Los Alamos National Laboratory is seeking a motivated candidate for a postdoctoral research position in applied statistics and machine learning. You will work on programs supporting fundamental, interdisciplinary research to advance machine learning methods for analysis of data supporting current and future planetary exploration efforts. The work will begin with existing measurements from SuperCam (currently deployed on the Mars rover Perseverance). The SuperCam platform measures laser-induced breakdown spectroscopy (LIBS), time-resolved Raman spectroscopy, time-resolved luminescence spectroscopy, visible and near infrared spectroscopy, color remote micro-imaging, and acoustic signals. The multi-modal capability of a SuperCam-like instrument highlights the requirement to develop novel data analysis tools and techniques. The elemental and molecular compositions must be self-consistent and integrated to maximize the joint information from the individual measurements. In contrast, statistical and machine learning methods commonly used in planetary science are typically designed for a single characteristic (e.g. chemistry) and can only infer other aspects (e.g. molecular structure). You will work with a team to develop the multi-modal and integrated data analysis tools and techniques required to directly measure the characteristics of interest and fully exploit these complex data sets. Existing analysis techniques such as random forests and neural networks have been successful in single-modality analysis, but extending to multi-modal data will require significant effort. We also plan to explore domain adaptation and transfer learning methods, as new data will be collected under different environments (e.g., Martian, lunar, and Venus), and methods that are able to utilize distinct but related data sets will be beneficial.