Search NASA⌕ Search

SEARCH · Search NASA

Results for “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.

At least 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Block-Structured Operator Inference for Coupled Multiphysics Model Reduction

This work presents a block-structured formulation of Operator Inference as a way to learn structured reduced-order models for multiphysics systems. The approach specifies the governing equation structure for each physics component and the structure of the coupling terms. Once the multiphysics structure is specified, the reduced-order model is learned from snapshot data following the nonintrusive Operator Inference methodology. In addition to preserving physical system structure, which in turn permits preservation of system properties such as stability and second-order structure, the block-structured approach has the advantages of reducing the overall dimensionality of the learning problem and admitting tailored regularization for each physics component. The numerical advantages of the block-structured formulation over a monolithic Operator Inference formulation are demonstrated for aeroelastic analysis, which couples aerodynamic and structural models. For the benchmark test case of the AGARD 445.6 wing, block-structured Operator Inference provides an average 20% online prediction speedup over monolithic Operator Inference across subsonic and supersonic flow conditions in both the stable and fluttering parameter regimes while preserving the accuracy achieved with monolithic Operator Inference.

42 ENGINEERING↗
NASA NTRS2008

Algorithm Optimally Orders Forward-Chaining Inference Rules

People typically develop knowledge bases in a somewhat ad hoc manner by incrementally adding rules with no specific organization. This often results in a very inefficient execution of those rules since they are so often order sensitive. This is relevant to tasks like Deep Space Network in that it allows the knowledge base to be incrementally developed and have it automatically ordered for efficiency. Although data flow analysis was first developed for use in compilers for producing optimal code sequences, its usefulness is now recognized in many software systems including knowledge-based systems. However, this approach for exhaustively computing data-flow information cannot directly be applied to inference systems because of the ubiquitous execution of the rules. An algorithm is presented that efficiently performs a complete producer/consumer analysis for each antecedent and consequence clause in a knowledge base to optimally order the rules to minimize inference cycles. An algorithm was developed that optimally orders a knowledge base composed of forwarding chaining inference rules such that independent inference cycle executions are minimized, thus, resulting in significantly faster execution. This algorithm was integrated into the JPL tool Spacecraft Health Inference Engine (SHINE) for verification and it resulted in a significant reduction in inference cycles for what was previously considered an ordered knowledge base. For a knowledge base that is completely unordered, then the improvement is much greater.

James, Mark↗
DOE OSTI2025

Optimizing inference of segmentation on high-resolution images in MLExchange

MLExchange is a machine learning (ML) operations platform providing web user-interfaces (UIs) for data visualization and analysis pipelines at synchrotron facilities. Among these UIs is the segmentation app which helps synchrotron users utilize ML algorithms to automatically segment high-resolution scientific images with minimal manual annotation effort. In this work, we share code optimizations that significantly speed up the segmentation inference workflow of large data in short time. By optimizing the sequence of CPU-GPU data transfers and introducing CPU parallelization to key operations, we improve the per-device, per-image frame computational efficiency and observe close to 3×$$\times$$ speedup over the original segmentation inference workflow run time when utilizing a single GPU. Further adaptations enabling multi-GPU inference yield more than 40×$$\times$$ speedup with 100 GPUs compared to the optimized single GPU inference workflow. This acceleration of the segmentation inference workflow will provide MLExchange users with easy access to segmentation results with little wait time.

Lu, Shizhao↗
DOE OSTI2026

Inferring performance metrics for laser direct drive experiments on OMEGA

Quantifying performance improvements on the OMEGA laser facility requires robust inference of established no-alpha performance metrics, which requires, at minimum, a model to infer the shocked fuel mass and pressure of the confined fusion plasma. In this work, we describe the methodology used to infer performance metrics on OMEGA and present the current state-of-the art model used to infer these metrics from OMEGA experiments. In particular, since neutron images of cryogenic implosions are not available on OMEGA at present, we present how x-ray sizes are determined on OMEGA using a Gaussian Process regression model and how the neutron production region's size is inferred from them. As a result, we end by benchmarking the model using synthetic data and 1-D LILAC simulations and test its experimental self-consistency across available x-ray diagnostic channels.

