Evaluating generative models in high energy physics
Not Available
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
SEARCH · Engineering Papers
Results for “deep generative models”
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.
Multi-fidelity Fourier neural operator for fast modeling of large-scale geological carbon storage
Deep learning-based surrogate models have been widely applied in geological carbon storage (GCS) problems to accelerate the prediction of reservoir pressure and CO2 plume migration. Large amounts of data from physics-based numerical simulators are required to train a model to accurately predict the complex physical behaviors associated with this process. In practice, the available training data are always limited in large-scale 3D problems due to the high computational cost. Therefore, we propose to use a multi-fidelity Fourier neural operator (FNO) to solve large-scale GCS problems with more affordable multi-fidelity training datasets. FNO has a desirable grid-invariant property, which simplifies the transfer learning procedure between datasets with different discretization. Here, we first test the model efficacy on a GCS reservoir model being discretized into 110 k grid cells. The multi-fidelity model can predict with accuracy comparable to a high-fidelity model trained with the same amount of high-fidelity data with 81% less data generation costs. We further test the generalizability of the multi-fidelity model on a same reservoir model with a finer discretization of 1 million grid cells. This case was made more challenging by employing high-fidelity and low-fidelity datasets generated by different geostatistical models and reservoir simulators. We observe that the multi-fidelity FNO model can predict pressure fields with reasonable accuracy even when the high-fidelity data are extremely limited. The findings of this study can help for better understanding of the transferability of multi-fidelity deep learning surrogate models.
58 GEOSCIENCES↗
Development of a Full-Scale Connected U-Net for Reflectivity Inpainting in Spaceborne Radar Blind Zones
CloudSat’s Cloud Profiling Radar is a valuable tool for remotely monitoring high-latitude snowfall, but its ability to observe hydrometeor activity near the Earth’s surface is limited by a radar blind zone caused by ground clutter contamination. This study presents the development of a deeply supervised U-Net-style convolutional neural network to predict cold season reflectivity profiles within the blind zone at two Arctic locations. The network learns to predict the presence and intensity of near-surface hydrometeors by coupling latent features encoded in blind zone-aloft clouds with additional context from collocated atmospheric state variables (i.e., temperature, specific humidity, and wind speed). Results show that the U-Net predictions outperform traditional linear extrapolation methods, with low mean absolute error, a 38% higher Sørensen–Dice coefficient, and vertical reflectivity distributions 60% closer to observed values. The U-Net is also able to detect the presence of near-surface cloud with a critical success index (CSI) of 72% and cases of shallow cumuliform snowfall and virga with 18% higher CSI values compared to linear methods. An explainability analysis shows that reflectivity information throughout the scene, especially at cloud edges and at the 1.2-km blind zone threshold, along with atmospheric state variables near the tropopause, are the most significant contributors to model skill. This surface-trained generative inpainting technique has the potential to enhance current and future remote sensing precipitation missions by providing a better understanding of the nonlinear relationship between blind zone reflectivity values and the surrounding atmospheric state.
54 ENVIRONMENTAL SCIENCES↗
Short-term solar radiation forecast using total sky imager via transfer learning
Ground-based sky cameras, which capture hemispherical images, have been extensively used for localized monitoring of clouds. This paper proposes a short-term forecasting approach based on transfer learning using Total Sky-Imager (TSI) images of the Southern Great Plains (SGP) site obtained from the Atmospheric Radiation Measurement (ARM) dataset. An accurate estimation of solar irradiance using TSI is key for short-term solar energy generation forecasting and optimal energy consumption planning. We make use of deep neural network architectures such as AlexNet and ResNet-101 to extract the underlying deep convolution features from TSI images and then train using an ensemble learning approach to model and forecast solar radiation. We demonstrate the performance of the proposed approach by showcasing the best and worst cases. Thus, the transfer learning approach significantly reduces the time and resources required for modeling solar radiation. We outperform with reference to another state-of-art technique for solar modeling using TSI images at different forecast lead times.
