Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep Operator Network”

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 523 records · Page 29
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

An Autonomous Robot for Shell and Tube Heat Exchanger Inspection

Shell and tube heat exchangers (STHEs) are critical to energy conversion efficiency of power plants. Eddy current examination is a way to evaluate working conditions of these tubes. However, the current testing apparatus requires human to manually insert an eddy current testing (ECT) probe into and extract it out of individual tubes, and meanwhile monitor measurement results for diagnosis. It is a time-consuming and labor-intensive procedure even for an experienced technician. To tackle this challenge, in this work, we developed a robot enabled ECT system for autonomous inspection of STHEs. The robotic platform employs Mecanum wheeled chassis for high mobility, machine vision to locate tube bundle and tube inlets, a rotational Cartesian mechanism to operate at planes with all possible inclinations, and a task-specific mechanism for ECT probe delivery. Machine vision locates tube bundle and tube inlets by an April tag detection algorithm and a Circle Hough Transform (CHT) algorithm, respectively. Assisted by a guidance cone, the ECT probe is continuously fed into the tubes with a fill factor of 0.819. During this process, the eddy current data are automatically collected and real-time analyzed by convolutional neural networks (CNN), showing accuracy of nearly 100% for identifying defective and non-defective tubes and 85% for four types of defective tubes and non-defective tubes.

autonomy, deep learning, eddy current testing, hea↗
DOE OSTI2023

DeePMD-kit v2: A software package for deep potential models

DeePMD-kit is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials known as Deep Potential (DP) models. This package, which was released in 2017, has been widely used in the fields of physics, chemistry, biology, and material science for studying atomistic systems. The current version of DeePMD-kit offers numerous advanced features, such as DeepPot-SE, attention-based and hybrid descriptors, the ability to fit tensile properties, type embedding, model deviation, DP-range correction, DP long range, graphics processing unit support for customized operators, model compression, non-von Neumann molecular dynamics, and improved usability, including documentation, compiled binary packages, graphical user interfaces, and application programming interfaces. This article presents an overview of the current major version of the DeePMD-kit package, highlighting its features and technical details. Additionally, this article presents a comprehensive procedure for conducting molecular dynamics as a representative application, benchmarks the accuracy and efficiency of different models, and discusses ongoing developments.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2018

Recurrent Neural Network Language Models for Open Vocabulary Event-Level Cyber Anomaly Detection

Automated analysis methods are crucial aids for monitoring and defending a network to protect the sensitive or confidential data it hosts. This work introduces a flexible, powerful, and unsupervised approach to detecting anomalous behavior in computer and network logs; one that largely eliminates domain-dependent feature engineering employed by existing methods. By treating system logs as threads of interleaved ``sentences'' (event log lines) to train online unsupervised neural network language models, our approach provides an adaptive model of normal network behavior. We compare the effectiveness of both standard and bidirectional recurrent neural network language models at detecting malicious activity within network log data. Extending these models, we introduce a tiered recurrent architecture, which provides context by modeling sequences of users' actions over time. Compared to isolation forests and Principal Components Analysis (PCA), two popular anomaly detection algorithms, we observe superior performance on the Los Alamos National Laboratory Cyber Security dataset. For log-line-level predictions, our best performing character-based model provides test set anomaly scores ranking red team events in the 98th percentile on average, and yields 0.97 area under the receiver operator characteristic curve, demonstrating the strong fine-grained anomaly detection performance of this approach on open vocabulary logging sources.

Cyber Analysis, Deep Learning, language analysis, ↗
DOE OSTI2020

Neural networks for modeling and control of particle accelerators

Charged particle accelerators support a wide variety of scientific, industrial, and medical applications. They range in scale and complexity from systems with just a few components for beam acceleration and manipulation, to large scientific user facilities that span many kilometers and have hundreds-to-thousands of individually-controllable components. Specific operational requirements must be met by adjusting the many controllable variables of the accelerator. Meeting these requirements can be challenging, both in terms of the ability to achieve specific beam quality metrics in a reliable fashion and in terms of the time needed to set up and maintain the optimal operating conditions. One avenue toward addressing this challenge is to incorporate techniques from the fields of machine learning (ML) and artificial intelligence (AI) into the way particle accelerators are modeled and controlled. While many promising approaches within AI/ML could be used for particle accelerators, this dissertation focuses on approaches based on neural networks. Neural networks are particularly well-suited to modeling, control, and diagnostic analysis of nonlinear systems, as well as systems with large parameter spaces. They are also very appealing for their ability to process high-dimensional data types, such as images and time series (both of which are ubiquitous in particle accelerators). In this work, key studies that demonstrated the potential utility of modern neural network-based approaches to modeling and control of particle accelerators are presented. The context for this work is important: at the start of this work in 2012, there was little interest in AI/ML in the particle accelerator community, and many of the advances in neural networks and deep learning that enabled its present success had not yet been made at that time. As such, this work was both an exploration of possible application areas and a generator of proof-of-concept demonstrations in these areas.

