Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model misspecification”

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

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

Aubourg, Eric [APC, Paris] (ORCID:000000025592023X↗

Ancient Rapid Radiation Explains Most Conflicts Among Gene Trees and Well-Supported Phylogenomic Trees of Nostocalean Cyanobacteria

Prokaryotic genomes are often considered to be mosaics of genes that do not necessarily share the same evolutionary history due to widespread horizontal gene transfers (HGTs). Consequently, representing evolutionary relationships of prokaryotes as bifurcating trees has long been controversial. However, studies reporting conflicts among gene trees derived from phylogenomic data sets have shown that these conflicts can be the result of artifacts or evolutionary processes other than HGT, such as incomplete lineage sorting, low phylogenetic signal, and systematic errors due to substitution model misspecification. Here, we present the results of an extensive exploration of phylogenetic conflicts in the cyanobacterial order Nostocales, for which previous studies have inferred strongly supported conflicting relationships when using different concatenated phylogenomic data sets. We found that most of these conflicts are concentrated in deep clusters of short internodes of the Nostocales phylogeny, where the great majority of individual genes have low resolving power. We then inferred phylogenetic networks to detect HGT events while also accounting for incomplete lineage sorting. Our results indicate that most conflicts among gene trees are likely due to incomplete lineage sorting linked to an ancient rapid radiation, rather than to HGTs. Moreover, the short internodes of this radiation fit the expectations of the anomaly zone, i.e., a region of the tree parameter space where a species tree is discordant with its most likely gene tree. In this work, we demonstrated that concatenation of different sets of loci can recover up to 17 distinct and well-supported relationships within the putative anomaly zone of Nostocales, corresponding to the observed conflicts among well-supported trees based on concatenated data sets from previous studies. Our findings highlight the important role of rapid radiations as a potential cause of strongly conflicting phylogenetic relationships when using phylogenomic data sets of bacteria. We propose that polytomies may be the most appropriate phylogenetic representation of these rapid radiations that are part of anomaly zones, especially when all possible genomic markers have been considered to infer these phylogenies.

59 BASIC BIOLOGICAL SCIENCES↗

Neural simulation-based inference approach for characterizing the Galactic Center γ-ray excess

The nature of the Fermi γ-ray Galactic Center Excess (GCE) has remained a persistent mystery for over a decade. Although the excess is broadly compatible with emission expected due to dark matter annihilation, an explanation in terms of a population of unresolved astrophysical point sources e.g., millisecond pulsars, remains viable. The effort to uncover the origin of the GCE is hampered in particular by an incomplete understanding of diffuse emission of Galactic origin. This can lead to spurious features that make it difficult to robustly differentiate smooth emission, as expected for a dark matter origin, from more “clumpy” emission expected from a population of relatively bright, unresolved point sources. Here, we use recent advancements in the field of simulation-based inference, in particular density estimation techniques using normalizing flows, in order to characterize the contribution of modeled components, including unresolved point source populations, to the GCE. Compared to traditional techniques based on the statistical distribution of photon counts, our machine learning-based method is able to utilize more of the information contained in a given model of the Galactic Center emission, and in particular can perform posterior parameter estimation while accounting for pixel-to-pixel spatial correlations in the γ-ray map. This makes the method demonstrably more resilient to certain forms of model misspecification. On application to Fermi data, the method generically attributes a smaller fraction of the GCE flux to unresolved point sources when compared to traditional approaches. We nevertheless infer such a contribution to make up a non-negligible fraction of the GCE across all analysis variations considered, with at least $38^{+9}_{-19}$% of the excess attributed to unresolved point sources in our baseline analysis.

