Lily Clough explores machine learning to predict the composition of seawater

My thesis project is Machine Learning of Ocean Worlds Laboratory Analog Seawaters to predict the composition of seawaters in ocean worlds and to detect biosignatures. Outer solar system missions are plagued by limited bandwidth and short windows of communication, so efficient transmission of quality data is essential to the collection and interpretation of in-flight data.

I am developing an R library, MLMS (Machine Learning for Mass Spectrometry), that provides functionality for quality checking, processing, and visualization of experimental IRMS (Isotope Ratio Mass Spectrometry) data to build machine learning datasets as well as implementation of machine learning algorithms adapted to the data. My research advisors are Dr. Bethany Theiling (NASA GSFC), Dr. Brett McKinney (Computer Science and Mathematics, TU), Dr. Jingyi Chen (Geoscience, TU).

My other research projects include machine learning for early warning and earthquake detection, mineralogy and petrology of meteorites, computational quantum chemistry using Fortran and R, and phylogenetics of astrobiologically significant extremophiles. I want to pursue a PhD in Computer Science continuing the phylogenetics research with a focus on Planetary Science and Astro/Bio-informatics, and Astrobiology.

I completed a BA in Chemistry and Mathematics as part of the Honors class of 2015 at TU and had a previous career as a STEM and math teacher. My professional goals are to be a professional planetary scientist and research the phylogenetics of astrobiologically significant extremophiles along with relevant biogeochemical and atmospheric processes to investigate the conditions of planetary accretion, early Earth, the Solar System, and other postulated planets that may have evolved life.