43 PARTICLE ACCELERATORS↗
DOE OSTI2018

Successful In Situ Remediation of Cr(VI)-Impacted Deeper Vadose Zone Soils for Groundwater Protection - 18603

Shallow soil at a former industrial wood treating facility was impacted with chromium, arsenic, and copper above cleanup goals and shallow soil has been excavated for protection of direct contact exposure pathways. Deeper vadose zone soil was predominantly impacted with chromium and was undergoing remediation for long-term groundwater protection. The 920-meter (m) long Cr(VI) groundwater plume has undergone full-scale remediation with groundwater recirculation and in situ bioremediation. Following approximately 4 years of operation, the Cr(VI) groundwater plume, with former source area groundwater concentrations over 10,000 micrograms per liter (μg/L), has been reduced to below the laboratory method reporting limit (0.50 μg/L). Approximately 23,000 cubic meters (m{sup 3}) of deeper (4.5 m - 11 m below ground surface, bgs) vadose zone soil required Cr(VI) remediation. The remediation strategy relied on reduction of Cr(VI) and geochemical fixation as trivalent chromium (Cr(III)) and iron hydroxide precipitates. Chromium reduction was facilitated by a carbon source (corn syrup and methanol) to establish and maintain biogeochemical reducing conditions and ferrous iron to support direct Cr(VI) chemical reduction. Combined, the injected soil moisture, carbon source and ferrous iron supported fast and sustained ferrous/ferric iron cycling and Cr(VI) reduction. Remedy performance monitoring included time-series water quality data from a network of vacuum lysimeters and confirmation soil borings. Reagent was applied either through liquid injection wells and direct-push injection points, or by deep soil mixing methodology in areas with difficult geology (i.e., fine-grained soils and discontinuous iron-silica hardpan layer). Following both phases of deep soil remediation, soils met long-term protection of groundwater remediation action objectives. In situ treatment of soils provides a cost-effective remedial solution compared to excavation, specifically when impacts are deep and long-term protection of groundwater is a primary remediation goal. The delivery methods employed in this case study can be applied to sites impacted with a broad range of contaminants amendable to geochemical fixation (e.g., chromium, uranium, strontium, nitrate, etc.). (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2022

Distributed Real-time Plume Monitoring for Deep Sea Mineral Extraction​

In the emerging industry of deep-sea mining for minerals and deposits (e.g. polymetallic nodules for nickel, cobalt, copper, and manganese), more data is required to understand the effects of sediment plume generation and predict the distribution of disturbed sediment. There are two main sources of plume generation, the first being at the active mining site where the “collector” directly removes the top layer of the sea floor. The other is the “midwater plume” consisting of unwanted sediment that was collected during extraction that is pumped back into the aphotic zone. The vast majority of plume generation is caused by the collector, causing detrimental and long-lasting impacts on seafloor ecosystems due to the lack of wave activity or strong currents at the sea floor. Therefore, it is crucial to invest in the infrastructure to support the study and constant monitoring over a large area of the sea floor where plume generation is present. Due to the limited number of usable channels and power requirements, current subsea wireless communications technologies are not well suited to instrumenting the large areas of the sea floor needed to monitor plume migration. The scope of this effort is to transition experimental demonstrations of high-bandwidth, full-duplex scalable underwater laser communications to the seafloor in an open ocean environment. Specifically tackling challenges associated with the dynamic nature of the subsea world, including but not limited to, deployment logistics, sustainability, and range. The goal is to enable the internet of underwater things for deep sea industries by broadening the capabilities of subsea communications. By using high-precision laser transmitters, many of the challenges current subsea optical systems face can be circumvented, such as power consumption, interference, and bandwidth limitations. This approach lends itself to wireless interlinking multi-node networks, in series or parallel, facilitating the implementation of a wide array of sensor types. This interlinking allows all the data gathered from the network to be processed through a single hardline uplink to the surface, lowering the complexity required for near real-time data processing. Additionally, the laser control systems produce metadata that can be used to help characterize the water column between the nodes. Combining data from various sensors such as turbidity, temperature, current velocity with metadata such as beam attenuation and deflection can produce a high-resolution model of sea floor conditions around an active mining zone. The resulting near real-time model can be used to optimize location and flow rate of the mining operation to minimize and quantify the environmental impact.

