.03 to 0.42 and a decrease in ub RMSE from -0.0005 to -0.0118 m 3 /m 3 . This study demonstrates the feasibility of SMERGE downscaling opening the prospect for the development of a long-term RZSM dataset at a more desirable field-scale resolution with the potential to support diverse hydrometeorological and agricultural applications.
Here, we introduce an approach for performing quantum state reconstruction on systems of n qubits using a machine learning-based reconstruction system trained exclusively on m qubits, where m ≥ n. This approach removes the necessity of exactly matching the dimensionality of a system under consideration with the dimension of a model used for training. We demonstrate our technique by performing quantum state reconstruction on randomly sampled systems of one, two, and three qubits using machine learning-based methods trained exclusively on systems containing at least one additional qubit. The reconstruction time required for machine learning-based methods scales significantly more favorably than the training time; hence this technique can offer an overall saving of resources by leveraging a single neural network for dimension-variable state reconstruction, obviating the need to train dedicated machine learning systems for each Hilbert space.
Various building loads, such as heating, ventilation, and air conditioners (HVACs), electric water heaters (EWHs), and electric vehicles (EVs), can introduce opportunities for improving the flexibility of electricity consumption while satisfying the needs of building owners as well as benefiting the resilience of distribution system. To utilize such flexibility, a tri-level distribution market framework is established, including residential consumers, load aggregators (LAs), and the distribution system operator (DSO). In this work, the uncertainties from all three levels are considered. The random consumption behavior at the consumer level is modeled as a Gaussian noise that is also aggregated and transmitted to the LA level. The weather temperature in the LA level is forecasted as an interval, and the photovoltaic (PV) power in the market-clearing level is modeled by a set of power scenarios generated by Generative Adversarial Networks (GANs). Then, a hybrid interval-stochastic programming is proposed to transform the uncertain problems in the first two levels into deterministic ones. For real-time implementations, a rolling horizon optimization (RHO) scheme is employed to continuously optimize the power consumption based on the latest operating information. Finally, case studies on a modified IEEE 69-bus system validate the effectiveness of the proposed uncertainty modeling strategies and the RHO scheme.
Power flow forms the basis of many power system studies. With the increased penetration of renewable energy, grid planners tend to perform multiple power flow simulations under various operating conditions and not just selected snapshots at peak or light load conditions. Getting a converged AC power flow (ACPF) case remains a significant challenge for grid planners especially in large power grid networks. This paper proposes a two-stage approach to improve Newton-Raphson ACPF convergence and was applied to a 6102 bus Electric Reliability Council of Texas (ERCOT) system. The first stage utilizes a deep learning-based initializer with data re-training. Here a deep neural network (DNN) initializer is developed to provide better initial voltage magnitude and angle guesses to aid in power flow convergence. This is because Newton-Raphson ACPF is quite sensitive to the initial conditions and bad initialization could lead to divergence. The DNN initializer includes a data re-training framework that improves the initializer's performance when faced with limited training data. The DNN initializer successfully solved 3,285 cases out of 3,899 non-converging dispatch and performed better than random forest and DC power flow initialization methods. ACPF cases not solved in this first stage are then passed through a hot-starting algorithm based on homotopy continuation with switched shunt control. The hot-starting algorithm successfully converged 416 cases out of the remaining 614 non-converging ACPF dispatch. In conclusion, the combined two-stage approach achieved a 94.9% success rate, by converging a total of 3,701 cases out of the initial 3,899 unsolved cases.
WPGNN is the graph neural network machine learning based surrogate model and software that provides a streamlined approximation of wind plant wake models. It can rapidly estimate the energy production of the plant and turbines for any arbitrarily sized wind plant and layout under any inflow condition. Associated tools include graphing and visualization capabilities as well as a wind plant generator capable of creating randomized realizations of canonical wind plant layouts. The WPGNN architecture and application is extendable to multiple wake models, turbine technologies and features, and supports downstream optimizations of wind plant layouts and control strategies. In addition to the WPGNN, we include the code for the plant layout generator (PLayGen) playgen.py. This generator can produce random realizations of realistic wind plant layouts from one of the four canonical styles: cluster, single string, multiple string, or parallel string. The PLayGen_demo.ipynb notebook provides a demonstration of how to use the generator tool.
High-precision calorimeter simulation at current and future colliders imposes rapidly growing computational demands, motivating the development of machine-learning surrogates for traditional Monte Carlo tools such as Geant4. Flow matching and diffusion-based generative models have become leading approaches for high-dimensional fast simulation because of their sample quality, but typically require ${\cal O}(100)$ function evaluations at inference and often rely on auxiliary networks to constrain global observables, compromising streamlined end-to-end generation. We introduce a unified framework that improves the balance between speed, shower quality, and physics fidelity. The method combines: (i) an average velocity field integrator that enables sampling in one or a few evaluations; (ii) a learned generative prior in shower space, constructed from data rather than random noise; and (iii) physics-guided loss terms that impose inductive biases on key observables during training. These elements are training time regularizers, preserving end-to-end inference with no additional cost. With only one or a few evaluation steps, the model achieves shower quality competitive with state-of-the-art flow and diffusion approaches, tested on several public high granularity calorimeter datasets. The results demonstrate inter-layer shower structure consistent with the underlying physics, providing a strong candidate for future fast simulation workflows.
