Search NASA⌕ Search

SEARCH · Search NASA

Results for “Predictors”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Using machine learning to derive cloud condensation nuclei number concentrations from commonly available measurements

Cloud condensation nuclei (CCN) number concentrations are an important aspect of aerosol–cloud interactions and the subsequent climate effects; however, their measurements are very limited. We use a machine learning tool, random decision forests, to develop a random forest regression model (RFRM) to derive CCN at 0.4 % supersaturation ([CCN0.4]) from commonly available measurements. The RFRM is trained on the long-term simulations in a global size-resolved particle microphysics model. Using atmospheric state and composition variables as predictors, through associations of their variabilities, the RFRM is able to learn the underlying dependence of [CCN0.4] on these predictors, which are as follows: eight fractions of PM 2.5 (NH 4 , SO 4 , NO 3, secondary organic aerosol (SOA), black carbon (BC), primary organic carbon (POC), dust, and salt), seven gaseous species (NO x , NH 3 , O 3 , SO 2 , OH, isoprene, and monoterpene), and four meteorological variables (temperature (T), relative humidity (RH), precipitation, and solar radiation). The RFRM is highly robust: it has a median mean fractional bias (MFB) of 4.4 % with ≈96.33 % of the derived [CCN0.4] within a good agreement range of -60% 2.5 speciation (NH 4 , SO 4 , NO 3 , and organic carbon (OC)), NO x , O 3 , SO 2 , T, and RH, as well as [CCN0.4] are available. We modify, optimize, and retrain the developed RFRM to make predictions from 19 to 9 of these available predictors. This retrained RFRM (RFRM-ShortVars) shows a reduction in performance due to the unavailability and sparsity of measurements (predictors); it captures the [CCN0.4] variability and magnitude at SGP with ≈67.02 % of the derived values in the good agreement range. This work shows the potential of using the more commonly available measurements of PM 2.5 speciation to alleviate the sparsity of CCN number concentrations' measurements.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Using predictions of outcomes of cache memory access requests for controlling whether a request generator sends memory access requests to a memory in parallel with cache memory access requests

An electronic device handles memory access requests for data in a memory. The electronic device includes a memory controller for the memory, a last-level cache memory, a request generator, and a predictor. The predictor determines a likelihood that a cache memory access request for data at a given address will hit in the last-level cache memory. Based on the likelihood, the predictor determines: whether a memory access request is to be sent by the request generator to the memory controller for the data in parallel with the cache memory access request being resolved in the last-level cache memory, and, when the memory access request is to be sent, a type of memory access request that is to be sent. When the memory access request is to be sent, the predictor causes the request generator to send a memory request of the type to the memory controller.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Disentangling natural and anthropogenic effects on benthic macroinvertebrate assemblages in western US streams

Abstract Stream macroinvertebrate assemblages are shaped by natural and human‐related factors that operate through complex hierarchical pathways. Quantifying these relationships can provide additional insights into stream ecological assessment. We applied a structural equation modeling framework to evaluate hypothesized pathways by which watershed, riparian, and in‐stream factors affect benthic macroinvertebrate condition in the Western Mountains (WMT) and Xeric (XER) ecoregions in the United States. We developed a conceptual model grounded in theory, empirical evidence, and expert opinion to evaluate the following hypotheses: (1) macroinvertebrate assemblages are primarily driven by proximal, in‐stream factors (e.g., water quality and physical habitat); (2) anthropogenic land uses affect macroinvertebrates indirectly by altering in‐stream characteristics; and (3) riparian vegetation cover attenuates land use effects. We tested our model separately on three measures of benthic macroinvertebrate assemblage condition: ratio of observed‐to‐expected taxonomic richness (O/E); a multimetric index (MMI); and richness of Ephemeroptera, Plecoptera, and Trichoptera taxa (EPT). In the WMT, site‐level riparian cover, in‐stream physical habitat (relative bed stability), and water chemistry (total nitrogen) were the top three predictors of macroinvertebrate assemblages, each having over two times the magnitude of effect on macroinvertebrates compared with watershed‐level predictors. In the arid XER, annual precipitation and stream flow characteristics were top predictors of macroinvertebrate assemblages and had similar magnitudes of effect as in‐stream water chemistry. Path analyses revealed that land use activities in the watershed and at the stream site degraded macroinvertebrate assemblages indirectly by altering relative bed stability, water quality, and riparian cover/complexity. Increased riparian cover was associated with greater macroinvertebrate condition by reducing land use impacts on stream flow, streambed substrate, and water quality, but the pathways differed among ecoregions. In the WMT, site‐level riparian cover affected macroinvertebrate assemblages partly through indirect pathways associated with greater streambed stability and reduced total nitrogen concentrations. In contrast, in the XER, watershed‐level riparian cover affected macroinvertebrate assemblages through greater specific stream power. Identifying the relative effects of and pathways by which natural and anthropogenic factors affect macroinvertebrates can serve as a framework for prioritizing management and conservation efforts.