Mons, Ishan↗
DOE OSTI2020

AmeriFlux US-xSB NEON Ordway-Swisher Biological Station (OSBS)

This is the AmeriFlux version of the carbon flux data for the site US-xSB NEON Ordway-Swisher Biological Station (OSBS). Site Description - The Ordway-Swisher Biological Station (OSBS) is operated by the University of Florida and comprises over 9,300 acres. It is a year-round field station established for the long-term study and conservation of unique ecosystems through management, research and education. The Station is located approximately 20 miles east of Gainesville in Melrose (Putnam County, Florida). There are two aquatic arrays at Ordway-Swisher, representing the two dominant aquatic features on the landscape: 1) Suggs lake, a shallow surface water lake that is rich in taxa and biologically active in structure and function; and 2) Barco lake, a deep lake connected to ground water. The forest is maintained by fire and has a relatively open structure: it is managed with prescribed burns at a frequency of 3-4 years.

Network), NEON (National Ecological Observatory↗
DOE OSTI2023

AmeriFlux FLUXNET-1F US-xSB NEON Ordway-Swisher Biological Station (OSBS)

This is the AmeriFlux Management Project (AMP) created FLUXNET-1F version of the carbon flux data for the site US-xSB NEON Ordway-Swisher Biological Station (OSBS). This is the FLUXNET version of the carbon flux data for the site US-xSB NEON Ordway-Swisher Biological Station (OSBS) produced by applying the standard ONEFlux (1F) software. Site Description - The Ordway-Swisher Biological Station (OSBS) is operated by the University of Florida and comprises over 9,300 acres. It is a year-round field station established for the long-term study and conservation of unique ecosystems through management, research and education. The Station is located approximately 20 miles east of Gainesville in Melrose (Putnam County, Florida). There are two aquatic arrays at Ordway-Swisher, representing the two dominant aquatic features on the landscape: 1) Suggs lake, a shallow surface water lake that is rich in taxa and biologically active in structure and function; and 2) Barco lake, a deep lake connected to ground water. The forest is maintained by fire and has a relatively open structure: it is managed with prescribed burns at a frequency of 3-4 years.

Network), NEON (National Ecological Observatory↗
DOE OSTI2023

Three-dimensional nanoscale reduced-angle ptycho-tomographic imaging with deep learning (RAPID)

X-ray ptychographic tomography is a nondestructive method for three dimensional (3D) imaging with nanometer-sized resolvable features. The size of the volume that can be imaged is almost arbitrary, limited only by the penetration depth and the available scanning time. Here we present a method that rapidly accelerates the imaging operation over a given volume through acquiring a limited set of data via large angular reduction and compensating for the resulting ill-posedness through deeply learned priors. The proposed 3D reconstruction method “RAPID” relies initially on a subset of the object measured with the nominal number of required illumination angles and treats the reconstructions from the conventional two-step approach as ground truth. It is then trained to reproduce equal fidelity from much fewer angles. After training, it performs with similar fidelity on the hitherto unexamined portions of the object, previously not shown during training, with a limited set of acquisitions. In our experimental demonstration, the nominal number of angles was 349 and the reduced number of angles was 21, resulting in a x140 aggregate speedup over a volume of 4.48 x 93.18 x 3.92 μm 3 and with (14nm) 3 feature size, i.e. ~ 10 8 voxels. RAPID’s key distinguishing feature over earlier attempts is the incorporation of atrous spatial pyramid pooling modules into the deep neural network framework in an anisotropic way. We found that adjusting the atrous rate improves reconstruction fidelity because it expands the convolutional kernels’ range to match the physics of multi-slice ptychography without significantly increasing the number of parameters.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2016

Control of spin defects in wide-bandgap semiconductors for quantum technologies

Deep-level defects are usually considered undesirable in semiconductors as they typically interfere with the performance of present-day electronic and optoelectronic devices. However, the electronic spin states of certain atomic-scale defects have recently been shown to be promising quantum bits for quantum information processing as well as exquisite nanoscale sensors due to their local environmental sensitivity. In this review, we will discuss recent advances in quantum control protocols of several of these spin defects, the negatively charged nitrogen-vacancy (NV - ) center in diamond and a variety of forms of the neutral divacancy (VV 0 ) complex in silicon carbide (SiC). These defects exhibit a spin-triplet ground state that can be controlled through a variety of techniques, several of which allow for room temperature operation. Microwave control has enabled sophisticated decoupling schemes to extend coherence times as well as nanoscale sensing of temperature along with magnetic and electric fields. On the other hand, photonic control of these spin states has provided initial steps toward integration into quantum networks, including entanglement, quantum state teleportation, and all-optical control. Electrical and mechanical control also suggest pathways to develop quantum transducers and quantum hybrid systems. In conclusion, the versatility of the control mechanisms demonstrated should facilitate the development of quantum technologies based on these spin defects.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2025

