The sectors of Artificial Intelligence and Machine Learning are reshaping the frontiers of space science and exoplanetary exploration. These sectors are rapidly advancing to support the understanding of quantification of metrics to analyse multidimensional data, design mission architecture, and improve the quality with the help of SIot. This chapter discusses the intersection of AI/ML methods with astrophysical models to solve numerous problems, including multidimensional data acquisition, processing, and scientific inferences/interpretations. Some of the use cases include detecting planets by transit photometry and radial velocity methods, analysing atmospheres and compounds using free form spectroscopy, and planning intelligent missions by autonomous robotic spacecraft. The main focus of the chapter will be on deep learning, reinforcement learning, and generative models for the extraction of latent variable structures, inference, and real-time decision-making in complex environments. The role of machine learning in the intersection with space science not only moves forward the process of searching for habitable worlds, but also provides us with greater opportunities in representing and interpreting astrobiological events in new dimensions. We aim to establish a new branch of studying intelligent, distributed infrastructures, putting data-driven intelligent systems in alignment with physical exploration and downstream applications for astrobiology, interstellar science, and future autonomous space missions.