AI-ML

Efficiency: AI can automate numerous satellite operations, reducing the need for human intervention and potential human error.

• • Example: Have you ever gotten irritated over a slow internet connection? Novel AI Reinforcement Learning algorithms are being developed in order to improve just that! They work by predicting demand as the satellite flies over an area, taking into account factors like whether that area is a city or a rural environment, or the time of day and whether people are sleeping below. Based on those predictions they allocate the available spectrum (the frequencies in which a signal is transmitted down to earth) more optimally [1], resulting in much faster communication.

Real-time Decision Making: Satellites equipped with AI can make on-the-fly decisions.

• • Examples: They can adjust their imaging parameters based on cloud cover or other atmospheric conditions. They can use Cloud Detection models that have been tested in space-representative hardware, to adjust parameters and sensors, or even to save bandwidth and not send unusable images down to earth. Bandwidth is a precious commodity in spacecraft, because of the difficulty of sending data across such large distances quickly and with low error rates. Another example of autonomous decision making with ML models is the capability to classify images based on their usability based a classification model. Then we can use a ML compression model to reduce the data size, that varies based on what information we want to preserve. For example if we want to track forest fires we don’t care about very high resolution images in urban areas, and that saves precious time on the data transmission [2]. This can be extremely useful in situations that rely in real-time observations such as flood detection, fire detection or military applications.

Space Exploration: Rovers like NASA’s Perseverance use AI for tasks like autonomous driving and selecting scientific points of interest.

• • Example: NASA’s Perseverance Rover is dependent on AI self-driving models. The communication delay between Mars and Earth can be up to 22 minutes [3]. Given that delay, trying to drive a rover a distance of a few meters might take days. Imaging trying to drive your car, and for each input to your steering wheel (and seeing the road in front of you), you would have had to wait 22 minutes each way. Now imagine if the road was full of boulders and you would have to swerve every few meters to avoid them! So being AI-enabled [4], allows the rover to make real-time decisions, avoid obstacles, and cover more ground efficiently, maximizing the scientific return from the mission.

• Combining critical systems with capable systems. Often systems that offer high reliability (e.g. space-grade FPGAs with Real-Time Operating Systems) lack the computational capability that are available to us here on earth [1]. So the need has surfaced to combine a reliable system that handles critical operations with a capable system that meets the requirements.
• Harsh Environments: Space environments can be unpredictable. AI can adapt in real-time to situations like solar flares or unexpected satellite movements [2].
• Computational Limitations: Space hardware is optimized for durability, and not necessarily computational power. This poses challenges in running advanced AI models [3].

• Emerging Tech Hub: There is a growing tech and startup ecosystem in Greece, with a focus on cutting-edge technologies, including AI. But apart from startups, big tech companies also invest heavily in the country (Google, Amazon, Microsoft, etc.) with offices, data centers etc., solidifying the global confidence in Greece [1].
• Greece benefits from a scientifically-advanced as well as cost-effective talent pool that stands out in comparison to many other European nations.
• Given recent catastrophes, Greece has a need for near-real-time methods for fire detection, flood detection and maritime monitoring.