SEARCH · Search NASA
Results for “Model Inference”
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.
On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models
For many real systems, several computer models may exist with different physics and predictive abilities. To achieve more accurate simulations/predictions, it is desirable for these models to be properly combined and calibrated. Here, we propose the Bayesian calibration of computer model mixture method which relies on the idea of representing the real system output as a mixture of the available computer model outputs with unknown input dependent weight functions. The method builds a fully Bayesian predictive model as an emulator for the real system output by combining, weighting, and calibrating the available models in the Bayesian framework. Moreover, it fits a mixture of calibrated computer models that can be used by the domain scientist as a mean to combine the available computer models, in a flexible and principled manner, and perform reliable simulations. It can address realistic cases where one model may be more accurate than the others at different input values because the mixture weights, indicating the contribution of each model, are functions of the input. Inference on the calibration parameters can consider multiple computer models associated with different physics. The method does not require knowledge of the fidelity order of the models. We provide a technique able to mitigate the computational overhead due to the consideration of multiple computer models that is suitable to the mixture model framework. We implement the proposed method in a real-world application involving the Weather Research and Forecasting large-scale climate model.
Active Operator Inference for Learning Low-Dimensional Dynamical-System Models from Noisy Data
Not provided.
Accurate geometrical inferences from proton radiography data using the CpRad forward model
Explore the source record for details and available documents.
$\overline{TKE}$ Parameterization and $\bar{v}$ Uncertainty Analysis for CGMF
Previous work was performed on tuning CGMF parameters for 235 U, 238 U, and Plutonium isotopes. Now work is being done to tune minor uranium isotopes. However, uranium isotopes like 232 U and 236 U have almost no experimental data. We are applying cross-isotope models to extrapolate and tune CGMF on isotopes that lack experimental data. There exist several internal CGMF physics quantities that affect the output of CGMF—multi-chance fission probability, excitation energy sharing, spin-cutoff factor, spin scaling, and fragment total kinetic energy to name a few. The mean fragment total kinetic energy, $\overline{TKE}$, is particularly interesting because of its strong anti-correlation with $\bar{v}$. We are most interested in the mean fragment total kinetic energy before neutron emissions. $\overline{TKE}$ is assumed to be pre-neutron emission unless otherwise stated. Currently in CGMF, the $\overline{TKE}$ model for 233,234,235,238 U are tuned independently to reproduce ν for the associated isotopes. In this report, we will tune a cross-isotope $\overline{TKE}$ model to experimental $\overline{TKE}$ data for 232,233,234,235,236,238 U. Because of the unreliable and sparse nature of $\overline{TKE}$ experimental data, future work will use more reliable experimental $\bar{v}$ data to infer the $\overline{TKE}$ model (and likely other internal CGMF parameters) for uranium isotopes. Such work has been performed previously using a sensitivity analysis and Kalman filter methods.
Subsurface Seismic Structure Around the Sanford Underground Research Facility
To address the fundamental challenges of understanding processes associated with enhanced or engineered geothermal systems (EGS), teams from the EGS Collab SIGMA-V project are conducting stimulations at the Sanford Underground Research Facility. Various modalities of geophysical observations are collected and analyzed, and different types of parameters are modeled to help investigate these critical processes. Among these parameters, the three-dimensional stress field is one of the primary objectives. Seismic velocity models have been used to estimate the 3D stress field for other regions. A detailed seismic velocities and density model can help us infer spatial variations of the stress field in the study area. We inverted the 3D seismic structure around the site by using body-wave travel times, surface-wave dispersions and gravity observations simultaneously. The resulting model will be a starting point for more detailed investigations and could also be used to study subsurface geological and stress field variations of the broad area.
Subsurface Seismic Structure Around the Sanford Underground Research Facility
To address the fundamental challenges of understanding processes associated with enhanced or engineered geothermal systems (EGS), teams from the EGS Collab SIGMA-V project are conducting stimulations at the Sanford Underground Research Facility. Various modalities of geophysical observations are collected and analyzed, and different types of parameters are modeled to help investigate these critical processes. Among these parameters, the three-dimensional stress field is one of the primary objectives. Seismic velocity models have been used to estimate the 3D stress field for other regions. A detailed seismic velocities and density model can help us infer spatial variations of the stress field in the study area. We inverted the 3D seismic structure around the site by using body-wave travel times, surface-wave dispersions and gravity observations simultaneously. The resulting model will be a starting point for more detailed investigations and could also be used to study subsurface geological and stress field variations of the broad area.
