Search NASA⌕ Search

SEARCH · Search NASA

Results for “Recurrent Neural Networks”

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 289 records · Page 16

The HEP.TrkX Project: Deep Learning for Particle Tracking

Charged particle reconstruction in dense environments, such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms, such as the combinatorial Kalman Filter, have been used with great success in HEP experiments for years. However, these state-of-the-art techniques are inherently sequential and scale quadratically or worse with increased detector occupancy. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as FPGAs or GPUs. In this paper we present the evolution and performance of our recurrent (LSTM) and convolutional neural networks moving from basic 2D models to more complex models and the challenges of scaling up to realistic dimensionality/sparsity.

Tsaris, Aristeidis↗

Real-time biomass feedstock particle quality detection using image analysis and machine vision

Abstract A common and costly challenge in the nascent biorefinery industry is the consistent handling and conveyance of biomass feedstock materials, which can vary widely in their chemical, physical, and mechanical properties. Solutions to cope with varying feedstock qualities will be required, including advanced process controls to adjust equipment and reject feedstocks that do not meet a quality standard. In this work, we present and evaluate methods to autonomously assess corn stover feedstock quality in real time and provide data to process controls with low-cost camera hardware. We explore the use of neural networks to classify feedstocks based on actual processing behavior and pixel matrix feature parameterization to further assess particle attributes that may explain the variable processing behavior. We used the pretrained ResNet neural network coupled with a gated recurrent unit (GRU) time-series classifier trained on our image data, resulting in binary classification of feedstock anomalies with favorable performance. The textural aspects of the image data were statistically analyzed to determine if the textural features were predictive of operational disruptions. The significant textural features were angular second moment, prominence, mean height of surface profile, mean resultant vector, shade, skewness, variation of the polar facet orientation, and direction of azimuthal facets. Expansion of these models is recommended across a wider variety of labeled feedstock images of different qualities and species to develop a more robust tool that may be deployed using low-cost cameras within biorefineries.

09 BIOMASS FUELS↗

A Medium‐Sized Paleo‐Tsunami Reconstruction by a Deep Neural Network Processing Sedimentary Deposits

Abstract Reconstructing the magnitude and recurrence time of tsunamis, one of the most destructive and unpredictable natural hazards impacting coastal communities, is essential. While major tsunamis are the most studied due to their disastrous impact, small/medium tsunamis (SMTs) are much more frequent and can still significantly impact the coast. Therefore, SMTs potentially provide an extensive archive of information preserved in the geological record. Analyzing the deposits of small/medium paleo‐tsunamis (SMPTs) opens a window into when their direct observation was unavailable. However, deposits of SMPTs are often degraded, traditional sediment deposition inversion models might fail. Recent research has shown that Deep Neural Networks (DNN) can effectively reconstruct the flow conditions of major tsunamis from their deposits. We evaluate the effectiveness of this approach in reconstructing the characteristics of a recent medium size tsunami (2006 Java) and of a medium paleo‐tsunami (1929 Grand Banks). We successfully reconstruct the flow characteristics of the 2006 Java event and show that an inversion of comparable quality is possible for the 1929 Grand Banks tsunami, despite greater uncertainties due to the deposit degradation. Our research shows that Machine Learning has the potential to unseal the meaning of data of thousands SMPTs.

Batubo, P.↗

Transformer Neural Networks with Spatiotemporal Attention for Predictive Control and Optimization of Industrial Processes

In the context of real-time optimization and model predictive control of industrial systems, machine learning, and neural networks represent cutting-edge tools that hold promise for enhancing dynamic modeling. This work presents a novel transformer neural network architecture for real-time optimization and model predictive control. This network design includes a modified attention mechanism inspired by positional embedding attention from vision transformers and task-specific modifications to the input-output structure of the transformer’s decoder stack. Experiments were conducted using data from a 450 MW coal-fired power plant to evaluate this approach's effectiveness. The transformer neural network was compared with conventional recurrent models, including GRU and LSTM. The transformer exhibited a 6% increase in the R-squared (R2) value of predictions and an 83% reduction in mean squared error (MSE). Computation time was also reduced by 84% compared to conventional recurrent models.

