Colin Jacobs
Papers
1
Total Citations
130
H-Index
1
About
Colin Jacobs is a leading figure in the application of machine learning to astrophysics, with a primary focus on the automated detection of strong gravitational lenses. His most influential work, "Finding strong lenses in CFHTLS using convolutional neural networks" (2017, 130 citations), pioneered the use of convolutional neural networks (CNNs) for identifying these rare, gravitationally distorted systems in wide-field survey data. By training an ensemble of CNNs on Canada-France-Hawaii Telescope Legacy Survey (CFHTLS) imaging, Jacobs demonstrated that deep learning could dramatically accelerate the discovery of strong lenses—objects critical for mapping dark matter and measuring the expansion of the Universe. This breakthrough has reshaped how astronomers approach large-scale surveys, enabling the efficient mining of vast datasets that would be impractical to inspect manually. Jacobs’ work has become a cornerstone for subsequent lens-finding pipelines in next-generation surveys like Euclid and LSST, cementing his reputation as a key innovator at the intersection of astrophysics and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Finding strong lenses in CFHTLS using convolutional neural networks130 citations · 2017