54 ENVIRONMENTAL SCIENCES↗
Deep learning model for fast, science-based forecasting of fluid migration along faults in geologic carbon storage scenarios
Effective long-term geologic storage depends on robust site selection and credible, science-based forecasting of subsurface behavior to ensure storage integrity. For this work, we develop a deep learning–based reduced-order model (ROM) to quantify potential carbon dioxide (CO₂) and brine migration through geological faults. The ROM combines a Transformer model for binary classification and a Stacked Ensemble for regression, trained on a comprehensive dataset generated from 1400 physics-based reservoir simulations. Key geologic and operational parameters—including fault geometry, reservoir structure, and injection conditions—were systematically varied to capture a wide range of fluid migration scenarios. The ROM accurately predicts the onset of migration, cumulative migration volumes of both CO₂ and brine, and associated migration rates, as compared to an independent set of validation simulations, while significantly reducing computational cost compared to traditional simulation methods. Model performance was evaluated across diverse fault configurations, revealing that shallow reservoir geometry and fault angle are among the most influential factors governing migration behavior. Sensitivity analysis using SHapley Additive exPlanations (SHAP) provided interpretability, revealing distinct patterns in how geological and operational features drive transient versus cumulative migration outcomes. The ROM’s ability to rapidly simulate fault migration scenarios enables efficient sensitivity analyses, scenario evaluations, and decision support for site selection and monitoring design. This approach enhances the safety, scalability, and long-term operational performance of geologic carbon storage (GCS) systems by providing a robust, interpretable tool for predicting subsurface fluid migration and assessing fault-related migration potential.
42 ENGINEERING↗
Learning genetic perturbation effects with variational causal inference
Advances in sequencing technologies have enhanced the understanding of gene regulation in cells. In particular, Perturb-seq has enabled high-resolution profiling of the transcriptomic response to genetic perturbations at the single-cell level. This understanding has implications in functional genomics and potentially for identifying therapeutic targets. Various computational models have been developed to predict perturbational effects. While deep learning models excel at interpolating observed perturbational data, they tend to overfit in the lack of enough data and may not generalize well to unseen perturbations. In contrast, mechanistic models, such as linear causal models based on gene regulatory networks, hold greater potential for extrapolation, as they encapsulate regulatory information that can predict responses to unseen perturbations. However, their application has been limited to small studies due to overly simplistic assumptions, making them less effective in handling noisy, large-scale single-cell data. We propose a hybrid approach that combines a mechanistic causal model with variational deep learning, termed Single Cell Causal Variational Autoencoder (SCCVAE). The mechanistic model employs a learned regulatory network to represent perturbational changes as shift interventions that propagate through the learned network. SCCVAE integrates this mechanistic causal model into a variational autoencoder, generating rich, comprehensive transcriptomic responses. Our results indicate that SCCVAE exhibits superior performance over current state-of-the-art baselines for extrapolating to predict unseen perturbational responses. Additionally, for the observed perturbations, the latent space learned by SCCVAE allows for the identification of functional perturbation modules and simulation of single-gene knockdown experiments of varying penetrance, presenting a robust tool for interpreting and interpolating perturbational responses at the single-cell level.
