Engineering Papers⌕ Search

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.

At least 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Accelerated Depth Computation for Surface Boxplots with Deep Learning

Functional depth is a well-known technique used to derive descriptive statistics (e.g., median, quartiles, and outliers) for 1D data. Surface boxplots extend this concept to ensembles of images, helping scientists and users identify representative and outlier images. However, the computational time for surface boxplots increases cubically with the number of ensemble members, making it impractical for integration into visualization tools. In this paper, we propose a deep-learning solution for efficient depth prediction and computation of surface boxplots for time-varying ensemble data. Our deep learning framework accurately predicts member depths in a surface boxplot, achieving average speedups of 6X on a CPU and 15X on a GPU for the 2D Red Sea dataset with 50 ensemble members compared to the traditional depth computation algorithm. Our approach achieves at least a 99% level of rank preservation, with order flipping occurring only at pairs with extremely similar depth values that pose no statistical differences. This local flipping does not significantly impact the overall depth order of the ensemble members.

Han, Mengjiao↗
DOE OSTI2020

Testing the predictive power of theory for Pd x Ir (100-x) alloy nanoparticles for the oxygen reduction reaction

Here, density functional theory (DFT) calculations of O and OH binding energies on triatomic surface ensembles of Pd x Ir (100-x) nanoalloys successfully predicted the overall trend in experimental oxygen reduction reaction (ORR) activity as a function of nanoparticle (NP) composition. Specifically, triatomic Pd 3 ensembles were found to possess optimal O and OH binding energies and were predicted to be highly active sites for the ORR, rivaling that of Pt(111). However, DFT calculations suggest that the O binding energy increases at active sites containing Ir, thereby decreasing ORR activity. Pd x Ir (100-x) nanoalloys were synthesized using a microwave-assisted method and their activity towards the ORR was tested using rotating disk voltammetry (RDV). As predicted, the bimetallic electrocatalysts exhibited worse catalytic activity than the Pd-only NPs. The strong qualitative correlation between the theoretical and experimental results demonstrates that the activity of individual active sites on the surface of NPs can serve as a proxy for overall activity. This is a particularly useful strategy for applying DFT calculations to electrocatalysts that are too large for true first-principle analysis.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Data-driven closure modeling for hypersonic turbulent flows

The Reynolds-averaged Navier–Stokes (RANS) equations remain a workhorse technology for simulating compressible fluid flows of practical interest. Due to model-form errors, however, RANS models can yield erroneous predictions that preclude their use on mission-critical problems. This report summarizes work performed from FY22-FY24 focused on improving RANS models for hypersonic flows using data-driven modeling and scientific machine learning. In this work we: 1. Investigate the current capabilities of RANS models in Sandia’s parallel aerodynamics and re-entry code (SPARC) for hypersonic flows with a focus on shock boundary layer interactions (SBLIs), 2. Assess several established corrections that exist in the literature aimed at improving predictions for SBLIs, 3. Develop improved models for the Reynolds stress tensor using tensor-basis neural networks, 4. Develop a neural-network-based variable turbulent Prandtl number model to reduce errors in wall heating in SBLIs. 5. Begin future investigations including employing the LIFE framework to improve wall heating predictions in SBLIs as well as the ensemble Kalman filter. We find that current RANS models in SPARC are deficient for complex SBLI flows. In particular, no current model jointly predicts wall heat flux, wall shear stress, and wall pressure with reasonable accuracy. Existing corrections help, but do not alleviate this issue altogether. The development of improved models for the Reynolds stress tensor via tensor-basis neural networks results in more predictive RANS models across a suite of low-speed and high-speed cases. For hypersonic boundary layers, the inclusion of the wall-normal Reynolds stress via TBNNs has an appreciable impact on the wall-normal momentum balance and wall quantities. However, we find that improvements to the Reynolds stress tensor do not address the over-prediction in wall heat flux in SBLIs. We find that a neural-network-based variable turbulent Prandtl number model systematically and substantially improves wall heating predictions for a range of SBLI cases.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Systems and methods for modeling water quality