Environmental Sciences & Ecology↗
DOE OSTI2020

The impact of demographic, clinical, genetic, and imaging variables on tau PET status

Purpose: A substantial proportion of amyloid-β (Aβ)+ patients with clinically diagnosed Alzheimer’s disease (AD) dementia and mild cognitive impairment (MCI) are tau PET–negative, while some clinically diagnosed non-AD neurodegenerative disorder (non-AD) patients or cognitively unimpaired (CU) subjects are tau PET–positive. We investigated which demographic, clinical, genetic, and imaging variables contributed to tau PET status. Methods: We included 2338 participants (430 Aβ+ AD dementia, 381 Aβ+ MCI, 370 non-AD, and 1157 CU) who underwent [ 18 F]flortaucipir ( n = 1944) or [ 18 F]RO948 ( n = 719) PET. Tau PET positivity was determined in the entorhinal cortex, temporal meta-ROI, and Braak V-VI regions using previously established cutoffs. We performed bivariate binary logistic regression models with tau PET status (positive/negative) as dependent variable and age, sex, APOE ε4, Aβ status (only in CU and non-AD analyses), MMSE, global white matter hyperintensities (WMH), and AD-signature cortical thickness as predictors. Additionally, we performed multivariable binary logistic regression models to account for all other predictors in the same model. Results: Tau PET positivity in the temporal meta-ROI was 88.6% for AD dementia, 46.5% for MCI, 9.5% for non-AD, and 6.1% for CU. Among Aβ+ participants with AD dementia and MCI, lower age, MMSE score, and AD-signature cortical thickness showed the strongest associations with tau PET positivity. In non-AD and CU participants, presence of Aβ was the strongest predictor of a positive tau PET scan. Conclusion: We identified several demographic, clinical, and neurobiological factors that are important to explain the variance in tau PET retention observed across the AD pathological continuum, non-AD neurodegenerative disorders, and cognitively unimpaired persons.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

The impacts of building characteristics, social psychological and cultural factors on indoor environment quality productivity belief

Indoor environmental quality (IEQ) plays a key role in determining occupants' productivity at work; however, analyses of the interconnected factors among building physical, attitudinal, social and demographic components in one study are lacking. To fill this research gap, this study investigates these interconnected factors' influence on occupants’ IEQ-productivity belief, defined as a personal, subjective evaluation of the linkage between the impacts of five IEQ aspects (the quality of indoor temperature, air, natural and electric lighting, and acoustics) and productivity. A cross-sectional survey data was collected in university offices from six countries (Brazil, Italy, Poland, Switzerland, Taiwan and the U.S.). Results of multiple linear regression models indicate that IEQ satisfaction is the strongest positive predictor of the IEQ-productivity belief and this relationship is stronger in private offices. Country of residence is the second primary predictor. Several attitudinal-behavioral factors, including thermal comfort, perceived ease of controlling indoor environmental features, and attitudes toward sharing controls are all positively associated with IEQ-productivity belief. Interestingly, the level of control accessibility to light switches has the strongest impact as opposed to other controls. On the other hand, group norms and conformity intention are not significant predictors. Regarding demographics, men are more likely than women to perceive the IEQs to have positive impacts on their productivity, without considering other variables in the regression model; however, women are more likely than men to consider all IEQs as having positive impacts on productivity, after considering other variables. Furthermore, our findings provide suggestions for prioritizing wellness in the workplace since the early design stage.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Uncertainty quantification of a deep learning fuel property prediction model