Deep Learning–Assisted Multiobjective Optimization of Geological CO 2 Storage Performance under Geomechanical Risks

In geological CO 2 storage, designing the optimal well control strategy for CO 2 injection to maximize CO 2 storage while minimizing the associated geomechanical risks is not trivial. This challenge arises due to pressure buildup, CO 2 plume migration, the highly nonlinear nature of geomechanical responses to rock-fluid interaction, and the high computational cost associated with coupled flow and geomechanics simulations. In this paper, we introduce a novel optimization framework to address these challenges. The optimization problem is formulated as follows: maximize total CO 2 storage while minimizing geomechanical risks by adjusting the injection schedules within bounded constraints. The geomechanical risks are primarily driven by injection-induced pressure build-up, which is characterized by ground displacement and the induced microseismicity. We used the Fourier neural operator (FNO)-based deep learning model to construct surrogate models, replacing the time-consuming coupled flow and geomechanics simulations for evaluating the aforementioned objective functions. The developed surrogate models have been incorporated into a multiobjective optimization framework through a genetic algorithm to reduce the computational burden. The proposed optimization framework reduces the computational cost from approximately 2,400 hours, when using objective function evaluations based on physics-based simulations, to around 20 minutes. A set of Pareto-optimal solutions of the proposed workflow yields nontrivial optimal decisions, reducing the microseismicity potential and the vertical displacement. This Pareto front highlights the optimal trade-offs between CO 2 storage amount, safety, and ground displacement, emphasizing the need for careful optimization and management of injection strategies to achieve a balanced outcome. The novelty of this work is twofold. First, we demonstrate the importance of incorporating the minimization of the geomechanical risks as objective functions into the CO 2 storage optimization workflow to mitigate the potential risk of induced microseismicity and ground displacement. Second, we leverage the FNO-based surrogate models to optimize a real-field CO 2 storage operation.

42 ENGINEERING↗
DOE OSTI2019

Generation of synthetic dielectric dispersion logs in organic-rich shale formations using neural-network models

Dielectric dispersion (DD) logs acquired in subsurface geologic formations generally are composed of conductivity ([Formula: see text]) and relative permittivity ([Formula: see text]) measurements at four discrete frequencies in the range of 10 MHz to 1 GHz. Acquisition of DD logs in subsurface formations is operationally challenging, and it requires a hard-to-deploy infrastructure. We developed three supervised neural-network-based predictive methods to process conventional, easy-to-acquire subsurface logs for generating the eight DD logs acquired at four frequencies. These predictive methods will improve reservoir characterization in the absence of a DD logging tool. The predictive methods are tested in three wells intersecting organic-rich shale formations of the Permian Basin and the Bakken Shale. The first method predicts the eight dispersion logs simultaneously using a single artificial neural network (ANN) model, whereas the second method simultaneously predicts the four conductivity dispersion logs using one ANN model, followed by simultaneous prediction of four permittivity dispersion logs using a second ANN model. The third method sequentially predicts the eight dispersion logs, one at a time using eight sequential ANN models, based on a predetermined ranking of the prediction accuracy for each of the eight DD logs when simultaneously generated. Considering that the conventional and DD logs are recorded more than 10,000 ft deep in the subsurface using logging tools that are run at different times in rugose boreholes for sensing the near-wellbore geologic formation, the data used in this predictive work is prone to noise and biases that tend to adversely affect the prediction performances of the proposed methods. In terms of normalized root-mean square error (Nrms error), the prediction performances of the second predictive method are 8.5% worse and 6.2% better for the conductivity and permittivity dispersion logs, respectively, as compared with those of the first predictive method. The third method has best prediction performance for permittivity dispersion logs, which is 0.089 in terms of the Nrms error.