A system, method, device and computer-readable medium for creating an ensemble model of water quality. The ensemble model is generated by determining a set of optimal component models for spectral regions of a body of water, and combining the optimal models. The optimal models can be based on remote sensing data, including satellite imagery. A K-fold partition approach or a global approach can be used to determine the optimal component models, and the optimal component models can be combined through spectral space partition rules to generate an ensemble model of water quality. The ensemble model not only has improved water quality prediction ability, but also has strong spatial and temporal extensibility. The spatial and temporal extensibility of the ensemble model is fundamentally important and desirable for long-term and large-scale remote sensing monitoring and assessment of water quality.

Liu, Hongxing↗
DOE OSTI2023

Amundsen Sea Embayment ice-sheet mass-loss predictions to 2050 calibrated using observations of velocity and elevation change

Mass loss from the Amundsen Sea Embayment of the West Antarctic Ice Sheet is a major contributor to global sea-level rise (SLR) and has been increasing over recent decades. Predictions of future SLR are increasingly modelled using ensembles of simulations within which model parameters and external forcings are varied within credible ranges. Accurately reporting the uncertainty associated with these predictions is crucial in enabling effective planning for, and construction of defences against, rising sea levels. Calibrating model simulations against current observations of ice-sheet behaviour enables the uncertainty to be reduced. Here we calibrate an ensemble of BISICLES ice-sheet model simulations of ice loss from the Amundsen Sea Embayment using remotely sensed observations of surface elevation and ice speed. Each calibration type is shown to be capable of reducing the 90% credibility bounds of predicted contributions to SLR by 34 and 43% respectively.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

LTAU-FF: Loss Trajectory Analysis for Uncertainty in atomistic Force Fields

Model ensembles are effective tools for estimating prediction uncertainty in deep learning atomistic force fields. However, their widespread adoption is hindered by high computational costs and overconfident error estimates. In this work, we address these challenges by leveraging distributions of per-sample errors obtained during training and employing a distance-based similarity search in the model latent space. Our method, which we call LTAU (Loss Trajectory Analysis for Uncertainty), efficiently estimates the full probability distribution function of errors for any test point using the logged training errors, achieving speeds that are 2–3 orders of magnitudes faster than typical ensemble methods and allowing it to be used for tasks where training or evaluating multiple models would be infeasible. We apply LTAU towards estimating parametric uncertainty in atomistic force fields (LTAU-FF), demonstrating that it produces well-calibrated confidence intervals and predicts errors that correlate strongly with the true errors for data near the training domain. Furthermore, we show that the errors predicted by LTAU-FF can be used in practical applications for detecting out-of-domain data, tuning model performance, and predicting failure during simulations. We believe that LTAU will be a valuable tool for uncertainty quantification in atomistic force fields and is a promising method that should be further explored in other domains of machine learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Bayesian Optimized Deep Ensemble for Uncertainty Quantification of Deep Neural Networks: a System Safety Case Study on Sodium Fast Reactor Thermal Stratification Modeling

Deep neural networks (DNNs) are increasingly important to scientific computing and engineering system simulations. Accurate uncertainty quantification (UQ) for DNNs is critical in safety-sensitive engineering domains. Traditional Deep Ensemble (DE) methods, while easy to implement, frequently suffer from poorly calibrated uncertainty estimates and limited predictive accuracy due to reliance on fixed architectures with varied weight initializations. To address these issues, we introduce a workflow that combines Bayesian Optimization (BO) and DE. The workflow is modular, scalable, and integrates parallel BO initialized with Sobol sequences to individually optimize the hyperparameters of each ensemble member. This method enhances ensemble diversity, improves predictive accuracy, and provides reliable uncertainty estimates. We evaluate the proposed BODE approach in a sodium fast reactor thermal stratification modeling case study, where we used a densely connected convolutional neural network to predict turbulent viscosity during the reactor transient with consideration of data noise. We benchmark its performance against several optimization approaches, including baseline deep ensemble, evolutionary algorithm-optimized ensemble, ensemble formed via random search combined with greedy selection, and a BO ensemble using random initialization. Here, our results demonstrate superior performance of the developed BODE approach. In noise-free scenarios, BODE notably reduces incorrect aleatoric uncertainty and significantly enhances predictive accuracy. Under conditions of 5% and 10% Gaussian noise, BODE adaptively quantifies uncertainty proportional to data noise, achieving up to an 80% reduction in root mean square error compared to baseline methods and producing well-calibrated prediction intervals.