59 BASIC BIOLOGICAL SCIENCES↗
Molecular Vision - Multimodal, multitask retrieval of molecular structure from measured signatures for reference-free compound identification
We are currently at risk of generating false conclusions based on limited methods to identify small molecules in biological systems and in chemical forensics. By definition, the chemical structures of novel small molecules have not been determined, let alone measured or synthesized. Currently, unambiguous structure determination of small molecules is constrained by the time and effort needed to isolate compounds and perform de novo structure elucidation using laboratory-based methods, significantly extending the time to inform mitigation strategies. To address this gap, we have developed a deep learning approach to directly map molecular structure to experimental signatures. We aim to unify measurement technologies employed in untargeted small molecule identification studies—such as infrared (IR) spectrometry, tandem mass spectrometry (MS/MS), ion mobility spectrometry-derived collision cross section (CCS)—through use of a multimodal, multitask deep learning architecture. Where existing methods require direct generation of information-rich spectra and/or properties, an inherently difficult task, we will simplify molecular signature-based identification by posing the problem as a recognition or retrieval task. The model is thus presented with relevant endpoints – structure and one or more molecular signatures – and need only determine whether they are semantically related. Thus, our approach offers the following advantages over existing techniques: (i) circumvents difficulties associated with direct generation of molecular signatures from structure and structure from signatures; (ii) incorporates multiple molecular signatures simultaneously, as available, to support identification; and (iii) enables rapid computation of structural embeddings toward broad coverage of known chemical space. Taken together, the approach removes the need to explicitly obtain or compute reference spectra, representing a powerful method for compound identification that requires only experimentally observed signatures.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
The Study of Clusters of Galaxies and Large Scale Structures
The work on the ROSAT Deep Survey has been successfully completed. A number of interesting results have been established within this joint MPE, Cal Tech, JHU, ST Scl, ESO collaboration. First, a very large fraction, 70-80 percent, of the X-ray background has been directly resolved into point sources. We have derived a new log N-log S for X- ray sources and have measured a source density of 970 sources per square degree at a limiting flux level of 10(exp -15)/erg s sq cm (0.5-2.0 keV). Care was taken in these studies to accurately model and measure the effects of sources confusion. This was possible because of our observing strategy which included both deep PSPC and HRI observations. In the last year we initiated work in the design and development of the Next Generation Space Telescope.
Source record↗
Validation of a Low-Thrust Mission Design Tool Using Operational Navigation Software
Design of flight trajectories for missions employing solar electric propulsion requires a suitably high-fidelity design tool. In this work, the Evolutionary Mission Trajectory Generator (EMTG) is presented as a medium-high fidelity design tool that is suitable for mission proposals. EMTG is validated against the high-heritage deep-space navigation tool MIRAGE, demonstrating both the accuracy of EMTG's model and an operational mission design and navigation procedure using both tools. The validation is performed using a benchmark mission to the Jupiter Trojans.
Englander, Jacob A.↗
Validation of a Low-Thrust Mission Design Tool Using Operational Navigation Software
Design of flight trajectories for missions employing solar electric propulsion requires a suitably high-fidelity design tool. In this work, the Evolutionary Mission Trajectory Generator (EMTG) is presented as a medium-high fidelity design tool that is suitable for mission proposals. EMTG is validated against the high-heritage deep-space navigation tool MIRAGE, demonstrating both the accuracy of EMTG's model and an operational mission design and navigation procedure using both tools. The validation is performed using a benchmark mission to the Jupiter Trojans.
Englander, Jacob A.↗
Advancing Wildfire Monitoring with TEMPO and ML tools: Hourly Smoke and Fire‑Front Mapping and Near‑Surface NO₂ Predictions
Wildfires impose substantial impacts on communities and regions downwind of wildfire smoke. We present a TEMPO‑enabled workflow that generates value‑added Level‑3 smoke‑plume masks and fire‑front maps for large wildfires, such as 2024 Park Fire, using the self‑supervised deep learning system SIT‑FUSE, along with near‑surface NO₂ predictions produced by a foundation model (Microsoft Aurora). We conclude by outlining a roadmap for expanding these capabilities to additional Western U.S. wildfire events and for delivering actionable tools to stakeholders. This open-source, reproducible workflow provides a scalable framework for cross-agency wildfire monitoring to overcome traditional limitations in smoke-cloud discrimination and air-quality forecasting by incorporating TEMPO data and beyond.
