ciemss/pyciemss
Causal and probabilistic reasoning with continuous time dynamical systems
SEARCH · Search NASA
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.
Causal and probabilistic reasoning with continuous time dynamical systems
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.
Intelligent systems require software incorporating probabilistic reasoning, and often times learning. Networks provide a framework and methodology for creating this kind of software. This paper introduces network models based on chain graphs with deterministic nodes. Chain graphs are defined as a hierarchical combination of Bayesian and Markov networks. To model learning, plates on chain graphs are introduced to model independent samples. The paper concludes by discussing various operations that can be performed on chain graphs with plates as a simplification process or to generate learning algorithms.
The success of a landed space exploration mission depends largely on the final landing site. Factors influencing site selection include safety, fuel-consumption, and scientific return. This paper addresses the problem of selecting the best available landing site based on these factors in real-time during autonomous spacecraft descent onto a planetary surface. The problem is modeled probabilistically using Bayesian Networks (BNs). BNs provide a means of representing the causal relationships between variables that impact the quality of a landing site. The final landing site is determined via probabilistic reasoning based on terrain safety derived from on-board sensors, available fuel based on spacecraft descent dynamics, and regions of interest defined by mission scientists.
Topics covered include: Flexible Skins Containing Integrated Sensors and Circuitry; Artificial Hair Cells for Sensing Flows; Video Guidance Sensor and Time-of-Flight Rangefinder; Optical Beam-Shear Sensors; Multiple-Agent Air/Ground Autonomous Exploration Systems; A 640 512-Pixel Portable Long-Wavelength Infrared Camera; An Array of Optical Receivers for Deep-Space Communications; Microstrip Antenna Arrays on Multilayer LCP Substrates; Applications for Subvocal Speech; Multiloop Rapid-Rise/Rapid Fall High-Voltage Power Supply; The PICWidget; Fusing Symbolic and Numerical Diagnostic Computations; Probabilistic Reasoning for Robustness in Automated Planning; Short-Term Forecasting of Radiation Belt and Ring Current; JMS Proxy and C/C++ Client SDK; XML Flight/Ground Data Dictionary Management; Cross-Compiler for Modeling Space-Flight Systems; Composite Elastic Skins for Shape-Changing Structures; Glass/Ceramic Composites for Sealing Solid Oxide Fuel Cells; Aligning Optical Fibers by Means of Actuated MEMS Wedges; Manufacturing Large Membrane Mirrors at Low Cost; Double-Vacuum-Bag Process for Making Resin- Matrix Composites; Surface Bacterial-Spore Assay Using Tb3+/DPA Luminescence; Simplified Microarray Technique for Identifying mRNA in Rare Samples; High-Resolution, Wide-Field-of-View Scanning Telescope; Multispectral Imager With Improved Filter Wheel and Optics; Integral Radiator and Storage Tank; Compensation for Phase Anisotropy of a Metal Reflector; Optical Characterization of Molecular Contaminant Films; Integrated Hardware and Software for No-Loss Computing; Decision-Tree Formulation With Order-1 Lateral Execution; GIS Methodology for Planning Planetary-Rover Operations; Optimal Calibration of the Spitzer Space Telescope; Automated Detection of Events of Scientific Interest; Representation-Independent Iteration of Sparse Data Arrays; Mission Operations of the Mars Exploration Rovers; and More About Software for No-Loss Computing.
We present R2U2 (Realizable, Responsive, Unobtrusive Unit), a hardware- supported tool and framework for the continuous monitoring of safetycritical and embedded cyber-physical systems.With the widespread advent of autonomous systems such as Unmanned Aerial Systems (UAS), satellites, rovers, and cars, real-time, on-board decision making requires unobtrusive monitoring of properties for safety, performance, security, and system health. R2U2 models combine past-time and future-time Metric Temporal Logic, “mission time” Linear Temporal Logic, probabilistic reasoning with Bayesian Networks, and modelbased prognostics. The R2U2 monitoring engine can be instantiated as a hardware solution, running on an FPGA, or as a software component. The FPGA realization enables R2U2 to monitor complex cyber-physical systems without any overhead or instrumentation of the flight software. In this tool exhibition report, we present R2U2 and demonstrate applications on system runtime monitoring, diagnostics, software health management, and security monitoring for a UAS. Our tool demonstration uses a hardware-based processor-in-the-loop “iron-bird” configuration.