Bayesian optimization↗
NASA NTRS2017

Assimilation of AERONET and MODIS AOT Observations Using Variational and Ensemble Data Assimilation Methods and Its Impact on Aerosol Forecasting Skill

Data assimilation of Aerosol Robotic Network (AERONET) and Moderate Resolution Imaging Spectroradiometer (MODIS) aerosol optical thickness (AOT) for aerosol forecasting was tested within the Navy Aerosol Analysis Prediction System (NAAPS) framework, using variational and ensemble data assimilation methods. Navy aerosol forecasting currently makes use of a deterministic NAAPS simulation coupled to Navy Variational Data Assimilation System for aerosol optical depth, a two-dimensional variational data assimilation system, for MODIS AOT assimilation. An ensemble version of NAAPS (ENAAPS) coupled to an ensemble adjustment Kalman filter (EAKF) from the Data Assimilation Research Testbed was recently developed, allowing for a range of data assimilation and forecasting experiments to be run with deterministic NAAPS and ENAAPS. The main findings are that the EAKF, with its flow-dependent error covariances, makes better use of sparse observations such as AERONET AOT. Assimilating individual AERONET observations in the two-dimensional variational system can increase the analysis errors when observations are located in high AOT gradient regions. By including AERONET with MODIS AOT assimilation, the magnitudes of peak aerosol events (AOT> 1) were better captured with improved temporal variability, especially in India and Asia where aerosol prediction is a challenge. Assimilating AERONET AOT with MODIS had little impact on the 24 h forecast skill compared to MODIS assimilation only, but differences were found downwind of AERONET sites. The 24 h forecast skill was approximately the same for forecasts initialized with analyses from AERONET AOT assimilation alone compared to MODIS assimilation, particularly in regions where the AERONET network is dense; including the United States and Europe, indicating that AERONET could serve as a backup observation network for over-land synoptic-scale aerosol events.

Rubin, Juli I.↗
DOE OSTI2024

Accelerating the Discovery of New, Single Phase High Entropy Ceramics via Active Learning

High-entropy ceramics have garnered interest due to their remarkable hardness, compressive strength, thermal stability, and fracture toughness; yet the discovery of new high-entropy ceramics (out of a tremendous number of possible elemental permutations) still largely requires costly, inefficient, trial-and-error experimental and computational approaches. The entropy forming ability (EFA) factor was recently proposed as a computational descriptor that positively correlates with the likelihood that a 5-metal high-entropy carbide (HECs) will form the desired single phase, homogeneous solid solution; however, discovery of new compositions is computationally expensive. If you consider 8 candidate metals, the HEC EFA approach uses 49 optimizations for each of the 56 unique 5-metal carbides, requiring a total of 2744 costly density functional theory calculations. Here, we describe an orders-of-magnitude more efficient active learning (AL) approach for identifying novel HECs. To begin, we compared numerous methods for generating composition-based feature vectors (e.g., magpie and mat2vec), deployed an ensemble of machine learning (ML) models to generate an average and distribution of predictions, and then utilized the distribution as an uncertainty. Here we then deployed an AL approach to extract new training data points where the ensemble of ML models predicted a high EFA value or was uncertain of the prediction. Our approach has the combined benefit of decreasing the amount of training data required to reach acceptable prediction qualities and biases the predictions toward identifying HECs with the desired high EFA values, which are tentatively correlated with the formation of single phase HECs. Using this approach, we increased the number of 5-metal carbides screened from 56 to 15,504, revealing 4 compositions with record-high EFA values that were previously unreported in the literature. Our AL framework is also generalizable and could be modified to rationally predict optimized candidate materials/combinations with a wide range of desired properties (e.g., mechanical stability, thermal conductivity).