Geochemistry & Geophysics↗
DOE OSTI2022

Prediction of DIII-D Pedestal Structure from Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. An experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (ne) and electron temperature (Te) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (Ip), toroidal magnetic field (Bφ), neutral beam heating power (PNBI) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2025

Topology-Aware Reinforcement Learning for Voltage Control: Centralized and Decentralized Strategies

Volt-VAR control (VVC) methods based on deep reinforcement learning (DRL) can effectively control distribution grid voltage and minimize power loss by implementing corrective and preventive control measures on the reactive power output of inverter-based distributed energy resources (DERs). However, model-free DRL-based VVC approaches usually cannot capture the important topological feature of the power system since they use a fully-connected network (FCN) to deliver the action. Therefore, this paper proposes a graph convolutional network (GCN)-based DRL approach that can employ the topological information of the network to take better control action for regulating the voltage. Our implementation allows for both centralized and decentralized configurations, utilizing a single agent and multiple agents respectively. Although the centralized GCN-based DRL approach has its advantages of minimizing voltage fluctuation and power loss, it is not suitable for large scale power systems due to its challenges in terms of scalability, computation speed and potential single points of failure. Therefore, these problems can be resolved using the decentralized GCN-based DRL approach. Moreover, to ensure the safe operation of the model, our proposed approach incorporates an exponential barrier function while formulating the reward function for each agent. To validate performance of the proposed approaches, the proposed model is tested on modified IEEE test systems and the performances are measured in terms on voltage fluctuation reduction, minimization of power loss and computational speed. Finally, the results show that the proposed topology-aware approach outperforms the FCN-based DRL approach in terms of reducing voltage fluctuation and minimizing power loss of the network. Moreover, it is shown that the decentralized GCN-based DRL has faster computational speed than other approaches.

42 ENGINEERING↗
DOE OSTI2024

Seismic Monitoring near Ithaca, New York, Reveals Nonuniform Distribution of Microseismicity in an Intraplate Region

Abstract Cornell University intends to use a deep direct-use geothermal system to heat its Ithaca, New York, campus. In preparation for this project, the Cornell Seismic Network has been monitoring the background seismicity in this intraplate region since 2019. From January 2020 to June 2023, 95 events were detected within 20 km of the proposed geothermal well site, with local magnitudes ranging from −1.02 to 0.56. None of these events appear in regional or national catalogs. Events locate in a narrow geographic band, with one-fourth exhibiting multimodal hypocentral probability peaks both near the surface and at 1–4 km depth. We relocate events with a joint hypocenter and 1D velocity model inversion, in addition to a fully nonlinear method, and then compare observations with synthetic waveforms. Together, these approaches provide strong evidence for >95% of events locating at the surface or within the 3-km-thick sedimentary sequence. We explore how anthropogenic activity and regional topographic stress may contribute to frequent surficial events. This information is critical for characterizing the background microseismicity for comparison during future geothermal operations. Ithaca’s geology of Paleozoic sediments overlying Precambrian crystalline basement is typical of many continental interiors, so these results also provide insight into intraplate microseismicity patterns.

Geochemistry & Geophysics↗
DOE OSTI2014

Quality-Controlled Upper-Air Sounding Dataset for DYNAMO/CINDY/AMIE: Development and Corrections

The upper-air sounding network for DYNAMO (Dynamics of the Madden-Julian Oscillation or MJO) has provided an unprecedented set of observations for studying the MJO over the Indian Ocean (IO) where coupling of this oscillation with deep convection first occurs. With 72 sounding sites and dropsonde data from 13 aircraft mission, the sonde network covers the tropics from Eastern African to the West Pacific. In total nearly 26,000 sondes were collected from this network during the experiment’s 6-month extended observing period (from October 2011 to March 2012). Slightly more than half of the sondes, collected from 33 sites, are at high vertical resolution. Rigorous post-field phase processing of the sonde data included several levels of quality checks and a variety of corrections which address a number of issues (e.g., daytime dry bias, baseline surface data errors, ship deck-heating effects, artificial dry spikes in slow ascent sondes). Because of the importance of an accurate description of the moisture field in meeting the scientific goals of the experiments, particular attention is given to humidity correction and its validation. The humidity corrections, though small relative to some previous field campaigns, produced high fidelity moisture analyses in which sonde precipitable water compared well with independent estimates. An assessment of model operational analyses moisture using corrected sonde data shows an overall good agreement with the exception at upper-levels where model moisture and clouds are more abundant than the sounding data would indicate.

dataset↗
DOE OSTI2021

Prediction of DIII-D Pedestal Structure From Externally Controllable Parameters

The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. Here, an experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (n e ) and electron temperature (T e ) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (I p ), toroidal magnetic field (B Φ ), neutral beam heating power (P NBI ) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