Light Curve Classification with DistClassiPy: a new distance-based classifier
arxiv(2024)
摘要
The rise of synoptic sky surveys has ushered in an era of big data in
time-domain astronomy, making data science and machine learning essential tools
for studying celestial objects. Tree-based (e.g. Random Forests) and deep
learning models represent the current standard in the field. We explore the use
of different distance metrics to aid in the classification of objects. For
this, we developed a new distance metric based classifier called DistClassiPy.
The direct use of distance metrics is an approach that has not been explored in
time-domain astronomy, but distance-based methods can aid in increasing the
interpretability of the classification result and decrease the computational
costs. In particular, we classify light curves of variable stars by comparing
the distances between objects of different classes. Using 18 distance metrics
applied to a catalog of 6,000 variable stars in 10 classes, we demonstrate
classification and dimensionality reduction. We show that this classifier meets
state-of-the-art performance but has lower computational requirements and
improved interpretability. We have made DistClassiPy open-source and accessible
at https://pypi.org/project/distclassipy/ with the goal of broadening its
applications to other classification scenarios within and beyond astronomy.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要