Deep learning models are being widely used in the field of combustion. Given the black-box nature of typical neural network based models, uncertainty quantification (UQ) is critical to ensure the reliability of predictions as well as the training datasets, and for a principled quantification of noise and its various sources. Deep learning surrogate models for predicting properties of chemical compounds and mixtures have been recently shown to be promising for enabling data-driven fuel design and optimization, with the ultimate goal of improving efficiency and lowering emissions from combustion engines. In this study, UQ is performed for a multi-task deep learning model that simultaneously predicts the research octane number (RON), Motor Octane Number (MON), and Yield Sooting Index (YSI) of pure components and multicomponent blends. The deep learning model is comprised of three smaller networks: Extractor 1, Extractor 2, and Predictor, and a mixing operator. The molecular fingerprints of individual components are encoded via Extractor 1 and Extractor 2, the mixing operator generates fingerprints for mixtures/blends based on linear mixing operation, and the predictor maps the fingerprint to the target properties. Two different classes of UQ methods, Monte Carlo ensemble methods and Bayesian neural networks (BNNs), are employed for quantifying the epistemic uncertainty. Combinations of Bernoulli and Gaussian distributions with DropConnect and DropOut techniques are explored as ensemble methods. All the DropConnect, DropOut and Bayesian layers are applied to the predictor network. Aleatoric uncertainty is modeled by assuming that each data point has an independent uncertainty associated with it. The results of the UQ study are further analyzed to compare the performance of BNN and ensemble methods. Although this study is confined to UQ of fuel property prediction, the methodologies are applicable to other deep learning frameworks that are being widely used in the combustion community.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Aboveground biomass density models for NASA’s Global Ecosystem Dynamics Investigation (GEDI) lidar mission

NASA's Global Ecosystem Dynamics Investigation (GEDI) is collecting spaceborne full waveform lidar data with a primary science goal of producing accurate estimates of forest aboveground biomass density (AGBD). This paper presents the development of the models used to create GEDI's footprint-level (~25 m) AGBD (GEDI04_A) product, including a description of the datasets used and the procedure for final model selection. The data used to fit our models are from a compilation of globally distributed spatially and temporally coincident field and airborne lidar datasets, whereby we simulated GEDI-like waveforms from airborne lidar to build a calibration database. We used this database to expand the geographic extent of past waveform lidar studies, and divided the globe into four broad strata by Plant Functional Type (PFT) and six geographic regions. GEDI's waveform-to-biomass models take the form of parametric Ordinary Least Squares (OLS) models with simulated Relative Height (RH) metrics as predictor variables. From an exhaustive set of candidate models, we selected the best input predictor variables, and data transformations for each geographic stratum in the GEDI domain to produce a set of comprehensive predictive footprint-level models. We found that model selection frequently favored combinations of RH metrics at the 98th, 90th, 50th, and 10th height above ground-level percentiles (RH98, RH90, RH50, and RH10, respectively), but that inclusion of lower RH metrics (e.g. RH10) did not markedly improve model performance. Second, forced inclusion of RH98 in all models was important and did not degrade model performance, and the best performing models were parsimonious, typically having only 1-3 predictors. Third, stratification by geographic domain (PFT, geographic region) improved model performance in comparison to global models without stratification. Fourth, for the vast majority of strata, the best performing models were fit using square root transformation of field AGBD and/or height metrics. There was considerable variability in model performance across geographic strata, and areas with sparse training data and/or high AGBD values had the poorest performance. These models are used to produce global predictions of AGBD, but will be improved in the future as more and better training data become available.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

CyProduct: A software tool for accurately predicting the byproducts of human cytochrome P450 metabolism

In silico metabolism prediction is a cheminformatic task of autonomously predicting the set of metabolic byproducts produced from a specified molecule and a set of enzymes or reactions. Here we describe a novel machine-learned in silico cytochrome P450 (CYP450) metabolism prediction suite, called CyProduct, that accurately predicts metabolic byproducts for a specified molecule and a human CYP450 isoform. It includes three modules: (1) CypReact, a tool that predicts if the query compound reacts with a given CYP450 enzyme; (2) CypBoM, a tool that accurately predicts the “bond site” of the reaction (i.e., which specific bonds within the query molecule react with the CYP isoform); and (3) MetaboGen, a tool that generates the metabolic byproducts based on CypBoM’s bond-site prediction. CyProduct predicts metabolic biotransformation products for each of the nine most important human CYP450 enzymes. CypBoM uses an important new concept called “Bond of Metabolism” (BoM), which extends the traditional “Site of Metabolism" (SoM) by specifying the information about the set of chemical bonds that is modified or formed in a metabolic reaction (rather than the specific atom). We created a BoM database for 3487 CYP450-mediated Phase I reactions, then used this to train the CypBoM Predictor to predict the reactive bond locations on substrate molecules. CypBoM Predictor’s cross-validated Jaccard score for reactive bond prediction ranged from 0.380 to 0.452 over the nine CYP450 enzymes. Over variants of a test set of 72 known CYP450 substrates and 30 non-reactants, CyProduct outperformed the other packages -- including ADMET Predictor, BioTransformer and GLORY -- by an average of 200% (wrt Jaccard score) in terms of predicting metabolites. The CyProduct suite and the datasets are freely available at https://bitbucket.org/wishartlab/cyproduct/src/master/.