Building electrical load profiles can improve understanding of building energy efficiency, demand flexibility, and building-grid interactions. Current approaches to generating load profiles are time-consuming and not capable of reflecting the dynamic and stochastic behaviors of real buildings; some approaches also trigger data privacy concerns. In this study, we proposed a novel approach for generating realistic electrical load profiles of buildings through the Generative Adversarial Network (GAN), a machine learning technique that is capable of revealing an unknown probability distribution purely from data. The proposed approach has three main steps: (1) normalizing the daily 24-hour load profiles, (2) clustering the daily load profiles with the k-means algorithm, and (3) using GAN to generate daily load profiles for each cluster. The approach was tested with an open-source database – the Building Data Genome Project. We validated the proposed method by comparing the mean, standard deviation, and distribution of key parameters of the generated load profiles with those of the real ones. The KL divergence of the generated and real load profiles are within 0.3 for majority of parameters and clusters. Additionally, results showed the load profiles generated by GAN can capture not only the general trend but also the random variations of the actual electrical loads in buildings. We report the proposed GAN approach can be used to generate building electrical load profiles, verify other load profile generation models, detect changes to load profiles, and more importantly, anonymize smart meter data for sharing, to support research and applications of grid-interactive efficient buildings.
In this work, we investigate and demonstrate the use of convolutional neural networks (CNNs) for the task of distinguishing between merging and non-merging galaxies in simulated images, and for the first time at high redshifts (i.e. $z=2$). We extract images of merging and non-merging galaxies from the Illustris-1 cosmological simulation and apply observational and experimental noise that mimics that from the Hubble Space Telescope; the data without noise form a "pristine" data set and that with noise form a "noisy" data set. The test set classification accuracy of the CNN is $79\%$ for pristine and $76\%$ for noisy. The CNN outperforms a Random Forest classifier, which was shown to be superior to conventional one- or two-dimensional statistical methods (Concentration, Asymmetry, the Gini, $M_{20}$ statistics etc.), which are commonly used when classifying merging galaxies. We also investigate the selection effects of the classifier with respect to merger state and star formation rate, finding no bias. Finally, we extract Grad-CAMs (Gradient-weighted Class Activation Mapping) from the results to further assess and interrogate the fidelity of the classification model.
Abstract Spatial modes of light constitute valuable resources for a variety of quantum technologies ranging from quantum communication and quantum imaging to remote sensing. Nevertheless, their vulnerabilities to phase distortions, induced by random media, impose significant limitations on the realistic implementation of numerous quantum‐photonic technologies. Unfortunately, this problem is exacerbated at the single‐photon level. Over the last two decades, this challenging problem has been tackled through conventional schemes that utilize optical nonlinearities, quantum correlations, and adaptive optics. In this article, the self‐learning and self‐evolving features of artificial neural networks are exploited to correct the complex spatial profile of distorted Laguerre–Gaussian modes at the single‐photon level. Furthermore, the potential of this technique is used to improve the channel capacity of an optical communication protocol that relies on structured single photons. The results have important implications for real‐time turbulence correction of structured photons and single‐photon images.
High entropy oxides (HEOs) have emerged as promising catalysts for several important chemical transformations including alkane activation. Hydrogen adsorption energy (HAE) has been used as a key descriptor for many reactions including methane C–H activation and hydrogen evolution reactions. Hence, understanding the relationship between HAEs and the surface chemistry of HEO surfaces could lay the foundation for meaningful correlations among methane C–H activation, HAE, and the complex, local environment of HEO surfaces. Here, we used a medium-entropy oxide as a prototypical system – Mg 0.25 Ni 0.25 Cu 0.25 Zn 0.25 O with a rock-salt structure – to interrogate these relationships. We sampled 2000 different surfaces of its (100) plane and calculated the HAEs at randomly chosen surface O sites using density functional theory (DFT). Our analysis of the 2000 data points reveals that the HAEs at the surface O sites are significantly influenced by the local environment around the adsorption sites, particularly the nature of the metal atom directly below the surface O site where H adsorbs. After comparing several popular graph-neural-network-based machine learning models, we found that the DimeNet++ model performed best achieving satisfactory accuracy in predicting HAEs for both Mg 0.25 Ni 0.25 Cu 0.25 Zn 0.25 O and slightly varied compositions. Our work underscores the promise of such models and the need for further refinement to address the complexity of HEOs.
Ground-motion time series are essential input data in seismic analysis and performance assessment of the built environment. Because instruments to record free-field ground motions are generally sparse, methods are needed to estimate motions at locations with no available ground-motion recording instrumentation. In this study, given a set of observed motions, ground-motion time series at target sites are constructed using a Gaussian process regression (GPR) approach, which treats the real and imaginary parts of the Fourier spectrum as random Gaussian variables. Model training, verification, and applicability studies are carried out using the physics-based simulated ground motions of the 1906 Mw 7.9 San Francisco earthquake and Mw 7.0 Hayward fault scenario earthquake in northern California. Additionally, the method’s performance is further evaluated using the 2019 Mw 7.1 Ridgecrest earthquake ground motions recorded by the Community Seismic Network stations located in southern California. These evaluations indicate that the trained GPR model is able to adequately estimate the ground-motion time series for frequency ranges that are pertinent for most earthquake engineering applications. The trained GPR model exhibits proper performance in predicting the long-period content of the ground motions as well as directivity pulses.