Michael J. Turmon

Statistical Pattern Recognition for Labeling Solar Active Regions: Application to SOHO/MDI Imagery

This paper presents a new application of statistical methods for identifying the various surface structures on the Sun that may contribute to observed changes in total and spectral solar irradiance. These structures are divided for our purposes into three types: quiet Sun, faculae, and sunspots (umbra and penumbra). Each region type is characterized by the observed data present at pixels of that type. Statistical models characterizing these observables are found from expert identification of a sample set of regions or unsupervised clustering. Information about the spatial continuity of regions is incorporated into the model via a prior distribution on the label image; the contribution of the prior can be interpreted as a regularizing term. Once the parameters defining the models are fixed, the inference procedure becomes to maximize the probability of an image labeling given the observed data. This allows objective and automated classification of a large set of images. We describe the application of these procedures to computing labelings from synchronized full-disk high-resolution magnetic-field and light-intensity maps from the Michelson Doppler Imager experiment on the Solar and Heliospheric Observatory.

Towards learned traversability for robot navigation: From underfoot to the far field

Autonomous off-road navigation of robotic ground vehicles has important applications on Earth and in space exploration. Progress in this domain has been retarded by the limited lookahead range of three-dimensional (3D) sensors and by the difficulty of heuristically programming systems to understand the traversability of the wide variety of terrain they can encounter. Enabling robots to learn from experience may alleviate both of these problems. We define two paradigms for this, learning from 3D geometry and learning from proprioception, and describe initial instantiations of them as developed under DARPA and NASA programs. Field test results show promise for learning traversability of vegetated terrain and learning to extend the lookahead range of the vision system.

Tests and tolerances for high-performance software-implemehted fault detection

We describe and test a software approach to fault detection in common numerical algorithms. Such result checking or algorithm-based fault tolerance (ABFT) methods may be used, for example, to overcome single-event upsets in computational hardware or to detect errors in complex, high-efficiency implementations of the algorithms. Following earlier work, we use checksum methods to validate results returned by a numerical subroutine operating subject to unpredictable errors in data. We consider common matrix and Fourier algorithms which return results satisfying a necessary condition having a linear form; the checksum tests compliance with this condition. We discuss the theory and practice of setting numerical tolerances to separate errors caused by a fault from those inherent in finite-precision floating-point calculations. We concentrate on comprehensively defining and evaluating tests having various accuracy/computational burden tradeoffs, and we emphasize average-case algorithm behavior rather than using worst-case upper, bounds on error.

Software-implemented fault detection for high-performance space applications

We describe and test a software approach to overcoming radiation-induced errors in spaceborne applications running on commercial off-the-shelf components. The approach uses checksum methods to validate results returned by a numerical subroutine operating subject to unpredictable errors in data. We can treat subroutines that return results satisfying a necessary condition having a linear form; the checksum tests compliance with this condition. We discuss the theory and practice of setting numerical tolerances to separate errors caused by a fault from those inherent infinite-precision numerical calculations. We test both the general effectiveness of the linear fault tolerant schemes we propose, and the correct behavior of our parallel implementation of them.

Learning long-range terrain classification for autonomous navigation

This paper describes a method for learning the terrain classification of long-range appearance data from short- range, stereo-based geometry, along with a map representation for utilizing this data to improve autonomous off-road navigation. The continuous, online learning method allows the system to constantly adapt to changing terrain and environmental conditions, while the polar-perspective map representation allows the system to effectively plan with stereo data at long ranges. Various evaluations of the long-range classification and improvements in system performance are described, including results from an independent third-party testing team.

Feature selection strategies for classifying high dimensional astronomical data sets

The amount of collected data in many scientific fields is increasing, all of them requiring a common task: extract knowledge from massive, multi parametric data sets, as rapidly and efficiently possible. This is especially true in astronomy where synoptic sky surveys are enabling new research frontiers in the time domain astronomy and posing several new object classification challenges in multi dimensional spaces; given the high number of parameters available for each object, feature selection is quickly becoming a crucial task in analyzing astronomical data sets. Using data sets extracted from the ongoing Catalina Real-Time Transient Surveys (CRTS) and the Kepler Mission we illustrate a variety of feature selection strategies used to identify the subsets that give the most information and the results achieved applying these techniques to three major astronomical problems.

