Browsing by Author "Etsebeth, Verlon"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Anomaly Detection With Machine Learning In Astronomical Images
    (University of the Western Cape, 2020) Etsebeth, Verlon; Lochner, Michelle
    Observations that push the boundaries have historically fuelled scientific breakthroughs, and these observations frequently involve phenomena that were previously unseen and unidentified. Data sets have increased in size and quality as modern technology advances at a record pace. Finding these elusive phenomena within these large data sets becomes a tougher challenge with each advancement made. Fortunately, machine learning techniques have proven to be extremely valuable in detecting outliers within data sets. Astronomaly is a framework that utilises machine learning techniques for anomaly detection in astronomy and incorporates active learning to provide target specific results. It is used here to evaluate whether machine learning techniques are suitable to detect anomalies within the optical astronomical data obtained from the Dark Energy Camera Legacy Survey. Using the machine learning algorithm isolation forest, Astronomaly is applied on subsets of the Dark Energy Camera Legacy Survey (DECaLS) data set. The pre-processing stage of Astronomaly had to be significantly extended to handle real survey data from DECaLS, with the changes made resulting in up to 10% more sources having their features extracted successfully. For the top 500 sources returned, 292 were ordinary sources, 86 artefacts and masked sources and 122 were interesting anomalous sources. A supplementary machine learning algorithm known as active learning enhances the identification probability of outliers in data sets by making it easier to identify target specific sources. The addition of active learning further increases the amount of interesting sources returned by almost 40%, with 273 ordinary sources, 56 artefacts and 171 interesting anomalous sources returned. Among the anomalies discovered are some merger events that have been successfully identified in known catalogues and several candidate merger events that have not yet been identified in the literature. The results indicate that machine learning, in combination with active learning, can be effective in detecting anomalies in actual data sets. The extensions integrated into Astronomaly pave the way for its application on future surveys like the Vera C. Rubin Observatory Legacy Survey of Space and Time.
  • Thumbnail Image
    Item
    Enabling scientific discovery in astronomical data with machine learning
    (University of the Western Cape, 2025) Etsebeth, Verlon
    The history of astronomy is defined by observational milestones that have profoundly transformed the understanding of the universe. Galileo’s pioneering use of the telescope allowed for detailed observations of celestial objects, such as the moons of Jupiter, providing empirical support for the then controversial heliocentric model (Galilei, 1610). Later advancements, including the development of space-based observatories like the Hubble Space Telescope (HST, Neal, 1990) and Karl Jansky’s groundbreaking discovery of radio waves from the Milky Way (Jansky, 1933), laid the foundation for modern astronomy. Astronomy has always been a data-driven science, but recent technological advances have brought about unprecedented volumes of data. Large-scale surveys and modern telescopes, such as the Sloan Digital Sky Survey (SDSS, York et al., 2000) and the Dark Energy Camera Legacy Survey (DECaLS, Dey et al., 2019) already produced terabytes of data. Future facilities will produce an even greater flow of data. The Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST, Ivezi´c et al., 2019) is projected to capture approximately 20 TB per night. Similarly, the Square Kilometre Array (SKA, Dewdney et al., 2009) is expected to generate up to 700 PB of data annually. In addition, Euclid (Scaramella et al., 2022) has begun delivering data and is expected to contribute significantly to the wealth of astronomical data and aims to map the geometry of the dark Universe with unprecedented accuracy (Tutusaus et al., 2023).