Modern AI and advanced sensing technologies have been transforming our ability to monitor the Earth and explore the Universe. By analysing and interpreting data (primarily in the form of imagery) captured by remote sensing devices (like multi/hyper‐spectral imaging or radar/lidar sensors) on satellites, aircrafts or UAVs and astronomical telescopes that operate either on ground or in orbit, valuable insights can be gained into the events on the Earth and the phenomena in the Universe.

Recent years have witnessed rapid advances in remote sensing technologies, resulting in an explosive growth of Earth observation data for probing the entire Earth at daily or even finer granularity. On the other hand, many new astronomical telescopes with enhanced sensing capabilities, like the recently launched James Webb Space Telescope, have been put into operation, generating massive data about the never explored aspects of the Universe. Nowadays, thanks to the boom of modern AI techniques, particularly deep learning, armed by an unprecedented growth in supercomputing power, such space data can be transformed into valuable scientific discoveries and actionable insights which may benefit various fields, such as astronomy, transportation, agriculture, and environment. However, the rapidly increasing complexity and requirements of newly emerging applications in different fields are posing greater challenges to existing AI techniques, leading to the surging needs of technology advancement.

This special session aims to bring together researchers from academia, governments and industries to review past achievements, disseminate latest studies, and explore future directions pertaining to innovating and applying modern AI techniques, particularly deep learning, to analyse space data. Authors are invited to submit original and unpublished works with topics including but not limited to:

• Deep vision for observing the Earth

  • Remote sensing data collection and curation, with data captured by various types of active (e.g., radar and lidar) and passive (e.g., optical) sensors on satellites, aircrafts, UAVs, etc.

  • Deep vision techniques for remote sensing data processing analysis and interpretation, including but not limited to:

    • Image denoising, restoration, and super‐resolution

    • Image registration, segmentation, classification and retrieval

    • Object/event detection, recognition, and tracking

    • Change detection

    • Feature engineering (e.g., selection and extraction) and representation learning

    • Data fusion and compression

    • Advanced machine learning techniques (e.g., transfer, federated, self‐supervised, semi‐supervised, few‐shot, and adversarial learning)

    • Physics‐informed neural networks

    • Onboard machine learning, deep learning, and computer vision

    • Edge AI platforms, frameworks, and techniques

    • Security and privacy

  • Earth observation applications including but not limited to transportation, urban design, agriculture, energy, environment, and management of resources and emergency

• Deep vision for probing other planets such as the Moon and the Mars

• Deep vision for exploring the Universe

  • Astronomical data collection and curation, with data captured by various telescopes that operate either on land or in orbit

  • Deep vision techniques for astronomical data processing, analysis and interpretation

    • Image denoising, restoration, and super‐resolution

    • Image segmentation, classification and retrieval

    • Object detection and recognition

    • Unknown (“anomaly”) detection

    • Feature engineering (e.g., selection and extraction) and representation learning

    • Advanced machine learning techniques (e.g., transfer, federated, self‐supervised, semi‐supervised, few‐shot, and adversarial learning)

    • Physics‐informed neural networks

    • Onboard machine learning, deep learning, and computer vision

    • Edge AI platforms, frameworks, and techniques

  • Universe exploration applications including but not limited to gravitational lens detection, photo-z estimation, star‐formation history estimation, etc.

• Deep vision driven intelligent decision‐making in space

  • Swarm intelligence for satellite constellation

  • Onboard event‐driven decision‐making in space

  • Collective intelligence for mission‐critical applications

• Responsible AI in space

Department of Computing Technologies, Swinburne University of Technology, Australia

Email: kqin@swin.edu.au

Yuan-Sen Ting

School of Astronomy & Astrophysics, Australian National University, Australia

Centre of Studies in Resources Engineering, Indian Institute of Technology Bombay, India