A Language for Probabilistic Modeling of Scientific Data
We describe a portable container which allows specification of the probablistic relations between several varibles.
models structures Stochastic Systems Scientific Da↗
SEARCH · Search NASA
Results for “probabilistic modeling scientific data”
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.
A Language for Probabilistic Modeling of Scientific Data
We describe a portable container which allows specification of the probabilistic relations between several variables. The applications motivating this work are mainly scientific inference problems.
probabilistic modeling scientific data↗
Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments
Artificial intelligence (AI) generative models, such as generative adversarial networks (GANs), variational autoencoders, and normalizing flows, have been widely used and studied as efficient alternatives for traditional scientific simulations. However, they have several drawbacks, including training instability and inability to cover the entire data distribution, especially for regions where data are rare. This is particularly challenging for whole-event, full-detector simulations in high-energy heavy-ion experiments, such as sPHENIX at the Relativistic Heavy Ion Collider and Large Hadron Collider experiments, where thousands of particles are produced per event and interact with the detector. This work investigates the effectiveness of denoising diffusion probabilistic models (DDPMs) as an AI-based generative surrogate model for the sPHENIX experiment that includes the heavy-ion event generation and response of the entire calorimeter stack. DDPM performance in sPHENIX simulation data is compared with a popular rival, GANs. Results show that both DDPMs and GANs can reproduce the data distribution where the examples are abundant (low-to-medium calorimeter energies). Nonetheless, DDPMs significantly outperform GANs, especially in high-energy regions where data are rare. Additionally, DDPMs exhibit superior stability compared to GANs. The results are consistent between both central and peripheral centrality heavy-ion collision events. Moreover, DDPMs offer a substantial speedup of approximately a factor of 100 compared to the traditional Geant4 simulation method.
42 ENGINEERING↗
Sequential Decision Making (SDM) for Mesh Refinement and Model Selection in Multiscale, Multi-Physics Applications
Intelligent automation and decision support are needed to enhance computational efficiency and robustness in multiscale and multi-physics problems, including materials science, manufacturing, and climate and weather modeling. Current scientific computing approaches for enabling decisions by scientists fail to explore the role of learning, reasoning, and probabilistic planning. Often these decisions are not performed in real-time during the computation but are made prior to the start of the computation, which must be interrupted in order to make changes to the prior choices. Such interruptions at different stages of the computation increase the total computing time and the need for a human expert to frequently monitor the results. State of art scientific computing methods consist of rule-based algorithms that cannot automatically adapt to a dynamically changing computing environment. The development of a Sequential Decision Making (SDM) framework will automate scientific computing by optimizing the policies for mesh refinement, time-stepping, model and algorithm selection, resource allocation, and pre and post-processing. Our agent SDM framework for scientific computing will consist of data-driven learning (Classifier), automated reasoning (contextual knowledge), and probabilistic planning (Reinforcement Learning). In this project, we focused on three problems to demonstrate our SDM framework on a set of ordinary and partial differential equations. Classification of Lorenz system regions using Feed-Forward Neural Networks examined learning in the SDM framework. On the other hand, reasoning and planning in the SDM framework were used in two problems: adaptive time-stepping for nonlinear ODEs using on-policy RL algorithms, and adaptive mesh refinement for 2-D PDEs using off-policy RL algorithms.
97 MATHEMATICS AND COMPUTING↗
Probabilistic data fusion and physics-informed machine learning: A new paradigm for modeling under uncertainty, and its application to accelerating the discovery of new materials
In this report we summarize the work conducted by PI Perdikaris and his group under this Early Career project DE–SC0019116 during the period of 09/01/2018 – 08/31/2023. The central aim of the work was to introduce a new paradigm for scientific data analysis that can seamlessly synthesize rigorous mathematical modeling with data of variable fidelity (e.g., measurements at multiple scales/resolutions or predictions of variable fidelity models) and multiple modalities (e.g., images, time–series, or scattered measurements). The setting we are interested in involves complex systems that are partially observed and whose dynamical behavior could be hard to model or totally unknown. The inherent uncertainty associated with this setting necessitates a departure from the classical deterministic realm of modeling and scientific computation, and, consequently, our main building blocks can no longer be crisp deterministic numbers and governing laws, but instead we must operate with probabilistic models.
