Deep-Learning-Enabled Fast Optical Identification and Characterization of 2D Materials
Not provided.
Chemistry↗
SEARCH · Engineering Papers
Results for “ensemble prediction”
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.
Strong plasma turbulence in the earth's electron foreshock
A quantitative model is developed to account for the distribution in magnitude and location of the intense plasma waves observed in the earth's electron foreshock given the observed rms levels of waves. In this model, nonlinear strong-turbulence effects cause solitonlike coherent wave packets to form and decouple from incoherent background beam-excited weak turbulence, after which they convect downstream with the solar wind while collapsing to scales as short as 100 m and fields as high as 2 V/m. The existence of waves with energy densities above the strong-turbulence wave-collapse threshold is inferred from observations from IMP 6 and ISEE 1 and quantitative agreement is found between the predicted distribution of fields in an ensemble of such wave packets and the actual field distribution observed in situ by IMP 6. Predictions for the polarization of plasma waves and the bandwidth of ion-sound waves are also consistent with the observations. It is shown that strong-turbulence effects must be incorporated in any comprehensive theory of the propagation and evolution of electron beams in the foreshock. Previous arguments against the existence of strong turbulence in the foreshock are refuted.
Robinson, P. A.↗
Uncertainty-aware predictions of molecular x-ray absorption spectra using neural network ensembles
Not Available
97 MATHEMATICS AND COMPUTING↗
Aerosol Observability and Predictability: From Research to Operations for Chemical Weather Forecasting. Lagrangian Displacement Ensembles for Aerosol Data Assimilation
A challenge common to many constituent data assimilation applications is the fact that one observes a much smaller fraction of the phase space that one wishes to estimate. For example, remotely sensed estimates of the column average concentrations are available, while one is faced with the problem of estimating 3D concentrations for initializing a prognostic model. This problem is exacerbated in the case of aerosols because the observable Aerosol Optical Depth (AOD) is not only a column integrated quantity, but it also sums over a large number of species (dust, sea-salt, carbonaceous and sulfate aerosols. An aerosol transport model when driven by high-resolution, state-of-the-art analysis of meteorological fields and realistic emissions can produce skillful forecasts even when no aerosol data is assimilated. The main task of aerosol data assimilation is to address the bias arising from inaccurate emissions, and Lagrangian misplacement of plumes induced by errors in the driving meteorological fields. As long as one decouples the meteorological and aerosol assimilation as we do here, the classic baroclinic growth of error is no longer the main order of business. We will describe an aerosol data assimilation scheme in which the analysis update step is conducted in observation space, using an adaptive maximum-likelihood scheme for estimating background errors in AOD space. This scheme includes e explicit sequential bias estimation as in Dee and da Silva. Unlikely existing aerosol data assimilation schemes we do not obtain analysis increments of the 3D concentrations by scaling the background profiles. Instead we explore the Lagrangian characteristics of the problem for generating local displacement ensembles. These high-resolution state-dependent ensembles are then used to parameterize the background errors and generate 3D aerosol increments. The algorithm has computational complexity running at a resolution of 1/4 degree, globally. We will present the result of assimilating AOD retrievals from MODIS (on both Aqua and TERRA satellites) from AERONET for validation. The impact on the GEOS-5 Aerosol Forecasting will be fully documented.
da Silva, Arlindo↗
Analyzing the Impact of CryoSat-2 Ice Thickness Initialization on Seasonal Arctic Sea Ice Prediction
Twin 5-month seasonal forecast experiments are performed to predict the September 2018 minimum ice extent using the fully coupled Navy Earth System Prediction Capability (ESPC). In the control run, ensemble forecasts are initialized from the operational US Navy Global Ocean Forecasting System (GOFS) 3.1 for the ocean and sea ice but do not assimilate ice thickness data. Another set of forecasts are initialized from the same GOFS 3.1 fields but with sea ice thickness derived from CryoSat-2 (CS2). The Navy ESPC ensemble mean September 2018 minimum sea ice extent initialized with GOFS 3.1 ice thickness was over-predicted by 0.68 M sq.km (5.27 M sq.km) versus the ensemble set of forecasts initialized with CS2 ice thickness that had an error of 0.40 M sq.km (4.99 M sq.km), a 56% reduction in error. The September mean Integrated Ice Edge Error (IIEE) shows a 19% improvement for the entire Arctic with the CS2 data versus the control run. Comparison against Upward Looking Sonar (ULS) ice thickness in the Beaufort Sea reveals a lower bias and RMSE with the CS2 forecasts at all three moorings. Ice concentration at these locations is also improved, but neither set of experiments show ice free conditions as observed at moorings A and D.