79 ASTRONOMY AND ASTROPHYSICS↗

Model Residuals as Shields: A Two-Level Formulation to Defend Smart Grids From Poisoning Attacks

The advancement of smart grids presents both vast opportunities and heightened cybersecurity risks. Data-driven defense mechanisms, though designed as a shield against these threats, can fall prey to poisoning attacks. We delve into regression settings, underscoring the imperative to fortify defenses against a spectrum of poison ratios, notably those above 0.5—an issue scarcely addressed in prior studies. Recognizing the susceptibilities of smart grids and their manipulable sensors, we exploit the very intent of poisoning attacks, compromising model accuracy, as our defense mechanism. Our proposed two-level optimization framework discerns between poisoned and authentic data based on model residuals, outperforming or matching existing methods in 72% to 77% of precision and 75% to 80% of recalls across various poisoning attacks, poison ratios, and datasets. Once the authentic data are identified, the trained model is adaptable for a variety of applications. Comprehensive evaluations on different smart grid datasets, pitted against myriad poisoning schemes, validate our methodology’s edge over existing methods. Here, we also shed light on the implications of model misspecification originating from temporal auto-correlation, a common feature in Internet of Things and smart grid data.

Adversarial machine learning (ML)↗

First Impressions: Early-time Classification of Supernovae Using Host-galaxy Information and Shallow Learning

Substantial effort has been devoted to the characterization of transient phenomena from photometric information. Automated approaches to this problem have taken advantage of complete phase coverage of an event, limiting their use for triggering rapid follow-up of ongoing phenomena. In this work, we introduce a neural network with a single recurrent layer designed explicitly for early photometric classification of supernovae (SNe). Our algorithm leverages transfer learning to account for model misspecification, host-galaxy photometry to solve the data-scarcity problem soon after discovery, and a custom weighted loss to prioritize accurate early classification. We first train our algorithm using state-of-the-art transient and host-galaxy simulations, then adapt its weights and validate it on the spectroscopically confirmed SNe Ia, SNe II, and SNe Ib/c from the Zwicky Transient Facility Bright Transient Survey. On observed data, our method achieves an overall accuracy of 82% ± 2% within 3 days of an event’s discovery, and an accuracy of 87% ± 5% within 30 days of discovery. At both early and late phases, our method achieves comparable or superior results to the leading classification algorithms with a simpler network architecture. These results help pave the way for rapid photometric and spectroscopic follow-up of scientifically valuable transients discovered in massive synoptic surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition

Multi-fidelity Bayesian optimization (MFBO) is a powerful approach that utilizes lowfidelity, cost-effective sources to expedite the exploration and exploitation of a high-fidelity objective function. Existing MFBO methods with theoretical foundations either lack justification for performance improvements over single-fidelity optimization or rely on strong assumptions about the relationships between fidelity sources to construct surrogate models and direct queries to low-fidelity sources. To mitigate the dependency on cross-fidelity assumptions while maintaining the advantages of low-fidelity queries, we introduce a random sampling and partition-based MFBO framework with deep kernel learning. This framework is robust to cross-fidelity model misspecification and explicitly illustrates the benefits of low-fidelity queries. Our results demonstrate that the proposed algorithm effectively manages complex cross-fidelity relationships and efficiently optimizes the target fidelity function.

Zhang, Fengxue [University of Chicago, Illinois, U↗

A frequentist approach to computer model calibration

The paper considers the computer model calibration problem and provides a general frequentist solution. Under the framework proposed, the data model is semiparametric with a non-parametric discrepancy function which accounts for any discrepancy between physical reality and the computer model. In an attempt to solve a fundamentally important (but often ignored) identifiability issue between the computer model parameters and the discrepancy function, the paper proposes a new and identifiable parameterization of the calibration problem. It also develops a two-step procedure for estimating all the relevant quantities under the new parameterization. This estimation procedure is shown to enjoy excellent rates of convergence and can be straightforwardly implemented with existing software. For uncertainty quantification, bootstrapping is adopted to construct confidence regions for the quantities of interest. As a result, the practical performance of the methodology is illustrated through simulation examples and an application to a computational fluid dynamics model.

