Leila Character

I am a geospatial scientist focused on solving hard, real-world environmental problems using remote sensing and machine learning. I have several projects focused on archaeological problem-solving but am also interested in addressing broader environmental questions. My work seeks to develop methodologies that enable the use of huge amounts of remotely sensed data to address environmental problems and draw conclusions that otherwise wouldn’t be possible: either because manual imagery analysis is far too time-consuming or because combining different types or layers of remotely sensed data and then processing using machine learning can produce new information, and entirely new GIS layers, that would be impossible to calculate or derive using just the human eye. These machine learning approaches enable insights that haven’t been possible in the past. Overall, my research is focused on three areas: machine learning model generalizability and methodological transferability, imagery preprocessing and data annotation, and data collection (which often includes lots of interesting fieldwork all over the world!).

Projects include sidescan sonar and deep learning to find aircraft that crashed underwater during World War II and may contain the remains of missing-in-action service members; lidar and machine learning to find cave entrances in an ancient Maya area of Belize that may be of interest to archaeologists and geologists; and hyperspectral imagery and machine learning to detect an early stage of beetle infestation in a tree species.

I have a bachelor’s degree in Geology with a minor in archaeology. I completed a master’s degree in Geography focused on geoarchaeology and soil science at the University of Texas at Austin (UT Austin). I received my PhD in Geography from UT Austin in 2022. I also have professional experience as a geologist, environmental scientist, and at an artificial intelligence start-up.

I also love rock climbing, being super active in general, my dogs, fieldwork, and exploring with my family.