time-lagged ensembles↗
Uncertainty quantification for molecular property predictions with graph neural architecture search
Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Decadal predictability of North Atlantic blocking and the NAO
Can multi-annual variations in the frequency of North Atlantic atmospheric blocking and mid-latitude circulation regimes be skilfully predicted? Recent advances in seasonal forecasting have shown that mid-latitude climate variability does exhibit significant predictability. However, atmospheric predictability has generally been found to be quite limited on multi-annual timescales. New decadal prediction experiments from NCAR are found to exhibit remarkable skill in reproducing the observed multi-annual variations of wintertime blocking frequency over the North Atlantic and of the North Atlantic Oscillation (NAO) itself. This is partly due to the large ensemble size that allows the predictable component of the atmospheric variability to emerge from the background chaotic component. The predictable atmospheric anomalies represent a forced response to oceanic low-frequency variability that strongly resembles the Atlantic Multi-decadal Variability (AMV), correctly reproduced in the decadal hindcasts thanks to realistic ocean initialization and ocean dynamics. The occurrence of blocking in certain areas of the Euro-Atlantic domain determines the concurrent circulation regime and the phase of known teleconnections, such as the NAO, consequently affecting the stormtrack and the frequency and intensity of extreme weather events. Therefore, skilfully predicting the decadal fluctuations of blocking frequency and the NAO may be used in statistical predictions of near-term climate anomalies, and it provides a strong indication that impactful climate anomalies may also be predictable with improved dynamical models.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
Learning the right channel in multimodal imaging: automated experiment in piezoresponse force microscopy
We report the development and experimental implementation of the automated experiment workflows for the identification of the best predictive channel for a phenomenon of interest in spectroscopic measurements. The approach is based on the combination of ensembled deep kernel learning for probabilistic predictions and a basic reinforcement learning policy for channel selection. It allows the identification of which of the available observational channels, sampled sequentially, are most predictive of selected behaviors, and hence have the strongest correlations. We implement this approach for multimodal imaging in piezoresponse force microscopy (PFM), with the behaviors of interest manifesting in piezoresponse spectroscopy. We illustrate the best predictive channel for polarization-voltage hysteresis loop and frequency-voltage hysteresis loop areas is amplitude in the model samples. The same workflow and code are applicable for any multimodal imaging and local characterization methods.
36 MATERIALS SCIENCE↗
The NASA Severe Thunderstorm Observations and Regional Modeling (NASA STORM) Project
The NASA Severe Storm Thunderstorm Observations and Regional Modeling(NASA STORM) project enhanced NASA’s severe weather research capabilities, building upon existing Earth Science expertise at NASA Marshall Space Flight Center (MSFC). During this project, MSFC extended NASA’s ground-based lightning detection capacity to include a readily deployable lightning mapping array (LMA). NASA STORM also enabled NASA’s Short-term Prediction and Research Transition (SPoRT) to add convection allowing ensemble modeling to its portfolio of regional numerical weather prediction (NWP) capabilities. As a part of NASA STORM, MSFC developed new open-source capabilities for analyzing and displaying weather radar observations integrated from both research and operational networks. These accomplishments enabled by NASA STORM are a step towards enhancing NASA’s capabilities for studying severe weather and positions them for any future NASA related severe storm field campaigns.