97 MATHEMATICS AND COMPUTING↗

A likelihood ratio anomaly detector for identifying within-perimeter computer network attacks

The rapid detection of attackers within firewalls of enterprise computer networks is of paramount importance. Anomaly detectors address this problem by quantifying deviations from baseline statistical models of normal network behavior and signaling an intrusion when the observed data deviates significantly from the baseline model. But, many anomaly detectors do not take into account plausible attacker behavior. As a result, anomaly detectors are prone to a large number of false positives due to unusual but benign activity. Our paper first introduces a stochastic model of attacker behavior which is motivated by real world attacker traversal. Then, we develop a likelihood ratio detector that compares the probability of observed network behavior under normal conditions against the case when an attacker has possibly compromised a subset of hosts within the network. Since the likelihood ratio detector requires integrating over the time each host becomes compromised, we illustrate how to use Monte Carlo methods to compute the requisite integral. We then present Receiver Operating Characteristic (ROC) curves for various network parameterizations that show for any rate of true positives, the rate of false positives for the likelihood ratio detector is no higher than that of a simple anomaly detector and is often lower. Finally, we demonstrate the superiority of the proposed likelihood ratio detector when the network topologies and parameterizations are extracted from real-world networks.

97 MATHEMATICS AND COMPUTING↗

Hyperspectral remote sensing of plant biochemistry using Bayesian model averaging with variable and band selection

Model specification remains challenging in spectroscopy of plant biochemistry, as exemplified by the availability of various spectral indices or band combinations for estimating the same biochemical. This lack of consensus in model choice across applications argues for a paradigm shift in hyperspectral methods to address model uncertainty and misspecification. We demonstrated one such method using Bayesian model averaging (BMA), which performs variable/band selection and quantifies the relative merits of many candidate models to synthesize a weighted average model with improved predictive performances. The utility of BMA was examined using a portfolio of 27 foliage spectral–chemical datasets representing over 80 species across the globe to estimate multiple biochemical properties, including nitrogen, hydrogen, carbon, cellulose, lignin, chlorophyll (a or b), carotenoid, polar and nonpolar extractives, leaf mass per area, and equivalent water thickness. We also compared BMA with partial least squares (PLS) and stepwise multiple regression (SMR). Results showed that all the biochemicals except carotenoid were accurately estimated from hyerspectral data with R2 values > 0.80.

Zhao, Kaiguang↗

Parameter uncertainties for imperfect surrogate models in the low-noise regime

Abstract Bayesian regression determines model parameters by minimizing the expected loss, an upper bound to the true generalization error. However, this loss ignores model form error, or misspecification, meaning parameter uncertainties are significantly underestimated and vanish in the large data limit. As misspecification is the main source of uncertainty for surrogate models of low-noise calculations, such as those arising in atomistic simulation, predictive uncertainties are systematically underestimated. We analyze the true generalization error of misspecified, near-deterministic surrogate models, a regime of broad relevance in science and engineering. We show that posterior parameter distributions must cover every training point to avoid a divergence in the generalization error and design a compatible ansatz which incurs minimal overhead for linear models. The approach is demonstrated on model problems before application to thousand-dimensional datasets in atomistic machine learning. Our efficient misspecification-aware scheme gives accurate prediction and bounding of test errors in terms of parameter uncertainties, allowing this important source of uncertainty to be incorporated in multi-scale computational workflows.

Swinburne, Thomas D. (ORCID:0000000232554257)↗

A Bayesian approach to time-domain photonic Doppler velocimetry analysis

Photonic Doppler velocimetry (PDV) is an established technique for measuring the velocities of fast-moving surfaces in high-energy-density experiments. In the standard approach to PDV analysis, the short-time Fourier transform (STFT) is used to generate a spectrogram from which the velocity history of the target is inferred. The user chooses the form, duration, and separation of the window function. Here, in this study, we present a Bayesian approach to infer the velocity directly from the PDV oscilloscope trace, without using the spectrogram for analysis. This is clearly a difficult inference problem due to the highly periodic nature of the data, but we find that with carefully chosen prior distributions for the model parameters, we can accurately recover the injected velocity from synthetic data. We validate this method using PDV data collected at the STAR two-stage light gas gun at Sandia National Laboratories, recovering shock-front velocities in quartz that are consistent with those inferred using the STFT-based approach and are interpolated across regions of low signal-to-noise data. Although this method does not rely on the same user choices as the STFT, we caution that it can be prone to misspecification if the chosen model is not sufficient to capture the velocity behavior. Analysis using posterior predictive checks can be used to establish whether a better model is required, although more complex models come with additional computational cost, often taking more than several hours to converge when sampling the Bayesian posterior. We, therefore, recommend it be viewed as a complementary method to that of the STFT-based approach.

