I am an astronomer working at Duke University trying to understand our universe and its evolution through the discovery and characterization of astrophysical transient events.
My scientific contributions are mainly in the time domain astronomy field, and include image analysis and Machine Learning, as well as statistical studies with observational data from telescopes around the world.
My main interests include Cosmology, time-domain astronomy with transient events and periodical variability, image analysis as well as applications of Machine Learning in these research areas.
Additionally I have worked with Gravitational Wave Astronomy, mostly related with Electromagnetic/Optical Counterparts to Compact Binary Merger GW events.
I enjoy creating different data visualizations, and I have experience in Feature Engineering for optimizing Machinge Learning models performance.
I have a PhD. in Astronomy, and I am able to create and use mathematical and physical models, to describe and explain data from diverse experiments.
Additionally, I have skills in software developement using Python, R as well as SQL and Fortran.
I posses the know-how on scientific data-analysis pipeline design using Object Oriented Programming, software design patterns, as well as diverse workflows for Extract-Transform-Load processes.
I am also able to optimize numeric calculus for a wide range of problems using a tool set involving many technologies, such as Spark, Dask, Tensorflow, Keras, etc.
As an advocate of good practices of software developing I use Git version control techniques for collaborating, and I am proficient in software testing as well, using techniques like unit-testing, continuous integration and property based testing.
Find my personal contact information at Duke Physics.