ExtremeMETA: High-speed Lightweight Image Segmentation Model by Remodeling Multi-channel Metamaterial Imagers
Deep neural networks (DNNs) have heavily relied on traditional computational units, such as CPUs and GPUs. However, this conventional approach brings significant computational burden, latency issues, and high power consumption, limiting their effectiveness. This has sparked the need for lightweight networks such as ExtremeC3Net. Meanwhile, there have been notable advancements in optical computational units, particularly with metamaterials, offering the exciting prospect of energy-efficient neural networks operating at the speed of light. Yet, the digital design of metamaterial neural networks (MNNs) faces precision, noise, and bandwidth challenges, limiting their application to intuitive tasks and low-resolution images. In this study, we proposed a large kernel lightweight segmentation model, ExtremeMETA. Based on ExtremeC3Net, our proposed model, ExtremeMETA maximized the ability of the first convolution layer by exploring a larger convolution kernel and multiple processing paths. With the large kernel convolution model, we extended the optic neural network application boundary to the segmentation task. To further lighten the computation burden of the digital processing part, a set of model compression methods was applied to improve model efficiency in the inference stage. The experimental results on three publicly available datasets demonstrated that the optimized efficient design improved segmentation performance from 92.45 to 95.97 on mIoU while reducing computational FLOPs from 461.07 MMacs to 166.03 MMacs. The large kernel lightweight model ExtremeMETA showcased the hybrid design’s ability on complex tasks.
Inferring and evaluating satellite-based constraints on NO x emissions estimates in air quality simulations
Satellite observations of tropospheric NO 2 columns can provide top-down observational constraints on emissions estimates of nitrogen oxides (NO x ). Mass-balance-based methods are often applied for this purpose but do not isolate near-surface emissions from those aloft, such as lightning emissions. Here, we introduce an inverse modeling framework that couples satellite chemical data assimilation to a chemical transport model. In the framework, satellite-constrained emissions totals are inferred using model simulations with and without data assimilation in the iterative finite-difference mass-balance method. The approach improves the finite-difference mass-balance inversion by isolating the near-surface emissions increment. We apply the framework to separately estimate lightning and anthropogenic NO x emissions over the Northern Hemisphere for 2019. Using overlapping observations from the Ozone Monitoring Instrument (OMI) and the Tropospheric Monitoring Instrument (TROPOMI), we compare separate NO x emissions inferences from these satellite instruments, as well as the impacts of emissions changes on modeled NO 2 and O 3 . OMI inferences of anthropogenic emissions consistently lead to larger emissions than TROPOMI inferences, attributed to a low bias in TROPOMI NO 2 retrievals. Updated lightning NO x emissions from either satellite improve the chemical transport model's low tropospheric O 3 bias. The combined lighting and anthropogenic emissions updates improve the model's ability to reproduce measured ozone by adjusting natural, long-range, and local pollution contributions. Thus, the framework informs and supports the design of domestic and international control strategies.
Predicting Missing Regions in Charged Particle Tracks Using a Sparse 3D Convolutional Neural Network
The 2x2 Demonstrator is a prototype of ND-LAr, the liquid argon time-projection chamber of the Deep Underground Neutrino Experiment’s Near Detector complex. Both the 2x2 Demonstrator and ND-LAr are modular detectors that will have pixelated charge readouts and inactive regions wherein there is no sensitivity to charge deposition and light signals that arise from charged particle interactions with liquid argon. In the 2x2, these inactive regions are located in between the active detector modules, which introduces the challenge of inferring what charge signals ought to look like in these regions. This study explores the use of a Sparse 3D Convolutional Neural Network (ConvNet) to infer missing regions in charged particle tracks. Hits corresponding to energy depositions are voxelized into a three-dimensional grid for each track. Voxels that fall into predefined inactive regions are removed to simulate the lack of detector output. The model is trained to infer the topology of the missing track voxels, with the ultimate goal of inferring the missing charge or energy values in these voxels as well. Results indicate that this approach shows promise in prediction of missing track regions with some accuracy.
Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology
With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The objective of the study is to quantify the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients’ information to mitigate confidentiality breaches. The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance.
