Results for “Probability estimates” — Page 13

NASA NTRS1994

Certification methodology applied to the NASA experimental radar system

The objective of the research is to apply selected FAA certification techniques to the NASA experimental wind shear radar system. Although there is no intent to certify the NASA system, the procedures developed may prove useful to manufacturers that plan to undergo the certification process. The certification methodology for forward-looking wind shear detection radars will require estimation of system performance in several FAA-specified microburst/clutter scenarios as well as the estimation of probabilities of missed and false hazard alerts under general operational conditions. Because of the near-impossibility of obtaining these results experimentally, analytical and simulation approaches must be used. Hazard detection algorithms were developed that derived predictive estimates of aircraft hazard from basic radar measurements of weather reflectivity and radial wind velocity. These algorithms were designed to prevent false alarms due to ground clutter while providing accurate predictions of hazard to the aircraft due to weather. A method of calculation of the probability of missed and false hazard alerts has been developed that takes into account the effect of the various algorithms used in the system and provides estimates of the probability of missed and false alerts per microburst encounter under weather conditions found at Denver, Kansas City, and Orlando. Simulation techniques have been developed that permit the proper merging of radar ground clutter data (obtained from flight tests) with simulated microburst data (obtained from microburst models) to estimate system performance using the microburst/clutter scenarios defined by the FAA.

Britt, Charles L.↗

DOE OSTI2021

Radar-Based Bayesian Estimation of Ice Crystal Growth Parameters within a Microphysical Model

The potential for polarimetric Doppler radar measurements to improve predictions of ice microphysical processes within an idealized model–observational framework is examined. In an effort to more rigorously constrain ice growth processes (e.g., vapor deposition) with observations of natural clouds, a novel framework is developed to compare simulated and observed radar measurements, coupling a bulk adaptive-habit model of vapor growth to a polarimetric radar forward model. Bayesian inference on key microphysical model parameters is then used, via a Markov chain Monte Carlo sampler, to estimate the probability distribution of the model parameters. The statistical formalism of this method allows for robust estimates of the optimal parameter values, along with (non-Gaussian) estimates of their uncertainty. To demonstrate this framework, observations from Department of Energy radars in the Arctic during a case of pristine ice precipitation are used to constrain vapor deposition parameters in the adaptive habit model. The resulting parameter probability distributions provide physically plausible changes in ice particle density and aspect ratio during growth. A lack of direct constraint on the number concentration produces a range of possible mean particle sizes, with the mean size inversely correlated to number concentration. Consistency is found between the estimated inherent growth ratio and independent laboratory measurements, increasing confidence in the parameter PDFs and demonstrating the effectiveness of the radar measurements in constraining the parameters. Furthermore, the combined Doppler and polarimetric observations produce the highest-confidence estimates of the parameter PDFs, with the Doppler measurements providing a stronger constraint for this case.

54 ENVIRONMENTAL SCIENCES↗

NASA NTRS2021

Radar-Based Bayesian Estimation of Ice Crystal Growth Parameters within a Microphysical Model

The potential for polarimetric Doppler radar measurements to improve predictions of ice microphysical processes within an idealized model–observational framework is examined. In an effort to more rigorously constrain ice growth processes (e.g., vapor deposition) with observations of natural clouds, a novel framework is developed to compare simulated and observed radar measurements, coupling a bulk adaptive-habit model of vapor growth to a polarimetric radar forward model. Bayesian inference on key microphysical model parameters is then used, via a Markov chain Monte Carlo sampler, to estimate the probability distribution of the model parameters. The statistical formalism of this method allows for robust estimates of the optimal parameter values, along with (non-Gaussian) estimates of their uncertainty. To demonstrate this framework, observations from Department of Energy radars in the Arctic during a case of pristine ice precipitation are used to constrain vapor deposition parameters in the adaptive habit model. The resulting parameter probability distributions provide physically plausible changes in ice particle density and aspect ratio during growth. A lack of direct constraint on the number concentration produces a range of possible mean particle sizes, with the mean size inversely correlated to number concentration. Consistency is found between the estimated inherent growth ratio and independent laboratory measurements, increasing confidence in the parameter PDFs and demonstrating the effectiveness of the radar measurements in constraining the parameters. The combined Doppler and polarimetric observations produce the highest-confidence estimates of the parameter PDFs, with the Doppler measurements providing a stronger constraint for this case.