Machine learning, Cytochrome P450, Metabolism pred↗
DOE OSTI2022

Short–Term Forecasting of Wind Gusts at Airports Across CONUS Using Machine Learning

Short–term forecasting of wind gusts, particularly those of higher intensity, is of great societal importance but is challenging due to the presence of multiple gust generation mechanisms. Wind gust observations from eight high–passenger–volume airports across the continental United States (CONUS) are summarized and used to develop predictive models of wind gust occurrence and magnitude. These short–term (same hour) forecast models are built using multiple logistic and linear regression, as well as artificial neural networks (ANNs) of varying complexity. A suite of 19 upper–air predictors drawn from the ERA5 reanalysis and an autoregressive (AR) term are used. Stepwise procedures instruct predictor selection, and resampling is used to quantify model stability. All models are developed separately for the warm (April–September) and cold (October–March) seasons. Results show that ANNs of 3–5 hidden layers (HLs) generally exhibit higher hit rates than logistic regression models and also improve skill with respect to wind gust magnitudes. However, deeper networks with more HLs increase false alarm rates in occurrence models and mean absolute error in magnitude models due to model overfitting. For model skill, inclusion of the AR term is critical while the majority of the remaining skill derives from wind speeds and lapse rates. A predictive ceiling is also clearly demonstrated, particularly for the strong and damaging gust magnitudes, which appears to be partially due to ERA5 predictor characteristics and the presence of mixed wind climates.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

How Well do Earth System Models Capture Apparent Relationships Between Phytoplankton Biomass and Environmental Variables?

Abstract As phytoplankton form the base of the marine food web, understanding the controls on their abundance is fundamental to understanding marine ecology and its sensitivity to global climate change. While many Earth System Models (ESMs) predict phytoplankton biomass, it is unclear whether they properly capture the mechanistic relationships that control this quantity in the real ocean. We used Random Forest analysis to analyze the output of 13 ESMs as well as two observational data sets. The target variable was phytoplankton carbon and the predictors included environmental parameters known to influence phytoplankton, including nutrients, light, mixed layer depth, salinity, temperature, and upwelling. We examined the following: (a) What fractions of variability in ESMs and observations can be linked to the large‐scale environmental variables simulated by ESMs? (b) What are the dominant predictors and relationships affecting phytoplankton biomass? (c) How well do ESMs simulate phytoplankton carbon and do they simulate the relationships we see in observations? About 88%–96% of the variability in observational data sets and greater than 98% in the ESMs was accounted for by environmental variables known to influence phytoplankton biomass. The dominant predictors in the observational data sets were shortwave radiation and dissolved iron, with temperature and ammonium also relatively important. All the ESMs show that shortwave radiation is the most important variable and most of them predict the right sign of sensitivity to most variables. However, the models predict that biomass reaches maximum levels at unrealistically low levels of iron and unrealistically high levels of light.

Environmental Sciences & Ecology↗
DOE OSTI2023

Physical Insights From the Multidecadal Prediction of North Atlantic Sea Surface Temperature Variability Using Explainable Neural Networks

Abstract North Atlantic sea surface temperatures (NASST), particularly in the subpolar region, are among the most predictable in the world's oceans. However, the relative importance of atmospheric and oceanic controls on their variability at multidecadal timescales remain uncertain. Neural networks (NNs) are trained to examine the relative importance of oceanic and atmospheric predictors in predicting the NASST state in the Community Earth System Model 1 (CESM1). In the presence of external forcings, oceanic predictors outperform atmospheric predictors, persistence, and random chance baselines out to 25‐year leadtimes. Layer‐wise relevance propagation is used to unveil the sources of predictability, and reveal that NNs consistently rely upon the Gulf Stream‐North Atlantic Current region for accurate predictions. Additionally, CESM1‐trained NNs successfully predict the phasing of multidecadal variability in an observational data set, suggesting consistency in physical processes driving NASST variability between CESM1 and observations.