Gopalaswamy, V. [Laboratory for Laser Energetics, ↗
NASA NTRS1992

New developments of a knowledge based system (VEG) for inferring vegetation characteristics

An extraction technique for inferring physical and biological surface properties of vegetation using nadir and/or directional reflectance data as input has been developed. A knowledge-based system (VEG) accepts spectral data of an unknown target as input, determines the best strategy for inferring the desired vegetation characteristic, applies the strategy to the target data, and provides a rigorous estimate of the accuracy of the inference. Progress in developing the system is presented. VEG combines methods from remote sensing and artificial intelligence, and integrates input spectral measurements with diverse knowledge bases. VEG has been developed to (1) infer spectral hemispherical reflectance from any combination of nadir and/or off-nadir view angles; (2) test and develop new extraction techniques on an internal spectral database; (3) browse, plot, or analyze directional reflectance data in the system's spectral database; (4) discriminate between user-defined vegetation classes using spectral and directional reflectance relationships; and (5) infer unknown view angles from known view angles (known as view angle extension).

Kimes, D. S.↗
DOE OSTI2025

Solving high-dimensional inverse problems using amortized likelihood-free inference with noisy and incomplete data

Here, we present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems. The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation. The summary network encodes raw observations into a fixed-size vector of summary features, while the inference network generates samples of the approximate posterior distribution of the model parameters based on these summary features. The posterior samples are produced in a deep generative fashion by sampling from a latent Gaussian distribution and passing these samples through an invertible transformation. We construct this invertible transformation by sequentially alternating conditional invertible neural network and conditional neural spline flow layers. The summary and inference networks are trained simultaneously. We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations of the system’s hydraulic head responses. The conductivity field is represented with 706 degrees of freedom in the considered problem. Comparison with the likelihood-based iterative ensemble smoother PEST-IES method demonstrates that the proposed method accurately estimates the parameter posterior distribution and the observations’ predictive posterior distribution at a fraction of the inference time of PEST-IES.

conditional invertible neural network↗
DOE OSTI2024

Analyzing inference workloads for spatiotemporal modeling

Ensuring power grid resiliency, forecasting climate conditions, and optimization of transportation infrastructure are some of the many application areas where data is collected in both space and time. Spatiotemporal modeling is about modeling those patterns for forecasting future trends and carrying out critical decision-making by leveraging machine learning/deep learning. Once trained offline, field deployment of trained models for near real-time inference could be challenging because performance can vary significantly depending on the environment, available compute resources and tolerance to ambiguity in results. Users deploying spatiotemporal models for solving complex problems can benefit from analytical studies considering a plethora of system adaptations to understand the associated performance-quality trade-offs. To facilitate the co-design of next-generation hardware architectures for field deployment of trained models, it is critical to characterize the workloads of these deep learning (DL) applications during inference and assess their computational patterns at different levels of the execution stack. In this paper, we develop several variants of deep learning applications that use spatiotemporal data from dynamical systems. We study the associated computational patterns for inference workloads at different levels, considering relevant models (Long short-term Memory, Convolutional Neural Network and Spatio-Temporal Graph Convolution Network), DL frameworks (Tensorflow and PyTorch), precision (FP16, FP32, AMP, INT16 and INT8), inference runtime (ONNX and AI Template), post-training quantization (TensorRT) and platforms (Nvidia DGX A100 and Sambanova SN10 RDU). Overall, our findings indicate that although there is potential in mixed-precision models and post-training quantization for spatiotemporal modeling, extracting efficiency from contemporary GPU systems might be challenging. Instead, co-designing custom accelerators by leveraging optimized High Level Synthesis frameworks (such as SODA High-Level Synthesizer for customized FPGA/ASIC targets) can make workload-specific adjustments to enhance the efficiency.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

An implementation of neural simulation-based inference for parameter estimation in ATLAS

Neural simulation-based inference (NSBI) is a powerful class of machine-learning-based methods for statistical inference that naturally handles high-dimensional parameter estimation without the need to bin data into low-dimensional summary histograms. Such methods are promising for a range of measurements, including at the Large Hadron Collider, where no single observable may be optimal to scan over the entire theoretical phase space under consideration, or where binning data into histograms could result in a loss of sensitivity. This work develops a NSBI framework for statistical inference, using neural networks to estimate probability density ratios, which enables the application to a full-scale analysis. It incorporates a large number of systematic uncertainties, quantifies the uncertainty due to the finite number of events in training samples, develops a method to construct confidence intervals, and demonstrates a series of intermediate diagnostic checks that can be performed to validate the robustness of the method. As an example, the power and feasibility of the method are assessed on simulated data for a simplified version of an off-shell Higgs boson couplings measurement in the four-lepton final states. This approach represents an extension to the standard statistical methodology used by the experiments at the Large Hadron Collider, and can benefit many physics analyses.