Gallup, Ethan R.↗

SU-E-J-254: Evaluating the Role of Mid-Treatment and Post-Treatment FDG-PET/CT in Predicting Progression-Free Survival and Distant Metastasis of Anal Cancer Patients Treated with Chemoradiotherapy

Purpose: To evaluate the role of mid-treatment and post-treatment FDG-PET/CT in predicting progression-free survival (PFS) and distant metastasis (DM) of anal cancer patients treated with chemoradiotherapy (CRT). Methods: 17 anal cancer patients treated with CRT were retrospectively studied. The median prescription dose was 56 Gy (range, 50–62.5 Gy). All patients underwent FDG-PET/CT scans before and after CRT. 16 of the 17 patients had an additional FDG-PET/CT image at 3–5 weeks into the treatment (denoted as mid-treatment FDG-PET/CT). 750 features were extracted from these three sets of scans, which included both traditional PET/CT measures (SUVmax, SUVpeak, tumor diameters, etc.) and spatialtemporal PET/CT features (comprehensively quantify a tumor’s FDG uptake intensity and distribution, spatial variation (texture), geometric property and their temporal changes relative to baseline). 26 clinical parameters (age, gender, TNM stage, histology, GTV dose, etc.) were also analyzed. Advanced analytics including methods to select an optimal set of predictors and a model selection engine, which identifies the most accurate machine learning algorithm for predictive analysis was developed. Results: Comparing baseline + mid-treatment PET/CT set to baseline + posttreatment PET/CT set, 14 predictors were selected from each feature group. Same three clinical parameters (tumor size, T stage and whether 5-FU was held during any cycle of chemotherapy) and two traditional measures (pre- CRT SUVmin and SUVmedian) were selected by both predictor groups. Different mix of spatial-temporal PET/CT features was selected. Using the 14 predictors and Naive Bayes, mid-treatment PET/CT set achieved 87.5% accuracy (2 PFS patients misclassified, all local recurrence and DM patients correctly classified). Post-treatment PET/CT set achieved 94.0% accuracy (all PFS and DM patients correctly predicted, 1 local recurrence patient misclassified) with logistic regression, neural network or support vector machine model. Conclusion: Applying radiomics approach to either midtreatment or post-treatment PET/CT could achieve high accuracy in predicting anal cancer treatment outcomes. This work was supported in part by the National Cancer Institute Grant R01CA172638.

60 APPLIED LIFE SCIENCES↗

Improving Subsurface Stress Characterization for Carbon Dioxide Storage Projects by Incorporating Machine Learning Techniques

The overall objective of this project is to develop a framework for reliable characterization and prediction of the state of stress in the overburden and underburden (including the basement) in CO 2 storage reservoirs using machine learning and integrated geomechanics and geophysical methods. Specifically, we propose to develop workflow encompassing of technologies and/or methods to predict stress and pressure changes due to CO 2 injection in an active tertiary recovery site and their impacts on subtle fault activation, fractures and occurrence of microseismic events and compare responses to field observations. In this project, we anticipate using dataset from the Farnsworth field Unit (FWU) which is operated by Purdure Petroleum. A novel elastic-waveform VSP inversion technique will be used to estimate high-resolution spatial and temporal changes of elastic moduli in CO 2 storage reservoirs, which will be combined with velocity-stress relationship derived from laboratory tests to obtain subsurface pressure and stress. Clustered microseismic data will be jointly inverted for improved focal mechanisms. Least-squares reverse-time migration of microseismic waveform data will be performed to directly image fracture/fault zones. Additionally, a deep neural network machine learning technique with convolutional and recurrent layers will be used for learning the spectro-temporal structures in microseismic waveforms. The results of this geotechnical data analysis will be integrated to develop a high-resolution 3D mechanical earth model extending from the overburden sealing formations to the underburden including the basement. Mechanical properties will be derived through integration of mechanical logs, tests, available results from chemo-mechanical laboratory tests, and elastic inversion of seismic data using a combination of Bayesian and stochastic methods as well as machine learning technique. Failure features (faults/fractures) will be represented and/or modeled based on seismic and core data analysis. A transient hydrodynamic-geomechanical model will be developed through coupling with the calibrated FWU reservoir simulation model. The full physics coupled model will be used to train a reduced order proxy model using machine learning algorithm for estimating stress which will then be used with appropriate constitutive relationships and forward seismological models to simulate pressure changes and induced microseismicity. An advanced optimization framework will be developed to perform a history match to minimize error between field observations and simulated. The history matched proxy model will be verified against the full-physics equivalent. The field observations that will be used in the coupled model calibration process include pressure/stress inverted from VSP, moment magnitude from microseismic analysis, real time downhole pressure measurements, production and injection data. Parameter sensitivity and uncertainty analysis will be performed to characterize the impact of model parameter uncertainty on stress estimates. The proposed project will have significant impact on future field implementation of the proposed technology. Because the project field site is an ongoing CO 2 EOR development, the value of the new technology will be demonstrated in an operational context and evaluated as a viable risk mitigation strategy. Cost/benefit will be evaluated together with the various commercial incentives for CO 2 sequestration available to oil and gas operators. The extensive available dataset and ongoing data acquisition under the SWP Phase III work plan provides flexibility for investigation of multiple approaches and reduces technical risk.