Xiaohua Pan↗
From Detector Layout to Signal Analysis: Geometry Optimization and Neutron-Gamma Tagging in Plastic Scintillator Detectors
Neutrinos are elementary particles with many properties still unknown. Their masses so far have only upper and lower limits. Still, due to neutrino oscillations, it is clear that they are not massless, as stated by the Standard Model of Elementary Particles. Neutrinos are also present in the Universe in vast amounts, but they rarely interact with the surrounding matter. Their abundance makes them very interesting for many theories beyond the Standard Model, e.g., dark matter searches and CP symmetry violation in the leptonic sector, which could be (partially) responsible for the observed matter-antimatter asymmetry in today's Universe.\\ The Deep Underground Neutrino Experiment (DUNE) is a next-generation accelerator-based neutrino oscillation experiment that will study neutrinos with unprecedented precision and may answer many open questions. DUNE uses a powerful neutrino beam from Fermilab. It consists of a Near Detector (ND) complex to measure neutrinos before oscillat ion, and a Far Detector (FD) complex $1300\ \mathrm{km}$ away to measure them after oscillation. As part of the ND complex, measurements are also possible with different angles to the neutrino beam. This enables excellent control of systematic uncertainties of e.g., neutrino cross section measurements.\\ One detector in the near detector complex is The Muon Spectrometer (TMS), an extension of a Liquid Argon (LAr) detector that measures the charge and momentum of muons produced in neutrino interactions within the LAr. The design of this detector, which consists of alternating layers of steel and plastic scintillator bars, must be optimized for the expected muon energies.\\ In this thesis, a study of the optimal module orientation plan is presented, which is necessary for the physics performance of the near detector complex and, by extension, DUNE. As part of this study, the event reconstruction was also developed and improved. Simulated muons are then reconstructed, and the performan ce of different module orientation plans is tested.\\ As a second part, a study of neutron and gamma tagging using a Pulse Shape Discriminating (PSD) plastic scintillator is presented. The properties of this material allow particle differentiation based on the temporal distribution of emitted light. A novel approach to using the individual light signals was successfully tested using data from a small, local test setup.
Nehm, Asa [Mainz U.]↗
Natural Language Processing for Text Based Event Extraction: Identifying Events of Interest Related to Worldwide State-Sponsored Civil Nuclear Power
Beginning in FY20, SRNL was funded by the National Nuclear Security Administration’s Office of Defense Nuclear Non-Proliferation Research and Development to develop a prototype natural language processing/natural language understating machine learning-based modeling and analysis pipeline to extract and forecast events of interest from massive open data sources. The working hypothesis within the approach is that contextual shifts in key words and phrases act as indicators of events of interest over time. Therefore, by identifying points in time where contextual shifts occur, events of interest can be extracted along with explicit and implicit connections of entities and activities. The development of the preliminary prototype pipeline proved successful, meriting further testing of the pipeline on more broad topical domains and in a worldwide data environment. Therefore, SRNL, in collaboration with the Sanghani Center for Artificial Intelligence and Data Analytics at Virginia Tech, have continued development with a test case of identifying events of interest related to worldwide state-sponsored civil nuclear power in open data sources. In the first year of this follow-on effort, the team has curated domain-specific data corpuses using an automated scheme and applied the modeling and analysis pipeline. This robust, focused, and efficient approach consists of an ensemble of analyses applied to time dependent word embedding models that are trained on the data corpuses. In this report, the team has demonstrated the capability of the existing pipeline (as development has continued in parallel) by exploring several specific case-studies centered around Rosatom’s international activities regarding the planning, construction, operation, and/or shutdown of nuclear reactors. A basic timeline events has been generated by manually cataloging known “milestone” events that have occurred at reactors in Turkey, Finland, Hungary, and Egypt and compared with the output of the modeling pipeline. In this approach, the team has characterized the lead time using the prototype pipeline, as well as the ability to capture relevant information, which proved 100% successful. A deep dive example of the Akkuyu reactor (Turkey) is presented that shows the breadth of information that can be captured using the approach. In this case study, events were extracted pertaining to the planning/construction of Akkuyu including protests from the population, information campaigns in response to the protests, forged regulatory documents and lawsuits, budgetary/shareholder information, geopolitical tensions, and the various construction milestones. This has demonstrated the pipeline’s utility as a research aid or real-time event extraction tool, where summary-level information and detailed text extractions from millions of articles or Tweets across long time periods can be generated with significantly less effort than current techniques.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
Knowledge-informed deep learning for hydrological model calibration: an application to Coal Creek Watershed in Colorado