Geology↗
DOE OSTI2023

Leveraging Groundwater Dynamics to Improve Predictions of Summer Low-Flow Discharges

Summer streamflow predictions are critical for managing water resources; however, warming-induced shifts from snow to rain regimes impact low-flow predictive models. Additionally, reductions in snowpack drive earlier peak flows and lower summer flows across the western United States increasing reliance on groundwater for maintaining summer streamflow. However, it remains poorly understood how groundwater contributions vary interannually. Here, we quantify recession limb groundwater (RLGW), defined as the proportional groundwater contribution to the stream during the period between peak stream flow and low flow, to predict summer low flows across three diverse western US watersheds. We ask (a) how do snow and rain dynamics influence interannual variations of RLGW contributions and summer low flows?; (b) which watershed attributes impact the effectiveness of RLGW as a predictor of summer low flows? Linear models reveal that RLGW is a strong predictor of low flows across all sites and drastically improves low-flow prediction compared to snow metrics at a rain-dominated site. Results suggest that strength of RLGW control on summer low flows may be mediated by subsurface storage. Subsurface storage can be divided into dynamic (i.e., variability saturated) and deep (i.e., permanently saturated) components, and we hypothesize that interannual variability in dynamic storage contribution to streamflow drives RLGW variability. In systems with a higher proportion of dynamic storage, RLGW is a better predictor of summer low flow because the stream is more responsive to dynamic storage contributions compared to deep-storage-dominated systems. Overall, including RLGW improved low-flow prediction across diverse watersheds.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Cross-scale covariance for material property prediction

A simulation can stand its ground against an experiment only if its prediction uncertainty is known. The unknown accuracy of interatomic potentials (IPs) is a major source of prediction uncertainty, severely limiting the use of large-scale classical atomistic simulations in a wide range of scientific and engineering applications. Here we explore covariance between predictions of metal plasticity, from 178 large-scale (~10 8 atoms) molecular dynamics (MD) simulations, and a variety of indicator properties computed at small-scales (≤10 2 atoms). All simulations use the same 178 IPs. In a manner similar to statistical studies in public health, we analyze correlations of strength with indicators, identify the best predictor properties, and build a cross-scale “strength-on-predictors” regression model. This model is then used to estimate regression error over the statistical pool of IPs. Small-scale predictors found to be highly covariant with strength are computed using expensive quantum-accurate calculations and used to predict flow strength, within the statistical error bounds established in our study.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Protein model accuracy estimation empowered by deep learning and inter-residue distance prediction in CASP14

Abstract The inter-residue contact prediction and deep learning showed the promise to improve the estimation of protein model accuracy (EMA) in the 13th Critical Assessment of Protein Structure Prediction (CASP13). To further leverage the improved inter-residue distance predictions to enhance EMA, during the 2020 CASP14 experiment, we integrated several new inter-residue distance features with the existing model quality assessment features in several deep learning methods to predict the quality of protein structural models. According to the evaluation of performance in selecting the best model from the models of CASP14 targets, our three multi-model predictors of estimating model accuracy (MULTICOM-CONSTRUCT, MULTICOM-AI, and MULTICOM-CLUSTER) achieve the averaged loss of 0.073, 0.079, and 0.081, respectively, in terms of the global distance test score (GDT-TS). The three methods are ranked first, second, and third out of all 68 CASP14 predictors. MULTICOM-DEEP, the single-model predictor of estimating model accuracy (EMA), is ranked within top 10 among all the single-model EMA methods according to GDT-TS score loss. The results demonstrate that inter-residue distance features are valuable inputs for deep learning to predict the quality of protein structural models. However, larger training datasets and better ways of leveraging inter-residue distance information are needed to fully explore its potentials.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

Enhancing alphafold-multimer-based protein complex structure prediction with MULTICOM in CASP15

