Charlotte Ward
Papers
1
Total Citations
158
H-Index
1
About
Charlotte Ward is a leading figure in the application of deep learning to time-domain astronomy, with her work fundamentally reshaping how massive sky surveys separate fleeting cosmic signals from mundane artifacts. Her most influential contribution is the development of *braai*, a convolutional-neural-network-based real/bogus classifier for the Zwicky Transient Facility (ZTF). Detailed in her 2019 paper—which has amassed 158 citations—this system efficiently automates the critical task of distinguishing genuine astrophysical transients, variable sources, and moving objects from instrumental noise and image artifacts. By enabling ZTF to process its torrent of nightly data with unprecedented speed and accuracy, Ward’s work has directly accelerated the discovery of supernovae, kilonovae, and other rare phenomena. Her research sits at the vital intersection of machine learning and observational astronomy, providing the algorithmic backbone that allows modern surveys to keep pace with their own data deluge. For students and researchers, Ward exemplifies how deep learning is not merely an auxiliary tool but a transformative force in the era of big-data astrophysics.
Research Focus
Key Achievements
Top Papers
- 1Real-bogus classification for the Zwicky Transient Facility using deep learning158 citations · 2019