36 MATERIALS SCIENCE↗
DOE OSTI2021

Inference of Rock Flow and Mechanical Properties from Injection-Induced Microseismic Events During Geologic CO 2 Storage

Monitoring microseismic activities during CO 2 injection into geologic formations is important for ensuring the safety of the storage operations. The resulting data provide insight into the response of the storage formation to CO 2 injection and can be used to infer the underlying rock flow and mechanical properties. In this paper, assimilation of microseismic data is performed for dynamic characterization of the storage formation by using a stochastic simulation model to forecast the microseismic response of a geologic formation during CO 2 injection. Two modeling approaches are adopted to predict the space-time distribution of the injection-induced microseismicity. The first model is based on pore pressure relaxation assumption, while the second model uses coupled flow and geomechanics simulation to establish the complex physical relation between the storage formation properties and the corresponding microseismic responses during CO 2 injection. The stochastic predictive models in each case are used in ensemble data assimilation frameworks to estimate rock properties from the observed microseismic data. Two data assimilation methods are considered: (i) a new ensemble-based stochastic point process filter (EnPPF) that can directly integrate discrete microseismic events, and (ii) a variant of ensemble smoother, known as the ensemble smoother with multiple data assimilation (ES-MDA), which requires continuous representation of microseismic events for assimilation. The two methods are successfully applied to a geologically realistic model of the Farnsworth Field in Texas, with complex geologic flow units and interacting fault systems.

42 ENGINEERING↗
NASA NTRS2020

Modelling climate change impacts on maize yields under low nitrogen input conditions in sub‐Saharan Africa

Smallholder farmers in sub‐Saharan Africa (SSA) currently grow rainfed maize with limited inputs including fertilizer. Climate change may exacerbate current production constraints. Crop models can help quantify the potential impact of climate change on maize yields, but a comprehensive multimodel assessment of simulation accuracy and uncertainty in these low‐input systems is currently lacking. We evaluated the impact of varying [CO2], temperature and rainfall conditions on maize yield, for different nitrogen (N) inputs (0, 80, 160 kg N/ha) for five environments in SSA, including cool subhumid Ethiopia, cool semi‐arid Rwanda, hot subhumid Ghana and hot semi‐arid Mali and Benin using an ensemble of 25 maize models. Models were calibrated with measured grain yield, plant biomass, plant N, leaf area index, harvest index and in‐season soil water content from 2‐year experiments in each country to assess their ability to simulate observed yield. Simulated responses to climate change factors were explored and compared between models. Calibrated models reproduced measured grain yield variations well with average relative root mean square error of 26%, although uncertainty in model prediction was substantial (CV = 28%). Model ensembles gave greater accuracy than any model taken at random. Nitrogen fertilization controlled the response to variations in [CO2], temperature and rainfall. Without N fertilizer input, maize (i) benefited less from an increase in atmospheric [CO2], (ii) was less affected by higher temperature or decreasing rainfall and (iii) was more affected by increased rainfall because N leaching was more critical. The model inter-comparison revealed that simulation of daily soil N supply and N leaching plays a crucial role in simulating climate change impacts for low-input systems. Climate change and N input interactions have strong implications for the design of robust adaptation practices across SSA, because the impact of climate change will be modified if farmers intensify maize production with more mineral fertilizer.