To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural predictions by using both traditional sequence alignments and Foldseek-based structure alignments, ranks structural predictions through multiple complementary metrics, and refines the structural predictions via a Foldseek structure alignment-based refinement method. The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. MULTICOM_qa ranked 3 rd among 26 CASP15 server predictors and MULTICOM_human ranked 7 th among 87 CASP15 server and human predictors. The average TM-score of the first predictions submitted by MULTICOM_qa for CASP15 assembly targets is ~0.76, 5.3% higher than ~0.72 of the standard AlphaFold-Multimer. The average TM-score of the best of top 5 predictions submitted by MULTICOM_qa is ~0.80, about 8% higher than ~0.74 of the standard AlphaFold-Multimer. Moreover, the Foldseek Structure Alignment-based Multimer structure Generation (FSAMG) method outperforms the widely used sequence alignment-based multimer structure generation.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Multi-Attribute Subset Selection enables prediction of representative phenotypes across microbial populations

The interpretation of complex biological datasets requires the identification of representative variables that describe the data without critical information loss. This is particularly important in the analysis of large phenotypic datasets (phenomics). Here we introduce Multi-Attribute Subset Selection (MASS), an algorithm which separates a matrix of phenotypes (e.g., yield across microbial species and environmental conditions) into predictor and response sets of conditions. Using mixed integer linear programming, MASS expresses the response conditions as a linear combination of the predictor conditions, while simultaneously searching for the optimally descriptive set of predictors. We apply the algorithm to three microbial datasets and identify environmental conditions that predict phenotypes under other conditions, providing biologically interpretable axes for strain discrimination. MASS could be used to reduce the number of experiments needed to identify species or to map their metabolic capabilities. The generality of the algorithm allows addressing subset selection problems in areas beyond biology.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks

Next generation High Performance (HP) tokamaks risk damage from unmitigated disruptions at high current and power. Achieving reliable disruption prediction for a device's HP operation based on its Low Performance (LP) data is a key to its success. In this letter, through explorative data analysis and dedicated numerical experiments on multiple existing tokamaks, we demonstrate how the operational regimes of tokamaks can affect the power of a trained disruption predictor. First, our results suggest data-driven disruption predictors trained on abundant LP discharges work poorly on the HP regime of the same tokamak, which is a consequence of the distinct distributions of the tightly correlated signals related to disruptions in these two regimes. Second, we find that matching operational parameters among tokamaks strongly improves cross-machine accuracy which implies our model learns from the underlying scalings of dimensionless physics parameters like q 95 , β p and confirms the importance of these parameters in disruption physics and cross machine domain matching from the data-driven perspective. Finally, our results show in the absence of HP data from the target devices, the best predictivity of the HP regime for the target machine can be achieved by combining LP data from the target with HP data from other machines. Furthermore, these results provide a possible disruption predictor development strategy for next generation tokamaks, such as ITER and SPARC, and highlight the importance of developing baseline scenario discharges of future tokamaks on existing machines to collect more relevant disruptive data.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Integrated deep learning framework for unstable event identification and disruption prediction of tokamak plasmas

Abstract The ability to identify underlying disruption precursors is key to disruption avoidance. In this paper, we present an integrated deep learning (DL) based model that combines disruption prediction with the identification of several disruption precursors like rotating modes, locked modes, H-to-L back transitions and radiative collapses. The first part of our study demonstrates that the DL-based unstable event identifier trained on 160 manually labeled DIII-D shots can achieve, on average, 84% event identification rate of various frequent unstable events (like H-L back transition, locked mode, radiative collapse, rotating MHD mode, large sawtooth crash), and the trained identifier can be adapted to label unseen discharges, thus expanding the original manually labeled database. Based on these results, the integrated DL-based framework is developed using a combined database of manually labeled and automatically labeled DIII-D data, and it shows state-of-the-art (AUC = 0.940) disruption prediction and event identification abilities on DIII-D. Through cross-machine numerical disruption prediction studies using this new integrated model and leveraging the C-Mod, DIII-D, and EAST disruption warning databases, we demonstrate the improved cross-machine disruption prediction ability and extended warning time of the new model compared with a baseline predictor. In addition, the trained integrated model shows qualitatively good cross-machine event identification ability. Given a labeled dataset, the strategy presented in this paper, i.e. one that combines a disruption predictor with an event identifier module, can be applied to upgrade any neural network based disruption predictor. The results presented here inform possible development strategies of machine learning based disruption avoidance algorithms for future tokamaks and highlight the importance of building comprehensive databases with unstable event information on current machines.

plasma instabilities↗