frequentist statistics↗
DOE OSTI2024

Probabilistic inference of the structure and orbit of Milky Way satellites with semi-analytic modelling

Semi-analytic modelling furnishes an efficient avenue for characterizing dark matter haloes associated with satellites of Milky Way-like systems, as it easily accounts for uncertainties arising from halo-to-halo variance, the orbital disruption of satellites, baryonic feedback, and the stellar-to-halo mass (SMHM) relation. We use the SatGen semi-analytic satellite generator, which incorporates both empirical models of the galaxy–halo connection as well as analytic prescriptions for the orbital evolution of these satellites after accretion onto a host to create large samples of Milky Way-like systems and their satellites. By selecting satellites in the sample that match observed properties of a particular dwarf galaxy, we can infer arbitrary properties of the satellite galaxy within the cold dark matter paradigm. For the Milky Way’s classical dwarfs, we provide inferred values (with associated uncertainties) for the maximum circular velocity v max and the radius r max at which it occurs, varying over two choices of baryonic feedback model and two prescriptions for the SMHM relation. While simple empirical scaling relations can recover the median inferred value for v max and r max , this approach provides realistic correlated uncertainties and aids interpretability. We also demonstrate how the internal properties of a satellite’s dark matter profile correlate with its orbit, and we show that it is difficult to reproduce observations of the Fornax dwarf without strong baryonic feedback. Furthermore, the technique developed in this work is flexible in its application of observational data and can leverage arbitrary information about the satellite galaxies to make inferences about their dark matter haloes and population statistics.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Exogeological inferences from white dwarf pollutants: the impact of stellar physics

Many white dwarfs have accreted material from their own planetary systems. These objects can be used to infer the composition of exoplanetary material and identify evidence for key geological processes. However, the white dwarf atmospheric physics distorts the inferred material composition away from the true composition, mainly through differential atomic diffusion of the accreted metals. Correcting for this effect is essential, but is dependent on various physical assumptions associated with the white dwarf itself. We first focus on the effect of assumptions related to convective overshoot and thermohaline mixing on the atomic diffusion time-scales. For white dwarfs with H-dominated atmospheres between 12000 K and 18000 K⁠, we find that including a complete treatment of convective overshoot decreases the inferred Fe and O abundances in accreted material. For these white dwarfs, we also find that including thermohaline mixing decreases Fe and O abundances. For He-dominated systems, the effect of convective overshoot is comparatively minor. We then explore the overall effect of other physical assumptions by comparing publicly available grids of diffusion time-scales. We find that the choice of model grid can have a large impact for white dwarfs with He-dominated atmospheres, notably on the inferred core to mantle ratio of accreted material. We identify several systems for which the geological interpretation is robust against these systematics. We also present a ‘discrepancy metric’ which can be used to estimate the potential impact of changing the stellar physics without requiring detailed modelling.

Astronomy and AstroPhysics↗
DOE OSTI2026

pyFLANK, a graph neural network based null distribution inference model for F ST outlier detection