97 MATHEMATICS AND COMPUTING↗
A statistical inference approach for the retrieval of the atmospheric ozone profile from simulated satellite measurements of solar backscattered ultraviolet radiation
NASA's Mission to Planet Earth (MTPE) will address important interdisciplinary and environmental issues such as global warming, ozone depletion, deforestation, acid rain, and the like with its long term satellite observations of the Earth and with its comprehensive Data and Information System. Extensive sets of satellite observations supporting MTPE will be provided by the Earth Observing System (EOS), while more specific process related observations will be provided by smaller Earth Probes. MTPE will use data from ground and airborne scientific investigations to supplement and validate the global observations obtained from satellite imagery, while the EOS satellites will support interdisciplinary research and model development. This is important for understanding the processes that control the global environment and for improving the prediction of events. In this paper we illustrate the potential for powerful artificial intelligence (AI) techniques when used in the analysis of the formidable problems that exist in the NASA Earth Science programs and of those to be encountered in the future MTPE and EOS programs. These techniques, based on the logical and probabilistic reasoning aspects of plausible inference, strongly emphasize the synergetic relation between data and information. As such, they are ideally suited for the analysis of the massive data streams to be provided by both MTPE and EOS. To demonstrate this, we address both the satellite imagery and model enhancement issues for the problem of ozone profile retrieval through a method based on plausible scientific inferencing. Since in the retrieval problem, the atmospheric ozone profile that is consistent with a given set of measured radiances may not be unique, an optimum statistical method is used to estimate a 'best' profile solution from the radiances and from additional a priori information.
Bonavito, N. L.↗
Robotic Planning under Uncertainty in Spatiotemporal Environments in Expeditionary Science
In the expeditionary sciences, spatiotemporally varying environments -- hydrothermal plumes, algal blooms, lava flows, or animal migrations -- are ubiquitous. Mobile robots are uniquely well-suited to study these dynamic, mesoscale natural environments. We formalize expeditionary science as a sequential decision-making problem, modeled using the language of partially-observable Markov decision processes (POMDPs). Solving the expeditionary science POMDP under real-world constraints requires efficient probabilistic modeling and decision-making in problems with complex dynamics and observational models. Previous work in informative path planning, adaptive sampling, and experimental design have shown compelling results, largely in static environments, using data-driven models and information-based rewards. However, these methodologies do not trivially extend to expeditionary science in spatiotemporal environments: they generally do not make use of scientific knowledge such as equations of state dynamics, they focus on information gathering as opposed to scientific task execution, and they make use of decision-making approaches that scale poorly to large, continuous problems with long planning horizons and real-time operational constraints. In this work, we discuss these and other challenges related to probabilistic modeling and decision-making in expeditionary science, and present some of our preliminary work that addresses these gaps. We ground our results in a real expeditionary science deployment of an autonomous underwater vehicle (AUV) in the deep ocean for hydrothermal vent discovery and characterization. Our concluding thoughts highlight remaining work to be done, and the challenges that merit consideration by the reinforcement learning and decision-making community.
Preston, Victoria↗
Trust-Enhancing Probabilistic Transfer Learning for Sparse and Noisy Data Environments
There is an increasing aspiration to utilize machine learning (ML) for various tasks of relevance to national security. ML models have thus far been mostly applied to tasks and domains that, while impactful, have sufficient volume of data. For predictive tasks of national security relevance, ML models of great capacity (ability to approximate nonlinear trends in input-output maps) are often needed to capture the complex underlying physics. However, scientific problems of relevance to national security are often accompanied by various sources of sparse and/or incomplete data, including experiments and simulations, across different regimes of operation, of varying degrees of fidelity, and include noise with different characteristics and/or intensity. State-of-the-art ML models, despite exhibiting superior performance on the task and domain they were trained on, may suffer detrimental loss in performance in such sparse data environments. This report summarizes the results of the Laboratory Directed Research and Development project entitled Trust-Enhancing Probabilistic Transfer Learning for Sparse and Noisy Data Environments. The objective of the project was to develop a new transfer learning (TL) framework that aims to adaptively blend the data across different sources in tackling one task of interest, resulting in enhanced trustworthiness of ML models for mission- and safety-critical systems. The proposed framework determines when it is worth applying TL and how much knowledge is to be transferred, despite uncontrollable uncertainties. The framework accomplishes this by leveraging concepts and techniques from the fields of Bayesian inverse modeling and uncertainty quantification, relying on strong mathematical foundations of probability and measure theories to devise new uncertainty-aware TL workflows.