58 GEOSCIENCES↗

On Neural Architectures for Astronomical Time-series Classification with Application to Variable Stars

Despite the utility of neural networks (NNs) for astronomical time-series classification, the proliferation of learning architectures applied to diverse data sets has thus far hampered a direct intercomparison of different approaches. Here we perform the first comprehensive study of variants of NN-based learning and inference for astronomical time series, aiming to provide the community with an overview on relative performance and, hopefully, a set of best-in-class choices for practical implementations. In both supervised and self-supervised contexts, we study the effects of different time-series-compatible layer choices, namely the dilated temporal convolutional neural network (dTCNs), long-short term memory NNs, gated recurrent units and temporal convolutional NNs (tCNNs). Additionally, we also study the efficacy and performance of encoder-decoder (i.e., autoencoder) networks compared to direct classification networks, different pathways to include auxiliary (non-time-series) metadata, and different approaches to incorporate multi-passband data (i.e., multiple time series per source). Performance—applied to a sample of 17,604 variable stars (VSs) from the MAssive Compact Halo Objects (MACHO) survey across 10 imbalanced classes—is measured in training convergence time, classification accuracy, reconstruction error, and generated latent variables. We find that networks with recurrent NNs generally outperform dTCNs and, in many scenarios, yield to similar accuracy as tCNNs. In learning time and memory requirements, convolution-based layers perform better. We conclude by discussing the advantages and limitations of deep architectures for VS classification, with a particular eye toward next-generation surveys such as the Legacy Survey of Space and Time, the Roman Space Telescope, and Zwicky Transient Facility.

79 ASTRONOMY AND ASTROPHYSICS↗

Data source authentication of synchrophasor measurement devices based on 1D-CNN and GRU

Synchrophasor measurement devices (SMDs) have been widely deployed to support real-time monitoring and control of power systems. In the meantime, data spoofing has emerged in recent years. Therefore, it is of great importance to study data authentication algorithms for detecting and defending the data spoofing effectively. Here, a one-dimensional convolutional neural network (1D-CNN) is utilized to extract temporal signatures hidden in frequency, voltage angle and amplitude data; then the gated recurrent unit (GRU) employs these temporal signatures for data source authentication. In case studies, the performances of different algorithms are tested in large-scale power systems with numerous SMDs for the first time, and comparisons among different algorithms show that the proposed algorithm can achieve a higher accuracy of data source authentication with a shorter time window.

47 OTHER INSTRUMENTATION↗

Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints

Subsurface nuclear magnetic resonance (NMR) logs acquired in the wellbore environment are sensitive to fluid-filled pore size distribution, fluid mobility, permeability, and porosity in the near-wellbore reservoir volume. NMR response of a formation layer is processed to extract the T2 distribution, which approximates the fluid-filled pore size distribution. NMR logs are acquired in limited number of wells due to financial and operational challenges, which adversely affects reservoir characterization. We developed here two neural-network-based machine learning techniques, long short-term memory (LSTM) network and variational autoencoder with a convolutional layer (VAEc) network, to process the ‘easy-to-acquire’ formation mineral and fluid saturation logs to generate synthetic NMR T2 distributions in the absence of ‘hard-to-acquire’ NMR T2 distribution log. Both the predictive models are trained and tested on limited wireline log measurements randomly selected from a 300-ft depth interval of the Bakken shale formation. Synthesis performances of LSTM and VAEc models in terms of R 2 are 0.78 and 0.75, respectively. Noise is inevitable in logging data due to the complex wellbore and formation conditions. Notably, both the predictive models robustly synthesize the fluid-filled pore size distributions in the presence of 50% noise in input logs and 30% noise in training T2 data. The performance of the proposed methodology improves with access to larger volume of training data from other formation types. The proposed method is critical to the synthesis of in situ fluid-filled pore size distributions in shale formations under data constraints due to financial and operational challenges.