Detecting genomic regions under selection is essential for understanding how populations adapt to different environments, yet it remains challenging due to the confounding effects of demographic history and linkage disequilibrium (LD). Fixation index (F ST ) is a widely used statistic to identify genomic regions under adaptation. However, identifying genes under selection by defining F ST outliers often remains challenging, owing to confounding effects of underlying demographic history. Traditional methods assume independence among loci and rely on simple demographic models, while newer models perform much better but are computationally expensive and not easily scalable. Here, we present pyFLANK, an open-source and automated Python implementation which detects F ST outliers using a null distribution inferred from quasi-independent loci. Our tool integrates three approaches to identify loci obeying a null distribution: graph neural network (GNN) inference, linkage disequilibrium (LD)-based inference, and user-defined input. Because pyFLANK uses GNN-based inference of quasi-independent loci, it yields a more accurate null model with less need for user parameter input. In simulation experiments, pyFLANK achieved lower false positive rates than current methods while maintaining comparable detection power, indicating that its refined null model better distinguishes true adaptive loci from background variation. The GNN-based model, in particular, detected additional loci associated with phenotypic variance that were not identified by existing methods. Assessments of simulation and real data from different species demonstrate that pyFLANK achieves lower false positive rates compared with other commonly used F ST outlier detectors, while maintaining comparable detection power and excellent computational performance, providing a robust and user-friendly tool for identifying loci under divergent selection. It extends existing F ST outlier frameworks by incorporating explicit LD-aware strategies for null model calibration. The method is intended as a practical and scalable complement to existing genome scan approaches.

FST↗
NASA NTRS1987

An inference engine for embedded diagnostic systems

The implementation of an inference engine for embedded diagnostic systems is described. The system consists of two distinct parts. The first is an off-line compiler which accepts a propositional logical statement of the relationship between facts and conclusions and produces data structures required by the on-line inference engine. The second part consists of the inference engine and interface routines which accept assertions of fact and return the conclusions which necessarily follow. Given a set of assertions, it will generate exactly the conclusions which logically follow. At the same time, it will detect any inconsistencies which may propagate from an inconsistent set of assertions or a poorly formulated set of rules. The memory requirements are fixed and the worst case execution times are bounded at compile time. The data structures and inference algorithms are very simple and well understood. The data structures and algorithms are described in detail. The system has been implemented on Lisp, Pascal, and Modula-2.

Fox, Barry R.↗
NASA NTRS1988

Inference of geologic surface parameters from polarimetric radar observations and model inversion

The results of inferring geologic parameters such as rms surface height, correlation length, and dielectric constant of rough surfaces by fitting observed polarization signatures with those predicted by the second order Rice model are discussed. The inferred results are compared to measured values of rms height and correlation length. The rms height values inferred are in good agreement with in situ measurements. The inferred correlation lengths generally do not agree with measured values. The results allow the separation of the effects of surface roughness and dielectric constant on the overall backscatter from rough surfaces.

Vanzyl, Jakob J.↗
NASA NTRS1987

The mechanisms of temporal inference

The properties of a temporal language are determined by its constituent elements: the temporal objects which it can represent, the attributes of those objects, the relationships between them, the axioms which define the default relationships, and the rules which define the statements that can be formulated. The methods of inference which can be applied to a temporal language are derived in part from a small number of axioms which define the meaning of equality and order and how those relationships can be propagated. More complex inferences involve detailed analysis of the stated relationships. Perhaps the most challenging area of temporal inference is reasoning over disjunctive temporal constraints. Simple forms of disjunction do not sufficiently increase the expressive power of a language while unrestricted use of disjunction makes the analysis NP-hard. In many cases a set of disjunctive constraints can be converted to disjunctive normal form and familiar methods of inference can be applied to the conjunctive sub-expressions. This process itself is NP-hard but it is made more tractable by careful expansion of a tree-structured search space.

Fox, B. R.↗
NASA NTRS2008

Safe Upper-Bounds Inference of Energy Consumption for Java Bytecode Applications

Many space applications such as sensor networks, on-board satellite-based platforms, on-board vehicle monitoring systems, etc. handle large amounts of data and analysis of such data is often critical for the scientific mission. Transmitting such large amounts of data to the remote control station for analysis is usually too expensive for time-critical applications. Instead, modern space applications are increasingly relying on autonomous on-board data analysis. All these applications face many resource constraints. A key requirement is to minimize energy consumption. Several approaches have been developed for estimating the energy consumption of such applications (e.g. [3, 1]) based on measuring actual consumption at run-time for large sets of random inputs. However, this approach has the limitation that it is in general not possible to cover all possible inputs. Using formal techniques offers the potential for inferring safe energy consumption bounds, thus being specially interesting for space exploration and safety-critical systems. We have proposed and implemented a general frame- work for resource usage analysis of Java bytecode [2]. The user defines a set of resource(s) of interest to be tracked and some annotations that describe the cost of some elementary elements of the program for those resources. These values can be constants or, more generally, functions of the input data sizes. The analysis then statically derives an upper bound on the amount of those resources that the program as a whole will consume or provide, also as functions of the input data sizes. This article develops a novel application of the analysis of [2] to inferring safe upper bounds on the energy consumption of Java bytecode applications. We first use a resource model that describes the cost of each bytecode instruction in terms of the joules it consumes. With this resource model, we then generate energy consumption cost relations, which are then used to infer safe upper bounds. How energy consumption for each bytecode instruction is measured is beyond the scope of this paper. Instead, this paper is about how to infer safe energy consumption estimations assuming that those energy consumption costs are provided. For concreteness, we use a simplified version of an existing resource model [1] in which an energy consumption cost for individual Java opcodes is defined.