97 MATHEMATICS AND COMPUTING↗
Bayesian Tensor Decompositions for Scalable Supervised Learning of Scientific Data (Final Report)
In this document we highlight the detailed accomplishments and progress that we have made in this period. This progress seeks to address the three main objectives to provide new algorithms for quantifying uncertainty in low-multilinear-rank models and to leverage them for data analysis. These include: (1) develop probabilistic models for low-multilinear-rank functions; (2) develop a suite of Bayesian learning approaches to learn the probabilistic models from data; (3) apply the techniques on challenging problems arising in DOE-relevant applications.
97 MATHEMATICS AND COMPUTING↗
Flood and Landslide Applications of Near Real-time Satellite Rainfall Products
Floods and associated landslides are one of the most widespread natural hazards on Earth, responsible for tens of thousands of deaths and billions of dollars in property damage every year. During 1993-2002, over 1000 of the more than 2,900 natural disasters reported were due to floods. These floods and associated landslides claimed over 90,000 lives, affected over 1.4 billion people and cost about $210 billion. The impact of these disasters is often felt most acutely in less developed regions. In many countries around the world, satellite-based precipitation estimation may be the best source of rainfall data due to lack of surface observing networks. Satellite observations can be of essential value in improving our understanding of the occurrence of hazardous events and possibly in lessening their impact on local economies and in reducing injuries, if they can be used to create reliable warning systems in cost-effective ways. This article addressed these opportunities and challenges by describing a combination of satellite-based real-time precipitation estimation with land surface characteristics as input, with empirical and numerical models to map potential of landslides and floods. In this article, a framework to detect floods and landslides related to heavy rain events in near-real-time is proposed. Key components of the framework are: a fine resolution precipitation acquisition system; a comprehensive land surface database; a hydrological modeling component; and landslide and debris flow model components. A key precipitation input dataset for the integrated applications is the NASA TRMM-based multi-satellite precipitation estimates. This dataset provides near real-time precipitation at a spatial-temporal resolution of 3 hours and 0.25deg x 0.25deg. By careful integration of remote sensing and in-situ observations, and assimilation of these observations into hydrological and landslide/debris flow models with surface topographic information, prediction of useful probabilistic maps of landslide and floods for emergency management in a timely manner is possible. Early results shows that the potential exists for successful application of satellite precipitation data in improving/developing global monitoring systems for flood/landslide disaster preparedness and management. The scientific and technological prototype can be first applied in a representative test-bed and then the information deliverables for the region can be tailored to the societal and economic needs of the represented affected countries.
Hong, Yang↗
Bayesian averaging for ground state masses of atomic nuclei in a Machine Learning approach
We present global predictions of the ground state mass of atomic nuclei based on a novel Machine Learning algorithm. We combine precision nuclear experimental measurements together with theoretical predictions of unmeasured nuclei. This hybrid data set is used to train a probabilistic neural network. In addition to training on this data, a physics-based loss function is employed to help refine the solutions. The resultant Bayesian averaged predictions have excellent performance compared to the testing set and come with well-quantified uncertainties which are critical for contemporary scientific applications. We assess extrapolations of the model’s predictions and estimate the growth of uncertainties in the region far from measurements.
