Artificial Intelligence for Astrobiology Investigations (AI2): An Open-Source Graphical User Interface

A growing number of studies in astrobiological research have utilized and shown the potential in applied machine learning. However, the number of these studies are still quite limited. Furthermore, educators, students, and researchers often do not have the time and/or resources for developing machine learning knowledge and skills. To facilitate the use of applied machine learning for astrobiology, we developed an open-source and freely available web-based graphical user interface (GUI) for teaching and developing machine learning models called Artificial Intelligence for Astrobiology Investigations (AI2). Our project enables educators, students, and researchers to make use of explainable machine learning models most amenable to tabular (i.e. .csv files) astrobiology datasets. The application is an interactive tool and serves as an entry point for educators, students, and researchers who are novices in machine learning. By providing an easy to follow and standardized machine learning workflow, the GUI highlights how certain machine learning approaches work, and how to reliably utilize machine learning Furthermore, the application can serve as a means of rapid prototyping of machine learning models, with or without the need for technical expertise, thus freeing up time for researchers to investigate and explore their data. Accordingly, the AI2 project aims to serve as a stepping stone towards more advanced implementation of applied machine learning by building the foundation and intuition necessary for technical expertise.

Published in Frontiers in Astronomy and Space Sciences