The SafeDNN project at NASA Ames explores analysis techniques and tools to ensure that systems that use Deep Neural Networks (DNN) are safe, robust and interpretable. Research directions we are pursuing include: symbolic execution for DNN analysis, label-guided clustering to automatically identify input regions that are robust, parallel and compositional approaches to improve formal SMT-based verification, property inference and automated program repair for DNNs, adversarial training and detection, probabilistic reasoning for DNNs. In this talk I will highlight some of the research advances from SafeDNN, that were already published.
An architecture and supporting methods are presented for the implementation of a resilient condition assessment monitoring system that can adaptively accommodate both cyber and physical anomalies to a monitored system under observation. In particular, the architecture includes three layers: information, assessment, and sensor selection. The information layer estimates probability distributions of process variables based on sensor measurements and assessments of the quality of sensor data. Based on these estimates, the assessment layer then employs probabilistic reasoning methods to assess the plant health. The sensor selection layer selects sensors so that assessments of the plant condition can be made within desired time periods. Resilient features of the developed system are then illustrated by simulations of a simplified power plant model, where a large portion of the sensors are under attack.
This paper shows how to solve problems using probability theory that the fuzzy approaches claim probability cannot solve. By using the view that probabilities are a measure of belief in a proposition in a particular context, limitations imposed by the frequncy interpretations of probability are avoided. The various fuzzy approaches (fuzzy sets, fuzzy logic, possibility theory and higher order generalizations) seem to fill the gap caused by the restricted frequency interpretation. Close examination shows that the fuzzy approaches have exactly the same representation as the corresponding probabilistc approach and include similar calculi. The probabilistic approach assumes less information when the calculi differ.
As robots become increasingly present in human environments, we need robots to be intuitively commanded by and effectively communicate with humans. In particular, non-expert users should be able to communicate task goals with robots. Language emerges as a logical mode of interaction due to its ubiquity in human environments and, more importantly, as the way humans naturally express tasks. Natural language commands present challenges in that robots must reason over ambiguous language probabilistically and reason over commands they may not be able to execute. We present hierarchical semantic frames , which ground commands in robot control primitives through hierarchies that construct high-level commands from lower-level commands. We demonstrate that hierarchical semantic frames allow robots to understand and execute a variety of commands, such as those involving multiple verb meanings, command variations, and compound nouns. The robot quickly processes hierarchical semantic frames and accurately grounds and executes the commanded tasks, demonstrating the power of hierarchical semantic frames for allowing users to intuitively interact with robots.
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.
This paper presents a probabilistic model for various machine learning (ML) applications. While deep learning (DL) has produced state-of-the-art results in many domains, DL models are complex and over-parameterized, which leads to high uncertainty about what the model has learned, as well as its decision process. Further, DL models are not probabilistic, making reasoning about their output challenging. In contrast, the proposed model, referred to as Yet Another Discriminate Analysis(YADA), is less complex than other methods, is based on a mathematically rigorous foundation, and can be utilized for a wide variety of ML tasks including classification, explainability, and uncertainty quantification. YADA is thus competitive in most cases with many state-of-the-art DL models. Ideally, a probabilistic model would represent the full joint probability distribution of its features, but doing so is often computationally expensive and intractable. Hence, many probabilistic models assume that the features are either normally distributed, mutually independent, or both, which can severely limit their performance. YADA is an intermediate model that (1) captures the marginal distributions of each variable and the pairwise correlations between variables and (2) explicitly maps features to the space of multivariate Gaussian variables. Numerous mathematical properties of the YADA model can be derived, thereby improving the theoretic underpinnings of ML. Validation of the model can be statistically verified on new or held-out data using native properties of YADA. However, there are some engineering and practical challenges that we enumerate to make YADA more useful.
Explore the source record for details and available documents.
The paper presents a methodology for satellite power system costing, places approximate limits on the accuracy possible in cost estimates made at this time, and outlines the use of probabilistic cost information in support of the decision-making process. Reasons for using probabilistic costing or risk analysis procedures instead of standard deterministic costing procedures are considered. Components of cost, costing estimating relationships, grass roots costing, and risk analysis are discussed. Risk analysis using a Monte Carlo simulation model is used to estimate future costs.