Robert S. Schrom↗

NASA NTRS2018

Predicting the Consequences of MMOD Penetrations on the International Space Station

The threat from micrometeoroid and orbital debris (MMOD) impacts on space vehicles is often quantified in terms of the probability of no penetration (PNP). However, for large spacecraft, especially those with multiple compartments, a penetration may have a number of possible outcomes. The extent of the damage (diameter of hole, crack length or penetration depth), the location of the damage relative to critical equipment or crew, crew response, and even the time of day of the penetration are among the many factors that can affect the outcome. For the International Space Station (ISS), a Monte-Carlo style software code called Manned Spacecraft Crew Survivability (MSCSurv) is used to predict the probability of several outcomes of an MMOD penetration-broadly classified as loss of crew (LOC), crew evacuation (Evac), loss of escape vehicle (LEV), and nominal end of mission (NEOM). By generating large numbers of MMOD impacts (typically in the billions) and tracking the consequences, MSCSurv allows for the inclusion of a large number of parameters and models as well as enabling the consideration of uncertainties in the models and parameters. MSCSurv builds upon the results from NASA's Bumper software (which provides the probability of penetration and critical input data to MSCSurv) to allow analysts to estimate the probability of LOC, Evac, LEV, and NEOM. This paper briefly describes the overall methodology used by NASA to quantify LOC, Evac, LEV, and NEOM with particular emphasis on describing in broad terms how MSCSurv works and its capabilities and most significant models.

Hyde, James↗

NASA NTRS2019

Consequences of MMOD Penetrations on the International Space Station

Risk from micrometeoroid and orbital debris (MMOD) impacts on space vehicles is often quantified in terms of the probability of no penetration (PNP). However, for large spacecraft, especially those with multiple compartments, a penetration may have a number of possible outcomes. The extent of the damage (diameter of hole, crack length or penetration depth), the location of the damage relative to critical equipment or crew, crew response, and even the time of day of the penetration are among the many factors that can affect the outcome. For the International Space Station (ISS), a Monte-Carlo style software code called Manned Spacecraft Crew Survivability (MSCSurv) is used to predict the probability of several outcomes of an MMOD penetration—broadly classified as loss of crew (LOC), crew evacuation (Evac), loss of escape vehicle (LEV), and nominal end of mission (NEOM). By generating large numbers of MMOD impacts (typically in the billions) and tracking the consequences, MSCSurv allows for the inclusion of a large number of parameters and models as well as enabling the consideration of uncertainties in the models and parameters. MSCSurv builds upon the results from NASA’s Bumper software (which provides the probability of penetration and critical input data to MSCSurv) to allow analysts to estimate the probability of LOC, Evac, LEV, and NEOM. This paper provides an overview of the methodology used by NASA to quantify LOC, Evac, LEV, and NEOM with particular emphasis on describing in broad terms how MSCSurv works and its capabilities and most significant models.

Evans, Hilary J.↗

NASA NTRS2010

Probabilistic Assessment of Cancer Risk from Solar Particle Events

For long duration missions outside of the protection of the Earth s magnetic field, space radiation presents significant health risks including cancer mortality. Space radiation consists of solar particle events (SPEs), comprised largely of medium energy protons (less than several hundred MeV); and galactic cosmic ray (GCR), which include high energy protons and heavy ions. While the frequency distribution of SPEs depends strongly upon the phase within the solar activity cycle, the individual SPE occurrences themselves are random in nature. We estimated the probability of SPE occurrence using a non-homogeneous Poisson model to fit the historical database of proton measurements. Distributions of particle fluences of SPEs for a specified mission period were simulated ranging from its 5 th to 95th percentile to assess the cancer risk distribution. Spectral variability of SPEs was also examined, because the detailed energy spectra of protons are important especially at high energy levels for assessing the cancer risk associated with energetic particles for large events. We estimated the overall cumulative probability of GCR environment for a specified mission period using a solar modulation model for the temporal characterization of the GCR environment represented by the deceleration potential (^). Probabilistic assessment of cancer fatal risk was calculated for various periods of lunar and Mars missions. This probabilistic approach to risk assessment from space radiation is in support of mission design and operational planning for future manned space exploration missions. In future work, this probabilistic approach to the space radiation will be combined with a probabilistic approach to the radiobiological factors that contribute to the uncertainties in projecting cancer risks.