58 GEOSCIENCES↗

Quantitative assessment of distant recurrence risk in early stage breast cancer using a nonlinear combination of pathological, clinical and imaging variables

Abstract Use of genomic assays to determine distant recurrence risk in patients with early stage breast cancer has expanded and is now included in the American Joint Committee on Cancer staging manual. Algorithmic alternatives using standard clinical and pathology information may provide equivalent benefit in settings where genomic tests, such as OncotypeDx, are unavailable. We developed an artificial neural network (ANN) model to nonlinearly estimate risk of distant cancer recurrence. In addition to clinical and pathological variables, we enhanced our model using intraoperatively determined global mammographic breast density (MBD) and local breast density (LBD). LBD was measured with optical spectral imaging capable of sensing regional concentrations of tissue constituents. A cohort of 56 ER+ patients with an OncotypeDx score was evaluated. We demonstrated that combining MBD/LBD measurements with clinical and pathological variables improves distant recurrence risk prediction accuracy, with high correlation ( r = 0.98) to the OncotypeDx recurrence score.

Nichols, Brandon S.↗

Improving Monsoon Precipitation Prediction Using Combined Convolutional and Long Short Term Memory Neural Network

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for the monsoon region. We develop a deep neural network composed of a convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against the GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including (1) quantile mapping, (2) the support vector machine, and (3) the convolutional neural network. To test the robustness of the model and its applicability in practical forecasting, we apply the trained network for precipitation prediction forced by retrospective forecasts from the ECMWF model. Compared to the ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead times from 1 day up to 2 weeks. This superiority decreases with the forecast lead time, as the GCM’s skill in predicting atmospheric dynamics is diminished by the chaotic effect. Finally, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is only slightly worse than the observed precipitation forced simulation (NSE = 0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

54 ENVIRONMENTAL SCIENCES↗

Keras2c: A library for converting Keras neural networks to real-time compatible C

With the growth of machine learning models and neural networks in measurement and control systems comes the need to deploy these models in a way that is compatible with existing systems. Existing options for deploying neural networks either introduce very high latency, require expensive and time consuming work to integrate into existing code bases, or only support a very limited subset of model types. We have therefore developed a new method called Keras2c, which is a simple library for converting Keras/TensorFlow neural network models into real-time compatible C code. It supports a wide range of Keras layers and model types including multidimensional convolutions, recurrent layers, multi-input/output models, and shared layers. Keras2c re-implements the core components of Keras/TensorFlow required for predictive forward passes through neural networks in pure C, relying only on standard library functions considered safe for real-time use. The core functionality consists of ~ 1500 lines of code, making it lightweight and easy to integrate into existing codebases. Keras2c has been successfully tested in experiments and is currently in use on the plasma control system at the DIII-D National Fusion Facility at General Atomics in San Diego.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

The TENNLab Suite of LIDAR-Based Control Applications for Recurrent, Spiking, Neuromorphic Systems

Recurrent, spiking neuromorphic systems (RSNS’s) have several desirable features compared to conventional neural networks when applied to applications that require real-time control. The TENNLab Exploratory Neuromorphic Computing Framework contains a variety of real-time control applications that use LIDAR for input, and allow a trained RSNS to make real-time decisions for navigation, surveillance and targeting. While each application is interesting on its own, the collection of applications is very useful for benchmarking RSNS’ s, evaluating training algorithms, and designing neuromorphic processing elements. In this paper, we describe the applications that compose the suite, and use them to benchmark four different RSNS’s.

Plank, James↗

GRUMDN: A Multi-Task Model for Predicting Human Patterns-of-Life from Stay Transition Data