modeling↗
Designing an Optimal Ensemble Strategy for GMAO S2S Forecast System
GMAO Sub/Seasonal prediction system (S2S) is being readied for a major upgrade to GEOS-S2S Version 3. An important factor in successful extended range forecast is the definition of an ensemble For initialization of the ensemble we propose a combination of lagged and burst initial conditions. We plan to run a relatively large ensemble of 40 members for sub-seasonal forecast (up to 3 months), at which point we sub-sample the ensemble, and continue the forecast with 10 members (up to 12 months). Here we present the results of the extensive testing of various ways to generate the perturbations to the initial conditions and the validation of the stratified sampling strategy we chose.To generate perturbations for the burst ensemble members we used scaled differences of pairs of analysis states separated by 1-10 days, randomly chosen from a corresponding season. We considered perturbing separately only the atmospheric fields or only the ocean or both of the forecast initial conditions. Considering varying separation times between the analysis states, we were able to produce perturbations sampling various modes of variability. Focusing on the ENSO SST indices, we found that all types of perturbations are important for the ensemble spread.Our ensemble size for sub-seasonal forecasts was determined as to maximize the skill of predicting some of the leading modes of boreal winter atmospheric modes, NAO, PNA and AO. It is not feasible to run equally large ensemble for seasonal forecasts. Using a stratified sampling procedure we can identify the emerging directions of error growth. By comparing the stratified ensemble with randomly sampled ensemble of the same size, we were able to show that the former better estimates the mean of the original large ensemble.
Borovikov, Anna↗
Data-driven prediction of scaling and ignition of inertial confinement fusion experiments
Recent advances in inertial confinement fusion (ICF) at the National Ignition Facility (NIF), including ignition and energy gain, are enabled by a close coupling between experiments and high-fidelity simulations. Neither simulations nor experiments can fully constrain the behavior of ICF implosions on their own, meaning pre- and postshot simulation studies must incorporate experimental data to be reliable. Linking past data with simulations to make predictions for upcoming designs and quantifying the uncertainty in those predictions has been an ongoing challenge in ICF research. We have developed a data-driven approach to prediction and uncertainty quantification that combines large ensembles of simulations with Bayesian inference and deep learning. The approach builds a predictive model for the statistical distribution of key performance parameters, which is jointly informed by past experiments and physics simulations. The prediction distribution captures the impact of experimental uncertainty, expert priors, design changes, and shot-to-shot variations. We have used this new capability to predict a 10× increase in ignition probability between Hybrid-E shots driven with 2.05 MJ compared to 1.9 MJ, and validated our predictions against subsequent experiments. We describe our new Bayesian postshot and prediction capabilities, discuss their application to NIF ignition and validate the results, and finally investigate the impact of data sparsity on our prediction results.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Inferring safety critical events from vehicle kinematics in naturalistic driving environment: Application of deep learning Algorithms
Advances in sensing technology has enabled the collection of countless terabytes of second-by-second kinematics data. Such data provides opportunities for real-time monitoring of driving behavior and identification of safety critical events (SCEs) including crashes and near crashes. The concept of volatility is relevant in this context, which identifies instability and erratic variations in driving behavior prior to involvement in SCEs. This study utilized vehicle kinematics from a large-scale naturalistic driving data to develop a deep learning approach based on 1D convolutional neural networks (CNN) for inferring SCEs. The data are unique in the sense that such accurate pre-crash data at high fidelity are not available in traditional crash repositories. This study contributes to the literature by providing a first attempt at predicting responses to SCEs by developing deep learning-based CNN architectures using novel driving volatility based kinematic thresholds for a sample of 9553 events. The key contribution lies in developing a volatility-based CNN input layout that is acceptable to CNN schemes and represents the motion kinematics such as speed, acceleration and volatility measures. Several 1D-CNN architectures were developed using layers, numbers of convolutions, layer patterns, and kernels. Shallow and deep architectures were tested, revealing higher accuracy of shallow architectures in detecting SCEs. The optimal number of epochs were identified using an early stopping method while the CNN performance was improved by increasing the number of epochs. The ensemble CNN had the highest predictive accuracy of 95.6% for detection of crashes and near crashes, which was 2.5% higher than the optimal CNN using 20% hold out test data. The ensemble CNN also outperformed classical machine learning models and model performance reported in past studies on detection of SCEs. Finally, these results have implications for identification of safety hotspots and providing real-time alerts and warnings in connected and highly automated vehicle environment including society of automotive engineers levels 3–5.