Finding the missing pieces: filling gaps that impede the translation of omics data into models
High-throughput omics technologies such as DNA sequencing have made the sequencing and computational assembly of microbial genomes recovered from the environment relatively routine. Computational inference of the protein products encoded by these genomes, and the associated biochemical functions, should enable the accurate prediction and modeling of microbial metabolism, organismal interactions, and ecosystem processes. However, a lack of scalable, probabilistic protein annotation tools limits the full potential of modeling for understanding the metabolism and biogeochemical cycles of microbial communities. Our approach to improve inference of protein annotations and metabolic models relied on learning from and emulating expert manual curation, leveraging software engineering and data science best practices to scale up the throughput and accuracy of annotations and metabolic model construction, building software to objectively evaluate different annotation strategies, and more closely linking the protein annotation and metabolic model inference process. Outcomes of this research include several improved or new computational tools, including DRAM (Distilled and Refined Annotation of Metabolism) for annotating microbial genomes with protein function and metabolic traits, CAMPER (Curated Annotations for Microbial Polyphenol Enzymes and Reactions) for annotating key polyphenol metabolisms, EC-Bench for comprehensive and unbiased benchmarking of annotation tools, and several apps available via the DOE Systems Biology Knowledgebase (KBase) for building genome-scale metabolic models. We demonstrate that these tools allow us to scalably annotate and understand thousands of genomes for microbial communities from a variety of systems and test cases, including rivers, thawing permafrost, and gut microbiomes. All of these computational tools are available as open-source software, with most broadly and easily accessible to the scientific community via KBase apps.
Accelerating astronomical and cosmological inference with preconditioned Monte Carlo
ABSTRACT We introduce preconditioned Monte Carlo (PMC), a novel Monte Carlo method for Bayesian inference that facilitates efficient sampling of probability distributions with non-trivial geometry. PMC utilizes a Normalizing Flow (NF) in order to decorrelate the parameters of the distribution and then proceeds by sampling from the preconditioned target distribution using an adaptive Sequential Monte Carlo (SMC) scheme. The results produced by PMC include samples from the posterior distribution and an estimate of the model evidence that can be used for parameter inference and model comparison, respectively. The aforementioned framework has been thoroughly tested in a variety of challenging target distributions achieving state-of-the-art sampling performance. In the cases of primordial feature analysis and gravitational wave inference, PMC is approximately 50 and 25 times faster, respectively, than nested sampling (NS). We found that in higher dimensional applications, the acceleration is even greater. Finally, PMC is directly parallelisable, manifesting linear scaling up to thousands of CPUs.
Sensitivity Analysis of Genome-Scale Metabolic Flux Prediction
TRIMER, Transcription Regulation Integrated with MEtabolic Regulation, is a genome-scale modeling pipeline targeting at metabolic engineering applications. Using TRIMER, regulated metabolic reactions can be effectively predicted by integrative modeling of metabolic reactions with a Transcription Factor (TF)-gene regulatory network (TRN), which is modeled via a Bayesian network (BN). In this paper, we focus on sensitivity analysis of metabolic flux prediction for uncertainty quantification of BN structures for TRN modeling in TRIMER. We propose a computational strategy to construct the uncertainty class of TRN models based on the inferred regulatory order uncertainty given transcriptomic expression data. With that, we analyze the prediction sensitivity of the TRIMER pipeline for the metabolite yields of interest. The obtained sensitivity analyses can guide Optimal Experimental Design (OED) to help acquire new data that can enhance TRN modeling and achieve specific metabolic engineering objectives, including metabolite yield alterations. Here we have performed small- and large-scale simulated experiments, demonstrating the effectiveness of our developed sensitivity analysis strategy for BN structure learning to quantify the edge importance in terms of metabolic flux prediction uncertainty reduction and its potential to effectively guide OED.
MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles
Optimal engine operation during a transient driving cycle is the key to achieving greater fuel economy, engine efficiency, and reduced emissions. In order to achieve continuously optimal engine operation, engine calibration methods use a combination of static correlations obtained from dynamometer tests for steady-state operating points and road and/or track performance data. As the parameter space of control variables, design variable constraints, and objective functions increases, the cost and duration for optimal calibration become prohibitively large. In order to reduce the number of dynamometer tests required for calibrating modern engines, a large-scale simulation-driven machine learning approach is presented in this work. A parallel, fast, robust, physics-based reduced-order engine simulator is used to obtain performance and emission characteristics of engines over a wide range of control parameters under various transient driving conditions (drive cycles). We scale the simulation up to 3,906 nodes of the Theta supercomputer at the Argonne Leadership Computing Facility to generate data required to train a machine learning model. The trained model is then used to predict various engine parameters of interest, and the results are compared with those predicted by the engine simulator. Our results show that a deepneural-network-based surrogate model achieves high accuracy: Pearson product-moment correlation values larger than 0.99 and mean absolute percentage error within 1.07% for various engine parameters such as exhaust temperature, exhaust pressure, nitric oxide, and engine torque. Once trained, the deep-neural-network-based surrogate model is fast for inference: it requires about 16 mu s for predicting the engine performance and emissions for a single design configuration compared with about 0.5 s per configuration with the engine simulator. Moreover, we demonstrate that transfer learning and retraining can be leveraged to incrementally retrain the surrogate model to cope with new configurations that fall outside the training data space.
A system identification approach for non-intrusive reduced order modeling of radiation-induced photocurrents
In this study, development of compact photocurrent models is currently dominated by analytical techniques that rely on physical assumptions to render the governing equations solvable in a closed form. Violation of these assumptions can reduce the accuracy of the models and/or limit their scope. In this paper we show that system identification of nonlinear state-space systems can serve as an alternative numerical basis for non-intrusive reduced order modeling of photocurrent effects. To that end we develop a compact gray box photocurrent model (GBPM) by using a state-space representation with a low-dimensional latent state equation that mimics a mathematical model for the response of an idealized class of devices to ionizing radiation. In so doing we obtain a model that learns the dynamics of a quantity of interest directly from its measurements without requiring snapshots of the internal device state or its discretized model, and can be inferred from very small data sets. To demonstrate the approach we train the GBPM using a small experimental data set for a Z5236 Zener diode and a small synthetic data set obtained by simulating a synthetic pn-junction device. We then compare the GBPMs with black box models trained on the same data and show that performance of the latter is limited by the size of the data set, while the former are able to achieve excellent performance in both the reproductive and the predictive regimes.
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
Mixture of Experts (MoE) models have enabled the scaling of Large Language Models (LLMs) and Vision Language Models (VLMs) by achieving massive parameter counts while maintaining computational efficiency. However, MoEs introduce several inference-time challenges, including load imbalance across experts and the additional routing computational overhead. To address these challenges and fully harness the benefits of MoE, a systematic evaluation of hardware acceleration techniques is essential. We present MoE-Inference-Bench, a comprehensive study to evaluate MoE performance across diverse scenarios. We analyze the impact of batch size, sequence length, and critical MoE hyperparameters such as FFN dimensions and number of experts on throughput. We evaluate several optimization techniques on Nvidia H100 GPUs, including pruning, Fused MoE operations, speculative decoding, quantization, and various parallelization strategies. Our evaluation includes MoEs from the Mixtral, DeepSeek, OLMoE and Qwen families. The results reveal performance differences across configurations and provide insights for the efficient deployment of MoEs.
Bayesian inference in band excitation scanning probe microscopy for optimal dynamic model selection in imaging
The universal tendency in scanning probe microscopy (SPM) over the last two decades is to transition from simple 2D imaging to complex detection and spectroscopic imaging modes. The emergence of complex SPM engines brings forth the challenge of reliable data interpretation, i.e., conversion from detected signals to descriptors specific to tip–surface interactions and subsequently to material’s properties. In this work, we implemented a Bayesian inference approach for the analysis of the image formation mechanisms in band excitation SPM. Compared to the point estimates in classical functional fit approaches, Bayesian inference allows for the incorporation of extant knowledge of materials and probe behavior in the form of corresponding prior distribution and return the information on the material functionality in the form of readily interpretable posterior distributions. We explore the nonlinear mechanical behaviors spatially in a classical ferroelectric material, PbTiO 3 . We observe the non-trivial evolution of the Duffing stiffness term and the nonlinearity of the sample surface, determine spatial clustering of the nonlinear response, and perform a Landau analysis on predicting the nonlinear coefficient, which indicates that ferroelectric behavior can be a cause of the observed results. These observations suggest that the spectrum of anomalous behaviors at the ferroelectric domain walls may be broader than previously believed and can extend to non-conventional mechanical properties in addition to static and microwave conductance.