Abstract. Deep learning (DL)-assisted inverse mapping has shown promise in hydrological model calibration by directly estimating parameters from observations. However, the increasing computational demand for running the state-of-the-art hydrological model limits sufficient ensemble runs for its calibration. In this work, we present a novel knowledge-informed deep learning method that can efficiently conduct the calibration using a few hundred realizations. The method involves two steps. First, we determine decisive model parameters from a complete parameter set based on the mutual information (MI) between model responses and each parameter computed by a limited number of realizations (∼50). Second, we perform more ensemble runs (e.g., several hundred) to generate the training sets for the inverse mapping, which selects informative model responses for estimating each parameter using MI-based parameter sensitivity. We applied this new DL-based method to calibrate a process-based integrated hydrological model, the Advanced Terrestrial Simulator (ATS), at Coal Creek Watershed, CO. The calibration is performed against observed stream discharge (Q) and remotely sensed evapotranspiration (ET) from the water year 2017 to 2019. Preliminary MI analysis on 50 realizations resulted in a down-selection of 7 out of 14 ATS model parameters. Then, we performed a complete MI analysis on 396 realizations and constructed the inverse mapping from informative responses to each of the selected parameters using a deep neural network. Compared with calibration using observations covering all time steps, the new inverse mapping improves parameter estimations, thus enhancing the performance of ATS forward model runs. The Nash–Sutcliffe efficiency (NSE) of streamflow predictions increases from 0.53 to 0.8 when calibrating against Q alone. Using ET observations, on the other hand, does not show much improvement on the performance of ATS modeling mainly due to both the uncertainty of the remotely sensed product and the insufficient coverage of the model ET ensemble in capturing the observation. By using observed Q only, we further performed a multiyear analysis and show that Q is best simulated (NSE > 0.8) by including in the calibration the dry-year flow dynamics that show more sensitivity to subsurface characteristics than the other wet years. Moreover, when continuing the forward runs till the end of 2021, the calibrated models show similar simulation performances during this evaluation period as the calibration period, demonstrating the ability of the estimated parameters in capturing climate sensitivity. Our success highlights the importance of leveraging data-driven knowledge in DL-assisted hydrological model calibration.
54 ENVIRONMENTAL SCIENCES↗
Particle-based fast jet simulation at the LHC with variational autoencoders
Abstract We study how to use deep variational autoencoders (VAEs) for a fast simulation of jets of particles at the Large Hadron Collider. We represent jets as a list of constituents, characterized by their momenta. Starting from a simulation of the jet before detector effects, we train a deep VAE to return the corresponding list of constituents after detection. Doing so, we bypass both the time-consuming detector simulation and the collision reconstruction steps of a traditional processing chain, speeding up significantly the events generation workflow. Through model optimization and hyperparameter tuning, we achieve state-of-the-art precision on the jet four-momentum, while providing an accurate description of the constituents momenta, and an inference time comparable to that of a rule-based fast simulation.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Increasing accessibility to deep learning-based analytics for space biology: pretrained models, transfer learning, and analytics platform development
Biological systems react in complex ways to the stressors of spaceflight, and the data capturing these relationships is concomitantly high-dimensional and complex. Deep learning and machine learning approaches are increasingly popular as an analytical approach for space biosciences, due to their ability to model complex relationships in complex data. However, such approaches often require large datasets and extensive computational resources. New approaches that minimize data sizes and computational power needed to leverage machine learning, and resources that make these approaches accessible, are needed to increase accessibility and adoption of machine learning in the space biosciences. Transfer learning, in which a pretrained model of broad utility is trained on a large dataset, and subsequently reused on downstream applications for which data is more limited, is one approach to minimizing data and computational intensity of deep learning applications. This transfer learning approach results in more performant models in high-dimensional, low-sample-size settings such as space biology, as compared to training models on limited data from scratch. This presentation will outline efforts to generate pretrained models for the space biology community, and highlight transfer learning applications modeling microbial antibiotic resistance during spaceflight. Finally, in order to increase accessibility of these models and tools, as well as others, for the broader space biology community, we present a modeling and analysis platform facilitating machine learning applications in space biology. This platform streamlines machine learning training and analysis in a notebook format, facilitates download and use of space biology data from the NASA GeneLab database, and can be utilized on NASA-hosted servers or downloaded and hosted locally. This effort, as part of the AI4LS (Artificial Intelligence for Life in Space) working group, will increase accessibility, feasibility, and performance of machine learning approaches for the space biology community.