42 ENGINEERING↗
Ecological niche models display nonlinear relationships with abundance and demographic performance across the latitudinal distribution of Astragalus utahensis (Fabaceae)
Abstract The potential for ecological niche models (ENMs) to accurately predict species' abundance and demographic performance throughout their geographic distributions remains a topic of substantial debate in ecology and biogeography. Few studies simultaneously examine the relationship between ENM predictions of environmental suitability and both a species' abundance and its demographic performance, particularly across its entire geographic distribution. Yet, studies of this type are essential for understanding the extent to which ENMs are a viable tool for identifying areas that may promote high abundance or performance of a species or how species might respond to future climate conditions. In this study, we used an ensemble ecological niche model to predict climatic suitability for the perennial forb Astragalus utahensis across its geographic distribution. We then examined relationships between projected climatic suitability and field‐based measures of abundance, demographic performance, and forecasted stochastic population growth (λ s ). Predicted climatic suitability showed a J‐shaped relationship with A. utahensis abundance, where low‐abundance populations were associated with low‐to‐intermediate suitability scores and abundance increased sharply in areas of high predicted climatic suitability. A similar relationship existed between climatic suitability and λ s from the center to the northern edge of the latitudinal distribution. Patterns such as these, where density or demographic performance only increases appreciably beyond some threshold of climatic suitability, support the contention that ENM‐predicted climatic suitability does not necessarily represent a reliable predictor of abundance or performance across large geographic regions.
Baer, Kathryn C.↗
Machine learning materials properties with accurate predictions, uncertainty estimates, domain guidance, and persistent online accessibility
One compelling vision of the future of materials discovery and design involves the use of machine learning (ML) models to predict materials properties and then rapidly find materials tailored for specific applications. However, realizing this vision requires both providing detailed uncertainty quantification (model prediction errors and domain of applicability) and making models readily usable. At present, it is common practice in the community to assess ML model performance only in terms of prediction accuracy (e.g. mean absolute error), while neglecting detailed uncertainty quantification and robust model accessibility and usability. Here, we demonstrate a practical method for realizing both uncertainty and accessibility features with a large set of models. We develop random forest ML models for 33 materials properties spanning an array of data sources (computational and experimental) and property types (electrical, mechanical, thermodynamic, etc). All models have calibrated ensemble error bars to quantify prediction uncertainty and domain of applicability guidance enabled by kernel-density-estimate-based feature distance measures. All data and models are publicly hosted on the Garden-AI infrastructure, which provides an easy-to-use, persistent interface for model dissemination that permits models to be invoked with only a few lines of Python code. We demonstrate the power of this approach by using our models to conduct a fully ML-based materials discovery exercise to search for new stable, highly active perovskite oxide catalyst materials.
domain of applicability↗
Integrating multimodal data through interpretable heterogeneous ensembles
Motivation: Integrating multimodal data represents an effective approach to predicting biomedical characteristics, such as protein functions and disease outcomes. However, existing data integration approaches do not sufficiently address the heterogeneous semantics of multimodal data. In particular, early and intermediate approaches that rely on a uniform integrated representation reinforce the consensus among the modalities but may lose exclusive local information. The alternative late integration approach that can address this challenge has not been systematically studied for biomedical problems. Results: We propose Ensemble Integration (EI) as a novel systematic implementation of the late integration approach. EI infers local predictive models from the individual data modalities using appropriate algorithms and uses heterogeneous ensemble algorithms to integrate these local models into a global predictive model. We also propose a novel interpretation method for EI models. We tested EI on the problems of predicting protein function from multimodal STRING data and mortality due to coronavirus disease 2019 (COVID-19) from multimodal data in electronic health records. We found that EI accomplished its goal of producing significantly more accurate predictions than each individual modality. It also performed better than several established early integration methods for each of these problems. The interpretation of a representative EI model for COVID-19 mortality prediction identified several disease-relevant features, such as laboratory test (blood urea nitrogen and calcium) and vital sign measurements (minimum oxygen saturation) and demographics (age). These results demonstrated the effectiveness of the EI framework for biomedical data integration and predictive modeling.