On March 11, 2011, a magnitude 9.0 earthquake followed by a tsunami caused loss of offsite power and disabled the emergency diesel generators, leading to a prolonged station blackout at the Fukushima Daiichi site. After successful reactor trip for all operating reactors, the inability to remove decay heat over an extended period led to boil-off of the water inventory and fuel uncovery in Units 1-3. A significant amount of metal-water reaction occurred, as evidenced by the quantities of hydrogen generated that led to hydrogen explosions in the auxiliary buildings of the Units 1 & 3, and in the de-fuelled Unit 4. Although it was assumed that extensive fuel damage, including fuel melting, slumping, and relocation was likely to have occurred in the core of the affected reactors, the status of the fuel, vessel, and drywell was uncertain. To understand the possible evolution of the accident conditions at Fukushima Daiichi, a Markov model of the likely state of one of the reactors was constructed and executed under different assumptions regarding system performance and reliability. The Markov approach was selected for several reasons: It is a probabilistic model that provides flexibility in scenario construction and incorporates time dependence of different model states. It also readily allows for sensitivity and uncertainty analyses of different failure and repair rates of cooling systems. While the analysis was motivated by a need to gain insight on the course of events for the damaged units at Fukushima Daiichi, the work reported here provides a more general analytical basis for studying and evaluating severe accident evolution over extended periods of time. This work was performed at the request of the U.S. Department of Energy to explore 'what-if' scenarios in the immediate aftermath of the accidents.
The NESSUS probabilistic analysis computer program has been developed with a built-in finite element analysis program NESSUS/FEM. However, the NESSUS/FEM program is specialized for engine structures and may not contain sufficient features for other applications. In addition, users often become well acquainted with a particular finite element code and want to use that code for probabilistic structural analysis. For these reasons, this work was undertaken to develop an interface between NESSUS and NASTRAN such that NASTRAN can be used for the finite element analysis and NESSUS can be used for the probabilistic analysis. In addition, NESSUS was restructured such that other finite element codes could be more easily coupled with NESSUS. NESSUS has been enhanced such that NESSUS will modify the NASTRAN input deck for a given set of random variables, run NASTRAN and read the NASTRAN result. The coordination between the two codes is handled automatically. The work described here was implemented within NESSUS 6.2 which was delivered to NASA in September 1995. The code runs on Unix machines: Cray, HP, Sun, SGI and IBM. The new capabilities have been implemented such that a user familiar with NESSUS using NESSUS/FEM and NASTRAN can immediately use NESSUS with NASTRAN. In other words, the interface with NASTRAN has been implemented in an analogous manner to the interface with NESSUS/FEM. Only finite element specific input has been changed. This manual is written as an addendum to the existing NESSUS 6.2 manuals. We assume users have access to NESSUS manuals and are familiar with the operation of NESSUS including probabilistic finite element analysis. Update pages to the NESSUS PFEM manual are contained in Appendix E. The finite element features of the code and the probalistic analysis capabilities are summarized.
In many domains, automated reasoning tools must represent graphs of causally linked events. These include fault-tree analysis, probabilistic risk assessment (PRA), planning, procedures, medical reasoning about disease progression, and functional architectures. Each of these fields has its own requirements for the representation of causation, events, actors and conditions. The representations include ontologies of function and cause, data dictionaries for causal dependency, failure and hazard, and interchange formats between some existing tools. In none of the domains has a generally accepted interchange format emerged. The paper makes progress towards interoperability across the wide range of causal analysis methodologies. We survey existing practice and emerging interchange formats in each of these fields. Setting forth a set of terms and concepts that are broadly shared across the domains, we examine the several ways in which current practice represents them. Some phenomena are difficult to represent or to analyze in several domains. These include mode transitions, reachability analysis, positive and negative feedback loops, conditions correlated but not causally linked and bimodal probability distributions. We work through examples and contrast the differing methods for addressing them. We detail recent work in knowledge interchange formats for causal trees in aerospace analysis applications in early design, safety and reliability. Several examples are discussed, with a particular focus on reachability analysis and mode transitions. We generalize the aerospace analysis work across the several other domains. We also recommend features and capabilities for the next generation of causal knowledge representation standards.
ICI has developed a unique and novel method of certifying a Terabyte optical tape. The tape quality is guaranteed as a statistical upper limit on the probability of uncorrectable errors. This is called the Corrected Byte Error Rate or CBER. We developed this probabilistic method because of two reasons why error rate cannot be measured directly. Firstly, written data is indelible, so one cannot employ write/read tests such as used for magnetic tape. Secondly, the anticipated error rates need impractically large samples to measure accurately. For example, a rate of 1E-12 implies only one byte in error per tape. The archivability of ICI 1012 Data Storage Tape in general is well characterized and understood. Nevertheless, customers expect performance guarantees to be supported by test results on individual tapes. In particular, they need assurance that data is retrievable after decades in archive. This paper describes the mathematical basis, measurement apparatus and applicability of the certification method.