Flashes in a star stream: Automated classification of astronomical transient events

An automated, rapid classification of transient events detected in the modern synoptic sky surveys is essential for their scientific utility and effective follow-up using scarce resources. This presents some unusual challenges: the data are sparse, heterogeneous and incomplete; evolving in time; and most of the relevant information comes not from the data stream itself, but from a variety of archival data and contextual information (spatial, temporal, and multi-wavelength). We are exploring a variety of novel techniques, mostly Bayesian, to respond to these challenges, using the ongoing CRTS sky survey as a testbed. The current surveys are already overwhelming our ability to effectively follow all of the potentially interesting events, and these challenges will grow by orders of magnitude over the next decade as the more ambitious sky surveys get under way. While we focus on an application in a specific domain (astrophysics), these challenges are more broadly relevant for event or anomaly detection and knowledge discovery in massive data streams.

Towards Real‐time Classification of Astronomical Transients

Exploration of time domain is now a vibrant area of research in astronomy, driven by the advent of digital synoptic sky surveys. While panoramic surveys can detect variable or transient events, typically some follow-up observations are needed; for short-lived phenomena, a rapid response is essential. Ability to automatically classify and prioritize transient events for follow-up studies becomes critical as the data rates increase. We have been developing such methods using the data streams from the Palomar-Quest survey, the Catalina Sky Survey and others, using the VOEventNet framework. The goal is to automatically classify transient events, using the new measurements, combined with archival data (previous and multi-wavelength measurements), and contextual information (e.g., Galactic or ecliptic latitude, presence of a possible host galaxy nearby, etc.); and to iterate them dynamically as the follow-up data come in (e.g., light curves or colors). We have been investigating Bayesian methodologies for classification, as well as discriminated follow-up to optimize the use of available resources, including Naive Bayesian approach, and the non-parametric Gaussian process regression. We will also be deploying variants of the traditional machine learning techniques such as Neural Nets and Support Vector Machines on datasets of reliably classified transients as they build up.

Real-time data mining of massive data streams from synoptic sky surveys

The nature of scientific and technological data collection is evolving rapidly: data volumes and rates grow exponentially, with increasing complexity and information content, and there has been a transition from static data sets to data streams that must be analyzed in real time.?Interesting or anomalous phenomena must be quickly characterized and followed up with additional measurements via optimal deployment of limited assets.?Modern astronomy presents a variety of such phenomena in the form of transient events in digital synoptic sky surveys, including cosmic explosions (supernovae, gamma ray bursts), relativistic phenomena (black hole formation, jets), potentially hazardous asteroids, etc. We have been developing a set of machine learning tools to detect, classify and plan a response to transient events for astronomy applications, using the Catalina Real-time Transient Survey (CRTS) as a scientific and methodological testbed. The ability to respond rapidly to the potentially most interesting events is a key bottleneck that limits the scientific returns from the current and anticipated synoptic sky surveys.?Similar challenge arises in other contexts, from environmental monitoring using sensor networks to autonomous spacecraft systems.?Given the exponential growth of data rates, and the time-critical response, we need a fully automated and robust approach.?We describe the results obtained to date, and the possible future developments. Advances in the automated classification of transient events in synoptic sky surveys.Innovative methods for the analysis of irregularly sampled, heterogeneous time series.Novel approach to the machine-assisted discovery using a symbolic regression.Approaches to an automated decision making based on the automated classification.

Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys

The nature of scientific and technological data collection is evolving rapidly: data volumes and rates grow exponentially, with increasing complexity and information content, and there has been a transition from static data sets to data streams that must be analyzed in real time. Interesting or anomalous phenomena must be quickly characterized and followed up with additional measurements via optimal deployment of limited assets. Modern astronomy presents a variety of such phenomena in the form of transient events in digital synoptic sky surveys, including cosmic explosions (supernovae, gamma ray bursts), relativistic phenomena (black hole formation, jets), potentially hazardous asteroids, etc. We have been developing a set of machine learning tools to detect, classify and plan a response to transient events for astronomy applications, using the Catalina Real-time Transient Survey (CRTS) as a scientific and methodological testbed. The ability to respond rapidly to the potentially most interesting events is a key bottleneck that limits the scientific returns from the current and anticipated synoptic sky surveys. Similar challenge arise in other contexts, from environmental monitoring using sensor networks to autonomous spacecraft systems. Given the exponential growth of data rates, and the time-critical response, we need a fully automated and robust approach. We describe the results obtained to date, and the possible future developments.