Understanding human patterns-of-life (PoL) is essential towards ensuring safe and secure indoor facility environment as well as outdoor urban environment. Prediction of human movement in between places of interest is vital in understanding human PoL. Movement between spaces maybe represented and detected in one of the two forms: 1) trajectories: locations measured at regular time intervals by mobile sensors, bluetooth or GPS sensors; or 2) stay transitions: semantic PoI (points of interest) and stay duration data measurable by eventbased sensors that collect data when a check-in or check-out event is detected. Stay transition data provides a more compressed data format compared to trajectories data, especially in situations with longer stay durations, while preserving the information necessary for PoL analysis. Now as introduced briefly in the paper, our deployed end application (Digital Twin of a facility with non-player characters, besides the interactive user in virtual reality) needed a well-performing and validated AI/ML model for simulating high quality stay transitions behavior. In this study we thus primarily present our findings with developing and validating that model, which is a multi-task neural network for stay transition prediction. The neural network consists of two heads, for corresponding two tasks of stay category prediction and stay duration prediction. We evaluated gated recurrent units and multi-layer perceptrons of varying network sizes for stay category prediction; while mixture density networks, noisy generator-only networks, and generative adversarial networks of varying network sizes for stay duration prediction. We have then evaluated four multi-task models, constructed by combining these specialized models, on their ability to predict stay transition data. We tested our models on datasets from two different cases: 1) a simulation-generated dataset of indoor movement within the HFIR (high flux isotope reactor) nuclear reactor facility at Oak Ridge National Laboratory (ORNL); and 2) the GeoLife human mobility dataset of outdoor urban movement available in literature. Our results indicate that GRUMDN, which combines gated recurrent units (GRU) for stay category prediction task, and mixture density networks (MDN) for stay duration prediction task, did overall outperform other multitask models and the current state-of-the-art.

Gunaratne, Chathika [ORNL] (ORCID:0000000225088745↗

SU-E-T-206: Improving Radiotherapy Toxicity Based On Artificial Neural Network (ANN) for Head and Neck Cancer Patients

Purpose/Objective(s): The aim of this study is to build the estimator of toxicity using artificial neural network (ANN) for head and neck cancer patients Materials/Methods: An ANN can combine variables into a predictive model during training and considered all possible correlations of variables. We constructed an ANN based on the data from 73 patients with advanced H and N cancer treated with external beam radiotherapy and/or chemotherapy at our institution. For the toxicity estimator we defined input data including age, sex, site, stage, pathology, status of chemo, technique of external beam radiation therapy (EBRT), length of treatment, dose of EBRT, status of post operation, length of follow-up, the status of local recurrences and distant metastasis. These data were digitized based on the significance and fed to the ANN as input nodes. We used 20 hidden nodes (for the 13 input nodes) to take care of the correlations of input nodes. For training ANN, we divided data into three subsets such as training set, validation set and test set. Finally, we built the estimator for the toxicity from ANN output. Results: We used 13 input variables including the status of local recurrences and distant metastasis and 20 hidden nodes for correlations. 59 patients for training set, 7 patients for validation set and 7 patients for test set and fed the inputs to Matlab neural network fitting tool. We trained the data within 15% of errors of outcome. In the end we have the toxicity estimation with 74% of accuracy. Conclusion: We proved in principle that ANN can be a very useful tool for predicting the RT outcomes for high risk H and N patients. Currently we are improving the results using cross validation.

60 APPLIED LIFE SCIENCES↗

Integrated Genomic Analysis Identifies Clinically Relevant Subtypes of Glioblastoma Characterized by Abnormalities in PDGFRA, IDH1, EGFR, and NF1

The Cancer Genome Atlas Network recently cataloged recurrent genomic abnormalities in glioblastoma multiforme (GBM). We describe a robust gene expression-based molecular classification of GBM into Proneural, Neural, Classical, and Mesenchymal subtypes and integrate multidimensional genomic data to establish patterns of somatic mutations and DNA copy number. Aberrations and gene expression of EGFR, NF1, and PDGFRA/IDH1 each define the Classical, Mesenchymal, and Proneural subtypes, respectively. Gene signatures of normal brain cell types show a strong relationship between subtypes and different neural lineages. Additionally, response to aggressive therapy differs by subtype, with the greatest benefit in the Classical subtype and no benefit in the Proneural subtype. We provide a framework that unifies transcriptomic and genomic dimensions for GBM molecular stratification with important implications for future studies.

59 BASIC BIOLOGICAL SCIENCES↗

Characterizing the acceleration time of laser-driven ion acceleration with data-informed neural networks

Peak ion energy is an important figure-of-merit in short-pulse, laser-driven ion acceleration and is dependent on an associated acceleration time. Standard metrics for these quantities depend on analytical results such as the self-similar fluid model or empirical models based on relatively small experimental and simulation datasets. In this work we attempt to use a data-informed neural network (NN) as a surrogate model for a large ensemble of PIC simulations to investigate an effective acceleration time. We explore the application of a stacked convolutional and recurrent NN architecture for improved regression by incorporating the time dependencies of the data into the training process. Of particular note is how pretraining a network on lower fidelity data, e.g. 1D analytical results, greatly improves the network's ability to learn more complex, higher fidelity data. Finally, the dependency of the acceleration time on various laser and plasma parameters is explored.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