74 ATOMIC AND MOLECULAR PHYSICS↗
Validation Metrics for Fixed Effects and Mixed-Effects Calibration
The modern scientific process often involves the development of a predictive computational model. To improve its accuracy, a computational model can be calibrated to a set of experimental data. A variety of validation metrics can be used to quantify this process. Some of these metrics have direct physical interpretations and a history of use, while others, especially those for probabilistic data, are more difficult to interpret. In this work, a variety of validation metrics are used to quantify the accuracy of different calibration methods. Frequentist and Bayesian perspectives are used with both fixed effects and mixed-effects statistical models. Through a quantitative comparison of the resulting distributions, the most accurate calibration method can be selected. Two examples are included which compare the results of various validation metrics for different calibration methods. It is quantitatively shown that, in the presence of significant laboratory biases, a fixed effects calibration is significantly less accurate than a mixed-effects calibration. This is because the mixed-effects statistical model better characterizes the underlying parameter distributions than the fixed effects model. The results suggest that validation metrics can be used to select the most accurate calibration model for a particular empirical model with corresponding experimental data.
97 MATHEMATICS AND COMPUTING↗
Predicting potential adverse events using safety data from marketed drugs
Abstract Background While clinical trials are considered the gold standard for detecting adverse events, often these trials are not sufficiently powered to detect difficult to observe adverse events. We developed a preliminary approach to predict 135 adverse events using post-market safety data from marketed drugs. Adverse event information available from FDA product labels and scientific literature for drugs that have the same activity at one or more of the same targets, structural and target similarities, and the duration of post market experience were used as features for a classifier algorithm. The proposed method was studied using 54 drugs and a probabilistic approach of performance evaluation using bootstrapping with 10,000 iterations. Results Out of 135 adverse events, 53 had high probability of having high positive predictive value. Cross validation showed that 32% of the model-predicted safety label changes occurred within four to nine years of approval (median: six years). Conclusions This approach predicts 53 serious adverse events with high positive predictive values where well-characterized target-event relationships exist. Adverse events with well-defined target-event associations were better predicted compared to adverse events that may be idiosyncratic or related to secondary target effects that were poorly captured. Further enhancement of this model with additional features, such as target prediction and drug binding data, may increase accuracy.
Daluwatte, Chathuri↗
Climate Intervention Assessment and Attribution
Focal Area(s): To ensure the US is positioned to scientifically attribute noncooperative climate interventions, we propose developing a foundational analytical framework for increased confidence in the assessment and attribution of observed changes in the climate. This framework will enable probabilistic attribution of prospective climate interventions. The target is to glean insight from complex Earth system data (Focal Area 3) by using AI to develop a prediction system comprised of a hierarchy of models (Focal Area 2).
54 ENVIRONMENTAL SCIENCES↗
Multi-Modal Active Perception for Autonomously Selecting Landing Sites on Icy Moons
Selecting suitable landing sites is fundamental to achieving many mission objectives in planetary robotic lander missions. However, due to sensing limitations, landing sites which are both safe and scientifically valuable often cannot be determined reliably from orbit, particularly, in icy moon missions where orbital sensing data is noisy and incomplete. This paper presents an active perception approach to Entry Descent and Landing (EDL) which enables the lander to autonomously plan informative descent trajectories, acquire high quality sensing data during descent and exploit this additional information to select higher utility landing sites. Our approach consists of two components: probabilistic modeling of landing site features and approximate trajectory planning using a sampling based planner. The proposed framework allows the lander to plan long horizons paths and remain robust to noisy data. Results in simulated environments show large performance improvements over alternative approaches and show promise that our approach has strong potential to improve science return of not only icy moon missions but EDL systems in general.