Crop simulation model↗
DOE OSTI2024

A novel conditional generative model for efficient ensemble forecasts of state variables in large-scale geological carbon storage

Integrating monitoring data to efficiently update reservoir pressure and CO 2 plume distribution forecasts presents a significant challenge in geological carbon storage (GCS) applications. Inverse modeling techniques are commonly used to fuse observational data and refine reservoir model parameters, thereby improving state variable forecasts. However, these techniques often rely on linear or Gaussian assumptions, which can limit their effectiveness in accurately predicting state variables. Moreover, simulating large-scale three-dimensional (3D) GCS problems is computationally expensive, making iterative runs in inverse problems prohibitive. To address these challenges, we propose a conditional generative model utilizing the score-based diffusion method for real-time 3D pressure and saturation field distribution predictions. Our approach involves solving the score function with a mini-batch-based Monte Carlo estimator to generate labeled data. This data is subsequently employed to train a fully connected neural network, enabling it to learn the conditional sample generator within a supervised learning framework. This method enables the rapid generation of a large ensemble of predictions, facilitating comprehensive uncertainty quantification of state variables. Here we applied our method to forecast the dynamic 3D distributions of pressure and saturation fields over a 30-year injection period. The statistical assessment with low root mean square error (RMSE) values demonstrates that our method can accurately predict the spatiotemporal distributions of both pressure and saturation fields. Moreover, the developed conditional generative model shows high computational efficiency by generating 100 ensemble forecasts of 3D state variables in less than 10 min. The consistency between ensemble averages and ground truth values further illustrates the model’s capability to capture state variable dynamics during the CO 2 plume injection process. Notably, the ground truth values fall within the ensemble forecasts, indicating that our uncertainty quantification effectively captures variability and potential noise in the observations. Thus, the developed conditional generative model proves to be a more efficient, accurate, and practical tool for GCS applications, facilitating timely risk analysis and informed decision-making.

58 GEOSCIENCES↗
DOE OSTI2025

Improving Trustworthiness of Data-Driven Power Grid Contingency Analysis With Bayesian Residual Graph Neural Networks

The evolving energy landscape requires novel tools to efficiently perform contingency analysis and reliability assessment of power grids, potentially in real-time. The high computational cost of traditional power flow solvers limits their applicability in practice. Machine learning (ML) surrogates such as deep neural networks (NNs) accelerate power flow solvers computations, enabling high-order contingency analysis and real-time decision-making by learning highly nonlinear functions and integrating grid topology via graph architectures. However, (graph) NNs lack predictive power away from training data and do not provide predictive confidence estimates. Here, we present a Bayesian residual graph NN that integrates knowledge from low-fidelity data via residual training and embeds granular quantification of uncertainties, improving trustworthiness critical for high-consequence decision-making. Applying Bayesian concepts to NNs is challenging due to the high-dimensionality of both the parameter space, complicating derivation of a meaningful prior, and the output space in large grid systems, requiring enhanced techniques to assess the predicted high-dimensional uncertainties. Our contributions include: (1) Deriving a prior for fully connected and graph NNs that leverages low-fidelity data to guide mean predictions and appropriately control prior predictive uncertainty. (2) Integrating this prior within an ensembling with anchoring scheme for efficient approximate posterior inference. (3) Deriving enhanced metrics to assess accuracy of both the mean and uncertainty predictions in high dimensions, appropriately accounting for correlations propagated through graph layers. The resulting Bayesian residual graph NN is tested on a contingency analysis task for 14-bus and 118-bus grids.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Ensembles of Metastable States Govern Heterogeneous Catalysis on Dynamic Interfaces