Allison, James R. [First Light Fusion Ltd., Yarnto↗

Regularized Differentiation for Bioburden Density Estimation in Planetary Protection

In this paper, we propose and investigate the performance of two novel shrinkage estimators for bioburden density estimation in planetary protection. The estimators are based on the regularized differentiation of a cumulative count of colony forming units collected throughout the data collecting session or the life cycle of the entire mission. The regularized differentiation recasts the problem of bioburden density estimation as a linear least squares problem. The least squares problem is then solved through regularization techniques, such as truncated singular value decomposition and penalized least squares. The regularization is necessary to avoid noise amplification during the differentiation of noisy data. The two regularization estimators are compared with four other commonly used estimators to simultaneously evaluate the means of multivariable independent Poisson distributions: the maximum likelihood, noninformative Bayes estimator with Jeffreys prior, Empirical Bayes using conjugate gamma-Poisson model with gamma parameters selected by method of moments, and the Clevenson-Zidek estimator. It is shown through computer-simulated data that the regularized differentiation based on ridge regression has the smallest mean-squared error among all estimators. The analysis of shrinkage mechanism implemented by regularized differentiation is performed, and it is shown that the regularized differentiation amounts to performing a weighted averaging of all the samples. The weights are determined by the regularization parameter automatically selected by the L-curve technique. Since the method of least squares makes no distributional assumptions about the data, it presents an attractive technique for bioburden density estimation when there are concerns about the misspecification of the distributional model. The paper concludes with the analysis of the bioburden data collected during InSight mission and directions for future work.

97 - MATHEMATICS AND COMPUTING↗

Uncertainty quantification for misspecified machine learned interatomic potentials

The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials. Atomic simulations can now plausibly target quantitative predictions in a variety of settings, which has brought renewed interest in robust means to quantify uncertainties. In many practical settings where model complexity is constrained (e.g., due to performance considerations), misspecification — the inability of any one choice of model parameters to exactly match all training data — is a key contributor to errors that is often disregarded. Here, we employ a recent misspecification-aware regression technique to quantify parameter uncertainties, which is then propagated to a broad range of phase and defect properties in tungsten. The propagation is performed through both brute-force resampling and implicit Taylor expansion. The propagated misspecification uncertainties robustly quantify and bound errors on a broad range of material properties. We demonstrate application to recent foundational machine learning interatomic potentials, accurately predicting and bounding errors in MACE-MPA-0 energy predictions across the diverse materials project database.

36 MATERIALS SCIENCE↗

Data-Driven Compositional Optimization in Misspecified Regimes

With a manifold growth in the scale and intricacy of systems, the challenges of parametric misspecification become pronounced. These concerns are further exacerbated in compositional settings, which emerge in problems complicated by modeling risk and robustness. In “Data-Driven Compositional Optimization in Misspecified Regimes,” the authors consider the resolution of compositional stochastic optimization problems, plagued by parametric misspecification. In considering settings where such misspecification may be resolved via a parallel learning process, the authors develop schemes that can contend with diverse forms of risk, dynamics, and nonconvexity. They provide asymptotic and rate guarantees for unaccelerated and accelerated schemes for convex, strongly convex, and nonconvex problems in a two-level regime with extensions to the multilevel setting. Surprisingly, the nonasymptotic rate guarantees show no degradation from the rate statements obtained in a correctly specified regime and the schemes achieve optimal (or near-optimal) sample complexities for general T-level strongly convex and nonconvex compositional problems.