Adrienne Hoarfrost↗
Toward The Development of Hailstorm Climatologies Derived From Reanalyses and Infared/Passive Microwave Satellite Imagers
Geostationary satellite imagers, such as those of the Geostationary Operational Environmental Satellite (GOES) and Meteosat series, provide both historical and near-real-time observations of cloud top patterns that are commonly associated with severe convection. Environmental conditions favorable for severe weather are thought to be represented well by reanalyses. Predicting exactly where convection and costly storm hazards like hail will occur using models or satellite imagery alone, however, is extremely challenging. The multivariate combination of satellite-observed cloud patterns with reanalysis environmental parameters, linked to United States Next Generation Weather Radar- (NEXRAD-) estimated Maximum Expected Size of Hail (MESH) using a deep neural network (DNN), enables estimation of potentially severe hail likelihood for any observed storm cell. These estimates are specifically designed to make hail likelihood distinctions based on satellite-indicated points of deep convection within environments favorable for storm development. We seek an approach that can be used to estimate climatological hailstorm frequency and risk throughout the historical satellite data record. This presentation demonstrates that statistical distributions of convective parameters from satellite and reanalysis show separation between non-severe/severe hailstorm classes for predictors including overshooting cloud top temperature and area characteristics, convective available potential energy, vertical wind shear, 500 hPa temperature, mid-level lapse rate, precipitable water, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN to produce a hail likelihood metric with a critical success index of 0.504 and Heidke skill score of 0.403, which is exceptional among recent analogous hail studies. Furthermore, applications of the DNN to select case studies demonstrate good qualitative agreement between hail likelihood and MESH. These hail classifications are aggregated across an 11-year GOES-12/13 image database to derive a hail frequency and severity climatology, which denotes the Central Plains, the Midwest, and northwestern Mexico as being the most hail-prone regions within the domain studied. Opportunities for training and applying DNN-based hailstorm predictions to recently developed GOES-8/10/12/13/16 and Meteosat Second Generation convective storm detection and characterization climatologies over South America and South Africa, respectively, will also be presented.
Kristopher Bedka↗
Global Solar Activity Data Portal for Studying 3D Dynamics and Activity of the Sun
The main problems with understanding and predicting solar activity are tightly linked to limitations in describing the global evolution of the Sun from the deep interior to the corona. Because of the complexity of interactions in a wide range of dynamical, turbulent, and spatial scales and dramatic changes in thermodynamic and magnetic field conditions, only physics-based models can provide essential background to generate reliable solar activity forecasts. However, performing accurate model calibration and estimating uncertainties is often challenging due to the unavailability of a long time series of observations. To mitigate these limitations, we have developed the Global Solar Activity (GSA) Data Portal, which enables convenient access to a variety of modern and historical data. The portal supports a dynamic visualization for 1D time series (such as the sunspot number and solar irradiance) and quick-look visualization for 2D datasets (e.g., synoptic magnetograms, the solar internal rotation, and flows). The GSA portal includes a search engine that enables data retrieval from user-specified data sources and time intervals. In this presentation, we will discuss the current and upcoming capabilities of the data portal and its potential applications for space weather studies.
SMD↗