Kim, Myung-Hee Y.↗

NASA NTRS2006

Earth Satellite Population Instability: Underscoring the Need for Debris Mitigation

A recent study by NASA indicates that the implementation of international orbital debris mitigation measures alone will not prevent a significant increase in the artificial Earth satellite population, beginning in the second half of this century. Whereas the focus of the aerospace community for the past 25 years has been on the curtailment of the generation of long-lived orbital debris, active remediation of the current orbital debris population should now be reconsidered to help preserve near-Earth space for future generations. In particular, we show in this paper that even if launch operations were to cease today, the population of space debris would continue to grow. Further, proposed remediation techniques do not appear to offer a viable solution. We therefore recommend that, while the aerospace community maintains the current debris-limiting mission regulations and postmission disposal procedures, future emphasis should be placed on finding new remediation technologies for solving this growing problem. Since the launch of Sputnik 1, space activities have created an orbital debris environment that poses increasing impact risks to existing space systems, including human space flight and robotic missions (1, 2). Currently, more than 9,000 Earth orbiting man-made objects (including many breakup fragments), with a combined mass exceeding 5 million kilograms, are tracked by the US Space Surveillance Network and maintained in the US satellite catalog (3-5). Three accidental collisions between cataloged satellites during the period from late 1991 to early 2005 have already been documented (6), although fortunately none resulted in the creation of large, trackable debris clouds. Several studies conducted during 1991-2001 demonstrated, with assumed future launch rates, the unintended growth potential of the Earth satellite population, resulting from random, accidental collisions among resident space objects (7-13). In some low Earth orbit (LEO) altitude regimes where the number density of satellites is above a critical spatial density, the production rate of new satellites (i.e., debris) due to collisions exceeds the loss of objects due to orbital decay. NASA s evolutionary satellite population model LEGEND (LEO-to-GEO Environment Debris model), developed by the Orbital Debris Program Office at the NASA Lyndon B. Johnson Space Center, is a high fidelity three-dimensional physical model that is capable of simulating the historical satellite environment, as well as the evolution of future debris populations (14, 15). The subject study assumed no rocket bodies and spacecraft were launched after December 2004, and no future disposal maneuvers were allowed for existing spacecraft, few of which currently have such a capability. The rate of satellite explosions would naturally decrease to zero within a few decades as the current satellite population ages. The LEGEND future projection adopts a Monte Carlo approach to simulate future on-orbit explosions and collisions. Within a given projection time step, once the explosion probability is estimated for an intact object, a random number is drawn and compared with the probability to determine if an explosion would occur. A similar procedure is applied to collisions for each pair of target and projectile involved within the same time step. Due to the nature of the Monte Carlo process, multiple projection runs must be performed and analyzed before one can draw reliable and meaningful conclusions from the outcome. A total of fifty, 200-year future projection Monte Carlo simulations were executed and evaluated (16).

Liou, Jer-chyi↗

NASA NTRS1990

Anytime synthetic projection: Maximizing the probability of goal satisfaction

A projection algorithm is presented for incremental control rule synthesis. The algorithm synthesizes an initial set of goal achieving control rules using a combination of situation probability and estimated remaining work as a search heuristic. This set of control rules has a certain probability of satisfying the given goal. The probability is incrementally increased by synthesizing additional control rules to handle 'error' situations the execution system is likely to encounter when following the initial control rules. By using situation probabilities, the algorithm achieves a computationally effective balance between the limited robustness of triangle tables and the absolute robustness of universal plans.