Heterogeneous catalysis is at the heart of chemical industry. Being able to tune and design efficient catalysts for processes of interest is of an utmost importance, and for this, the molecular-level understanding of heterogeneous catalysts is the first step, and indeed a prime focus of the modern catalysis research. For a long time, a single most thermodynamically stable structure of the catalytic interface attained in reaction conditions had been envisioned as the reactive phase. However, some catalytic interfaces continue to undergo structural dynamics in the steady state, triggered by high temperatures, pressures, and binding and changing reagents. Among particularly dynamic interfaces are such widely-used catalysts as crystalline and amorphous surfaced supporting (sub-)nano metallic clusters. Recently, it became clear that this dynamic fluxionality causes the supported clusters to populate many distinct structural and stoichiometric states in catalytic conditions. Hence, the catalytic interface should be viewed as an evolving statistical ensemble of many (not one) structures. As such, every member in the ensemble contributes to the properties of the catalyst differently, and in proportion to its probability to be populated. This new notion flips the established paradigm and calls for new theory, modeling approaches, operando measurements, and updated design strategies. The statistical ensemble nature of surface-supported sub-nano cluster catalysts can be exemplified by oxide-supported and adsorbate-covered Pt, Pd, Cu, CuPd clusters, catalytic toward oxidative and non-oxidative dehydrogenation. They have access to a variety of 3D and quasi-2D shapes. The compositions of their thermal ensembles are dependent on the cluster size, leading to size-specific catalytic activities and the famous “every atom counts” phenomenon. The support and adsorbates affect catalyst structures, and state of the reacting species causes the ensemble to change in every reaction intermediate. The most stable member of the ensemble dominates the thermodynamic properties of the corresponding intermediate, whereas the kinetics can be determined by more active but less populated metastable catalyst states, and that suggests that many earlier studies might have overlooked the actual active sites. Both effects depend on the relative time-scales of catalyst restructuring and reaction dynamics. The catalyst may routinely operate off-equilibrium. Ensemble phenomena lead to surprising exceptions from established rules of catalysis, such as scaling relations, and Arrhenius behavior. Catalyst deactivation is also an ensemble property, and its extent of mitigation can be predicted through the new paradigm. These findings were enabled by advances in theory, such as global optimization and subsequent utilization of multiple local minima, and pathways sampling, as well as operando catalyst characterization. The fact that the per-site and per-species resolution is needed for the description and predicting of catalyst properties gives theory the central role in catalysis research, as most experiments provide ensemble-average information and cannot detect the crucial minority species that may be responsible for the catalytic activity.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Lithium-Ion Battery Diagnostics Using Electrochemical Impedance via Machine-Learning

Diagnosing battery states such as health, state-of-charge, or temperature is crucial for ensuring the safety and reliability of electrochemical energy storage systems. While some states, such as temperature, may be measured using cheap sensors, accurate diagnosis of battery health metrics usually requires time-consuming performance measurements, making them infeasible for use in real-world operation. These health metrics can be measured during lab-testing and then estimated on-line using predictive life models or via state observer algorithms such as Kalman filters, but these predictive methods should be supplemented by actual measurement of battery health whenever possible to ensure reliability. Rapid measurement of battery health may be done by various types of fast diagnostic techniques such as electrochemical impedance spectroscopy (EIS), which can be performed in only a few minutes and require only a fraction of the energy and power needed for a full charge and discharge measurement. But there is a substantial challenge for estimating battery health using EIS data, as EIS is sensitive to cell temperature, state-of-charge, current, and resting time in addition to health. Thus, utilizing EIS data to predict battery capacity requires correcting for all these additional variables, a task that is extremely difficult to handle analytically. This talk utilizes machine-learning methods to estimate the effectiveness of battery capacity prediction from EIS data, leveraging a data set of hundreds of EIS measurements recorded at varying temperature and state-of-charge throughout a 500-day aging study of 32 commercial, large-format NMC-Graphite lithium-ion batteries. Using EIS as input to machine-learning models is complicated by the nonlinear response of impedance to battery health, temperature, and state-of-charge, as well as the collinearity between the impedance response at neighboring frequencies, which can easily lead to overfit models. To train robust models, features from EIS data need to be extracted from the data or some subset of critical frequencies selected. Many approaches for extracting and selecting features from EIS data from electrochemical analysis and machine-learning fields were identified for analysis: using the entire raw spectra; selection of one, two, or many frequencies from the entire spectra; selecting interesting points from the EIS measurement using domain knowledge; fitting EIS with an equivalent-circuit model; calculating statistics on the raw impedance values; and reducing the dimensionality of the data using unsupervised linear (principal component analysis) and non-linear (uniform manifold approximation and projection) methods. These approaches were rigorously compared using a machine-learning pipeline approach, training linear, Gaussian process, and random forest regression models and quantifying performance using cross-validation as well as a held-out test set. An artificial neural network model trained on the raw spectra was also tested. Promising pipelines were fine-tuned via Bayesian hyperparameter optimization using cross-validation loss and training with class-specific weights to counter data set imbalance. The most reliable method for utilizing impedance in this work was the selection of two optimal frequencies through an exhaustive search, resulting in about 2% mean absolute error on test data for both Gaussian process and random forest model architectures. Interrogation of a variety of models reveals critical frequencies of 100 Hz and 103 Hz for this data set, though the optimal set of frequencies is not necessarily intuitive, i.e., the best performing models are not simply those that use impedance at frequencies that have the highest correlation to the relative discharge capacity. The best performing model is an ensemble model, which is able to predict battery capacity with 1.9% mean absolute error for unseen cells using impedance recorded at a variety of temperatures and states-of-charge.