autonomy↗
Evaluating Probability of Containment Effectiveness at a GCS Sites using integrated assessment modeling approach with Bayesian decision Networks
Improved scientific and engineering understanding of the behavior of geologic CO2 storage together with established regulatory framework and incentive structures raise the prospects for accelerated, large-scale deployment of this greenhouse gas emissions reduction approach. Incentive structures call for the establishment of appropriate verification and accounting approaches to support claims of the integrity of a geologic storage complex and to justify taking credit for long-term storage. In this study, we present a framework for assessing the probability of containment effectiveness over the lifetime of a geologic carbon storage site (e.g., after 70 years of injection and post-injection site performance) using forward stochastic model realizations based on site characterization data and using a monitoring-informed Bayesian network based on hypothetical detectability from surface seismic surveys over the site injection and post-injection phases. The National Risk Assessment Partnership’s open-source Integrated Assessment Model (NRAP-Open-IAM) was utilized to develop an ensemble of 10,000 a priori stochastic forecasts of CO2 containment. Those simulations were used to train the Bayesian network model to estimate the prior probabilities of the CO2 leakage mass into overlying, monitorable aquifers considering the uncertainties in the reservoir properties, permeability of potentially leaky wells and the overlying aquifers. The conditional probabilities in the Bayesian network were either learned from the NRAP-Open-IAM simulations or derived from the predefined detection thresholds for the monitoring method. Observations obtained from monitoring, over time during the site operation phases were then used to generate updated posterior probabilities of containment (and any loss from containment) in the Bayesian network by propagating the prior probabilities through the conditional probabilities. We demonstrate how to construct and use the Bayesian network for verifying the long-term storage complex effectiveness informed by monitoring based on the NRAP-Open-IAM simulations previously developed for the FutureGen 2.0 site. This approach may have relevance for stake holders to demonstrate secure geologic storage, provide a defensible, probabilistic approach to claim credit for geologic storage, and to estimate the likelihood that any fraction of the claimed credit may need to be refunded to the creditor based on available monitoring information.
Bayesian network, Risk assessment, Monitoring, car↗
Modeling interconnections of safety and financial performance of nuclear power plants, part 3: Spatiotemporal probabilistic physics-of-failure analysis and its connection to safety and financial performance
Here, this paper is a byproduct of a line of research by the authors to analyze interrelationships of safety and financial performance of nuclear power plants (NPPs). The result of this line of research is summarized in three parts: Part 1 covers a categorical review of relevant literature and the theoretical bases that support the methodological developments in Part 2. Part 2 introduces an Integrated Enterprise Risk Management (I-ERM) methodological framework to quantify the interconnections of safety and financial performance with a focus on operation and maintenance (O&M) of NPPs. Part 2 has also demonstrated the applicability and values of the I-ERM methodology through an NPP case study. This paper is Part 3, where detailed development and implementation of one of the I-ERM modules, i.e., probabilistic physics-of-failure (PPoF) analysis, and its connection with safety and financial performance is reported. In this article, the physical failure modeling for hardware components is advanced by incorporating finite element analysis (FEA) into PPoF analysis and coupling the FEA-based PPoF with the maintenance performance through a renewal process model. This article covers two scientific contributions: (i) first-of-its-kind incorporation of FEA into the PPoF model of thermal fatigue for NPP components; and (ii) advancing the interface between the PPoF analysis and the renewal process model in order to deal with spatiotemporal FEA outputs and to efficiently estimate the physical transition rates even when the PPoF outputs are dominated by success data. Through the incorporation of FEA, the resolution of the PPoF analysis is enhanced as spatiotemporal conditions such as stress and temperature can be considered explicitly instead of relying on simplified assumptions or analytical models with reduced spatiotemporal dimensions. To demonstrate an application of the FEA-based PPoF analysis and its coupling with maintenance through the renewal process model, a case study is conducted using excess letdown elbow piping in the chemical and volume control system of a Pressurized Water Reactor.
22 GENERAL STUDIES OF NUCLEAR REACTORS↗
In-Situ Inference: Bringing Advanced Data Science Into Exascale Simulations
As simulations generate ever-increasing amounts of data, there are correspondingly richer opportunities for analysis and scientific discovery - discoveries that will be missed if most of the data must be discarded before it is analyzed. Because future exascale architectures will be increasingly storage-limited, it will not be possible to save the vast majority of simulation data for later analysis, requiring analysis to occur “in-situ” within the simulation. However, existing in-situ data analysis frameworks provide little or no support for one of the most sophisticated forms of data science: probabilistic statistical modeling or uncertainty quantification (UQ), and the accompanying challenge of inference - fitting those statistical models to massive simulation output. Our goal is to develop the fundamental statistical algorithms and computer science needed to perform statistical inference in-situ (in HPC simulations) to the full stream of data those simulations generate.
97 MATHEMATICS AND COMPUTING↗