Drummond, Mark↗

NASA NTRS1968

Charts designate probable future oceanographic research fields

Charts outline the questions and problems of oceanographic research in the future. NASA uses the charts to estimate the probable requirements for instrumentation carried by satellites engaged in cooperative programs with other agencies concerned with identification, analysis, and solution of many of these problems.

Source record↗

DOE OSTI2020

A Rapid Population Assessment Method for Wild Pigs Using Baited Cameras at 3 Study Sites

ABSTRACT Reliable and efficient population estimates are a critical need for effective management of invasive wild pigs ( Sus scrofa ). We evaluated the use of 10‐day camera grids for rapid population assessment (RPA) of wild pigs at 3 study sites that varied in vegetation communities and wild pig densities. Study areas included Buck Island Ranch, Florida; Tejon Ranch, California; and the Savannah River Site, South Carolina, USA, during 2016–2018. Rapid population assessments grids were composed of baited camera traps spaced approximately 500 or 750 m apart. Two RPA grids were deployed per study site and each grid was deployed twice (4–6 months apart) to assess changes in response to season or population control efforts. We assessed the ability of RPA grids to track population trends, how camera number influenced estimate precision, and how relative abundance indices related to density estimates. We detected changes in occupancy probability, detection probability, and N‐mixture estimates following removal operations and between seasons, but the ability of RPA grids to track population trends was dependent on the statistical method used and number of cameras traps. Increasing the number of cameras traps used in RPA grids increased precision, and these results can be used in determining survey design and estimate choice. We found that estimates of occupancy probability, detection probability, and N‐mixture estimates were positively correlated with spatially explicit capture–recapture density estimates. Thus, these less labor‐intensive estimates from RPA grids showed potential to index the relative abundance of wild pigs in some systems. Our evaluation of RPAs indicates that using study‐specific combinations of statistical method and number of cameras can provide a useful tool for monitoring wild pig presence, tracking population trends, and evaluating the effectiveness of management actions. © 2020 The Wildlife Society.

Schlichting, Peter E.↗

DOE OSTI2020

Probabilistic Zonal Reserve Requirements for Improved Energy Deliverability with Wind Power

In power systems with high penetration of renewable energy resources, uncertainty and variability of these stochastic resources introduce additional challenges for the operation of power systems. To improve the power system's reliability in the face of uncertainty, reserves are required as additional generation capacity to rebalance the power system following random disturbances. However, reserve deliverability is not guaranteed, because it may encounter potential transmission line congestion. Zonal reserve requirements can address this issue, but operators lack efficient ways to allocate reserves to zones while accounting for wind power forecast uncertainty. Herein we propose a methodology for probabilistic zonal reserve requirements to address wind power forecast uncertainties. This method estimates the probability distribution of line flows based on the system generation margin and injection shift factor. This estimate is then used to construct pre-defined and post-zonal reserve requirements. Case studies demonstrate that the proposed method efficiently schedules energy and reserves to balance energy and manage deliverability with wind power forecast uncertainty.We also discuss operational implications of the proposed method.

17 WIND ENERGY↗

NASA NTRS1964

The probability density function for phase- difference estimates obtained from the envelopes of the sum and difference of two sine waves.

Probability density function of phase difference magnitude, using estimator having gain matched amplifiers

PHASE DEVIATION↗

NASA NTRS1989

Probabilities and statistics for backscatter estimates obtained by a scatterometer with applications to new scatterometer design data

The values of the Normalized Radar Backscattering Cross Section (NRCS), sigma (o), obtained by a scatterometer are random variables whose variance is a known function of the expected value. The probability density function can be obtained from the normal distribution. Models for the expected value obtain it as a function of the properties of the waves on the ocean and the winds that generated the waves. Point estimates of the expected value were found from various statistics given the parameters that define the probability density function for each value. Random intervals were derived with a preassigned probability of containing that value. A statistical test to determine whether or not successive values of sigma (o) are truly independent was derived. The maximum likelihood estimates for wind speed and direction were found, given a model for backscatter as a function of the properties of the waves on the ocean. These estimates are biased as a result of the terms in the equation that involve natural logarithms, and calculations of the point estimates of the maximum likelihood values are used to show that the contributions of the logarithmic terms are negligible and that the terms can be omitted.