battery↗
DOE OSTI2023

Laser Wakefield Accelerator modelling with Variational Neural Networks

A machine learning model was created to predict the electron spectrum generated by a GeV-class laser wakefield accelerator. The model was constructed from variational convolutional neural networks, which mapped the results of secondary laser and plasma diagnostics to the generated electron spectrum. An ensemble of trained networks was used to predict the electron spectrum and to provide an estimation of the uncertainty of that prediction. It is anticipated that this approach will be useful for inferring the electron spectrum prior to undergoing any process that can alter or destroy the beam. In addition, the model provides insight into the scaling of electron beam properties due to stochastic fluctuations in the laser energy and plasma electron density.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

Global fire modelling and control attributions based on the ensemble machine learning and satellite observations

Contemporary fire dynamics is one of the most complex and least understood land surface phenomena. Global fire controls related to climate, vegetation, and anthropogenic activity are usually intertwined, and difficult to disentangle in a quantitative way. Here, we leveraged an ensemble of five machine learning (ML) models and multiple satellite-based observations to conduct global fire modeling for three fire metrics (burned area, fire number, and fire size), and quantified driving mechanisms underlying annual fire changes in a spatially resolved manner for the period 2003–2019. Ensemble learning is a meta-approach that combines multiple ML predictions to improve accuracy, robustness, and generalization performance. We found that the optimized ensemble ML well reproduced annual dynamics of global burned area (R 2 = 0.90, P < 0.001), total fire numbers (R 2 = 0.86, P < 0.001), and averaged fire size (R 2 = 0.70, P < 0.001). Additionally, the ensemble ML captured key spatial patterns of multi-year mean magnitudes, annual variabilities, anomalies, and trends for different fire metrics. Our ML-based fire attributions further highlighted the dominant role of enhanced anthropogenic activity in reducing global burned area (–1.9 Mha/yr, P < 0.01), followed by climate control (–1.3 Mha/yr, P < 0.01) and insignificant positive vegetation control (0.4 Mha/yr, P = 0.60). Spatially, climate dominated a much larger burned area (53.7%) than human (23.4%) or vegetation control (22.9%); however, the counteracting effects from regional wetting and drying trends weakened the net climate impacts on global burned area. The fire number and fire size exhibited similar spatial control patterns with burned area; globally, however, fire number tended to be more affected by climate while fire size more influenced by human activities. Overall, our study confirmed the feasibility and efficiency of ensemble ML in global fire modeling and subsequent control attributions, providing a better understanding of contemporary fire regimes and contributing to robust fire projections in a changing environment.

54 ENVIRONMENTAL SCIENCES↗