59 BASIC BIOLOGICAL SCIENCES↗
The Role of Multiscale Interaction in Tropical Cyclogenesis and Its Predictability in Near-Global Aquaplanet Cloud-Resolving Simulations
Tropical cyclogenesis (TCG) is a multiscale process that involves interactions between large-scale circulation and small-scale convection. A near-global aquaplanet cloud-resolving model (NGAqua) with 4-km horizontal grid spacing that produces tropical cyclones (TCs) is used to investigate TCG and its predictability. This study analyzes an ensemble of three 20-day NGAqua simulations, with initial white-noise perturbations of low-level humidity. TCs develop spontaneously from the northern edge of the intertropical convergence zone (ITCZ), where large-scale flows and tropical convection provide necessary conditions for barotropic instability. Zonal bands of positive low-level absolute vorticity organize into cyclonic vortices, some of which develop into TCs. A new algorithm is developed to track the cyclonic vortices. A vortex-following framework analysis of the low-level vorticity budget shows that vertical stretching of absolute vorticity due to convective heating contributes positively to the vorticity spinup of the TCs. A case study and composite analyses suggest that sufficient humidity is key for convective development. TCG in these three NGAqua simulations undergoes the same series of interactions. The locations of cyclonic vortices are broadly predetermined by planetary-scale circulation and humidity patterns associated with ITCZ breakdown, which are predictable up to 10 days. Whether and when the cyclonic vortices become TCs depend on the somewhat more random feedback between convection and vorticity.
54 ENVIRONMENTAL SCIENCES↗
A Monte Carlo Uncertainty Analysis of Ozone Trend Predictions in a Two Dimensional Model
We use Monte Carlo analysis to estimate the uncertainty in predictions of total O3 trends between 1979 and 1995 made by the Goddard Space Flight Center (GSFC) two-dimensional (2D) model of stratospheric photochemistry and dynamics. The uncertainty is caused by gas-phase chemical reaction rates, photolysis coefficients, and heterogeneous reaction parameters which are model inputs. The uncertainty represents a lower bound to the total model uncertainty assuming the input parameter uncertainties are characterized correctly. Each of the Monte Carlo runs was initialized in 1970 and integrated for 26 model years through the end of 1995. This was repeated 419 times using input parameter sets generated by Latin Hypercube Sampling. The standard deviation (a) of the Monte Carlo ensemble of total 03 trend predictions is used to quantify the model uncertainty. The 34% difference between the model trend in globally and annually averaged total O3 using nominal inputs and atmospheric trends calculated from Nimbus 7 and Meteor 3 total ozone mapping spectrometer (TOMS) version 7 data is less than the 46% calculated 1 (sigma), model uncertainty, so there is no significant difference between the modeled and observed trends. In the northern hemisphere midlatitude spring the modeled and observed total 03 trends differ by more than 1(sigma) but less than 2(sigma), which we refer to as marginal significance. We perform a multiple linear regression analysis of the runs which suggests that only a few of the model reactions contribute significantly to the variance in the model predictions. The lack of significance in these comparisons suggests that they are of questionable use as guides for continuing model development. Large model/measurement differences which are many multiples of the input parameter uncertainty are seen in the meridional gradients of the trend and the peak-to-peak variations in the trends over an annual cycle. These discrepancies unambiguously indicate model formulation problems and provide a measure of model performance which can be used in attempts to improve such models.
Considine, D. B.↗
Predictability and Dynamics of Hurricane Joaquin (2015) Explored through Convection-Permitting Ensemble Sensitivity Experiments
Explore the source record for details and available documents.
Robert G. Nystrom↗