Pierson, Willard J., Jr.↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

reinforcement learning↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗

NASA NTRSDate not supplied

Discovery and Analysis of Rare High-Impact Failure Modes using Adversarial RL-Informed Sampling

Adaptive learning agents have tremendous potential to handle critical tasks currently performed by humans. Unfortunately, due to their complexity, it can be difficult to verify that these learning agents do not have critical failure modes. Standard verification and validation methods often do not apply directly to learning agents and Monte Carlo methods have difficulty covering even a small fraction of the state space, especially in multiagent systems or over long time horizons. To overcome this difficulty, we demonstrate an adaptive stress-testing method based on reinforcement learning of correlations that raise the probability of failure. This approach has three key properties: (1) it is able to find rare failure modes with far greater sample efficiency than Monte Carlo methods, (2) it can estimate the true probability of a failure mode despite the inherent bias in the learning method, and (3) it is capable of learning and resampling compact representations of multimodal failure spaces. These properties are important in practice as we need to find disparate failure modes while accounting for their actual relevance. This is a significant advantage over traditional adaptive stress testing methods that give abstract likelihoods of particular failure instances, but cannot estimate the probability of a broader failure mode. We test our algorithm on a simple problem from the aviation domain where an autonomous aircraft lands in gusty wind conditions. The results suggest that we can find failure modes with far fewer samples than the Monte Carlo approach and simultaneously estimate the probability of failure.

Validation↗

NASA NTRS2010

Automated Detection of Clouds in Satellite Imagery

Many different approaches have been used to automatically detect clouds in satellite imagery. Most approaches are deterministic and provide a binary cloud - no cloud product used in a variety of applications. Some of these applications require the identification of cloudy pixels for cloud parameter retrieval, while others require only an ability to mask out clouds for the retrieval of surface or atmospheric parameters in the absence of clouds. A few approaches estimate a probability of the presence of a cloud at each point in an image. These probabilities allow a user to select cloud information based on the tolerance of the application to uncertainty in the estimate. Many automated cloud detection techniques develop sophisticated tests using a combination of visible and infrared channels to determine the presence of clouds in both day and night imagery. Visible channels are quite effective in detecting clouds during the day, as long as test thresholds properly account for variations in surface features and atmospheric scattering. Cloud detection at night is more challenging, since only courser resolution infrared measurements are available. A few schemes use just two infrared channels for day and night cloud detection. The most influential factor in the success of a particular technique is the determination of the thresholds for each cloud test. The techniques which perform the best usually have thresholds that are varied based on the geographic region, time of year, time of day and solar angle.

Jedlovec, Gary↗

NASA NTRS2016

Pitfalls and Precautions When Using Predicted Failure Data for Quantitative Analysis of Safety Risk for Human Rated Launch Vehicles

Launch vehicle reliability analysis is largely dependent upon using predicted failure rates from data sources such as MIL-HDBK-217F. Reliability prediction methodologies based on component data do not take into account risks attributable to manufacturing, assembly, and process controls. These sources often dominate component level reliability or risk of failure probability. While consequences of failure is often understood in assessing risk, using predicted values in a risk model to estimate the probability of occurrence will likely underestimate the risk. Managers and decision makers often use the probability of occurrence in determining whether to accept the risk or require a design modification. Due to the absence of system level test and operational data inherent in aerospace applications, the actual risk threshold for acceptance may not be appropriately characterized for decision making purposes. This paper will establish a method and approach to identify the pitfalls and precautions of accepting risk based solely upon predicted failure data. This approach will provide a set of guidelines that may be useful to arrive at a more realistic quantification of risk prior to acceptance by a program.

Hatfield, Glen S.↗