Business & Economics↗

Effect of likelihood misspecification in Gaussian process-driven autonomous experimentation

In recent years, several groups have designed Autonomous Experiment (AE) models with the aim of using them as an alternative method for neutron scattering scanning. In an AE, Gaussian processes (GPs) are most frequently used due to their interpretability, their non-parametric nature, their universal approximation, and their closed-form predictive distribution. GPs have two key components, namely, the model for the likelihood of a neutron count knowing the underlying dynamic structure factor and the acquisition function. In this paper, we investigate the impact, on the quality of an AE, of the likelihood and acquisition function choices, in energy scans and (Q, ω) ones, with respect to the signal-over-noise ratio. While we hypothesized that the quality of GP predictions would decrease when the normal to Poisson likelihood approximation breaks down at low count rates, we found that the use of the correct Poisson likelihood does not improve the quality of the data collected, as well as yields very poor results in (Q, ω) scans at low count rates. In fact, the best results are obtained with a combination of normal likelihood, including the observation noise, and the change in variance acquisition function. In addition, we find that the performance, or quality of the predictive distribution, is a misleading measure of efficiency, that is, of the quality of the data collected.

Perryman, David Elliott [Inst. Laue-Langevin (ILL)↗

Too Good to Be True? Evaluation of Colonoscopy Sensitivity Assumptions Used in Policy Models

Background: Models can help guide colorectal cancer screening policy. Although models are carefully calibrated and validated, there is less scrutiny of assumptions about test performance. Methods: We examined the validity of the CRC-SPIN model and colonoscopy sensitivity assumptions. Standard sensitivity assumptions, consistent with published decision analyses, assume sensitivity equal to 0.75 for diminutive adenomas (<6 mm), 0.85 for small adenomas (6–10 mm), 0.95 for large adenomas (≥10 mm), and 0.95 for preclinical cancer. We also selected adenoma sensitivity that resulted in more accurate predictions. Targets were drawn from the Wheat Bran Fiber study. In the study, we examined how well the model predicted outcomes measured over a three-year follow-up period, including the number of adenomas detected, the size of the largest adenoma detected, and incident colorectal cancer. Results: Using standard sensitivity assumptions, the model predicted adenoma prevalence that was too low (42.5% versus 48.9% observed, with 95% confidence interval 45.3%–50.7%) and detection of too few large adenomas (5.1% versus 14.% observed, with 95% confidence interval 11.8%–17.4%). Predictions were close to targets when we set sensitivities to 0.20 for diminutive adenomas, 0.60 for small adenomas, 0.80 for 10- to 20-mm adenomas, and 0.98 for adenomas 20 mm and larger. Conclusions: Colonoscopy may be less accurate than currently assumed, especially for diminutive adenomas. Alternatively, the CRC-SPIN model may not accurately simulate onset and progression of adenomas in higher-risk populations. Impact: Misspecification of either colonoscopy sensitivity or disease progression in high-risk populations may affect the predicted effectiveness of colorectal cancer screening. When possible, decision analyses used to inform policy should address these uncertainties.

60 APPLIED LIFE SCIENCES↗

Evaluating Gaussian process metamodels and sequential designs for noisy level set estimation

Abstract We consider the problem of learning the level set for which a noisy black-box function exceeds a given threshold. To efficiently reconstruct the level set, we investigate Gaussian process (GP) metamodels. Our focus is on strongly stochastic simulators, in particular with heavy-tailed simulation noise and low signal-to-noise ratio. To guard against noise misspecification, we assess the performance of three variants: (i) GPs with Student- t observations; (ii) Student- t processes (TPs); and (iii) classification GPs modeling the sign of the response. In conjunction with these metamodels, we analyze several acquisition functions for guiding the sequential experimental designs, extending existing stepwise uncertainty reduction criteria to the stochastic contour-finding context. This also motivates our development of (approximate) updating formulas to efficiently compute such acquisition functions. Our schemes are benchmarked by using a variety of synthetic experiments in 1–6 dimensions. We also consider an application of level set estimation for determining the optimal exercise policy of Bermudan options in finance.

97 MATHEMATICS AND COMPUTING↗