Navas, Jorge↗
NASA NTRS2008

Electron Precipitation Parameters and Ionospheric Conductances Inferred from Auroral Images Acquired by the Visible Imaging Systems (VIS) on the Polar Spacecraft

The Visible Imaging System (VIS) on the polar spacecraft provided time sequences of auroral images at multiple wavelengths that yield information of auroral dynamics on a global scale with a spatial resolution of - 20 km and temporal resolution of approx. 1 minute. Time sequences of VIS images in which the aurora was highly dynamic are used to infer global maps for the electron precipitation parameters, energy flux and characteristic energies, and ionospheric conductances. The maps are inferred from the corresponding VIS images using an auroral model (Lumerzheim et al., 1987). The temporal and spatial resolution of the VIS inferred patterns are unprecedented. The inferred patterns are highly structured and vary significantly on a time scale of less than 5 minutes. These patterns can be very beneficial for global physics-based numerical models for the high-latitude ionosphere which previously had to rely on statistical models for the electron precipitation and ionospheric conductance.

Sigwarth, John B.↗
NASA NTRS2016

Degree of Ice Particle Surface Roughness Inferred from Polarimetric Observations

The degree of surface roughness of ice particles within thick, cold ice clouds is inferred from multidirectional, multi-spectral satellite polarimetric observations over oceans, assuming a column-aggregate particle habit. An improved roughness inference scheme is employed that provides a more noise-resilient roughness estimate than the conventional best-fit approach. The improvements include the introduction of a quantitative roughness parameter based on empirical orthogonal function analysis and proper treatment of polarization due to atmospheric scattering above clouds. A global 1-month data sample supports the use of a severely roughened ice habit to simulate the polarized reflectivity associated with ice clouds over ocean. The density distribution of the roughness parameter inferred from the global 1- month data sample and further analyses of a few case studies demonstrate the significant variability of ice cloud single-scattering properties. However, the present theoretical results do not agree with observations in the tropics. In the extra-tropics, the roughness parameter is inferred but 74% of the sample is out of the expected parameter range. Potential improvements are discussed to enhance the depiction of the natural variability on a global scale.

surface↗
NASA NTRSDate not supplied

Use of Design of Experiments and Rule-Based Inference in Determining Neural Network Architectures for Loss of Control Detection

In this work, we describe methods for selecting the neural network architectures and input spaces to implement belief state inference on generic commercial transport aircraft. First, we highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). We present a structured method that can be used in a number of aerospace applications, to optimize the structure and training parameters of the CVAE for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from a NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications. While theoretically, we could create a single CVAE with an input space the size of all measurable flight variables and environmental dynamics, it becomes intractable to use such a neural network in an in-situ intelligent multi-agent system. Using the recommendations from our case study, we introduce a technical approach for feasibly describing the belief space by (1) identifying significant statistical relationships among flight variables using rule induction, (2) using a set of rules that cover all features to define the input space of multiple CVAEs, and (3) forming a belief space based on the joint probability density of their collective latent spaces. This results in a series of relatively small matrix multiplications that can be performed in real time, as opposed to large matrix computations in a single CVAE. We demonstrate the application of this approach on the T-2 flight loss-of control experiments, using the architecture and hyperparameter recommendations from the case study. We compare the utilities of an individual CVAE trained on all flight variables and multiple CVAEs defined on subsets of flight variables for detecting qualitative changes in flight. We demonstrate that the use of multiple CVAEs with smaller input spaces permits the CVAE to capture more granular relationships in the latent space, permitting better state space characterization and loss-of-control detection.

Design of experiments↗