Free-Space Optical Channel Turbulence Prediction: A Machine Learning Approach

Channel turbulence presents a formidable obstacle for free-space optical (FSO) communication. Anticipation of turbulence levels is highly important for mitigating disruptions. We study the application of machine learning (ML) to FSO data streams to rapidly predict channel turbulence levels with no additional sensing hardware. An optical bit stream was transmitted through a controlled channel in the lab under six distinct turbulence levels, and the efficacy of using ML to classify turbulence levels was examined. ML-based turbulence level classification was found to be >98% accurate with multiple ML training parameters, but highly dependent upon the timescale of changes between turbulence levels.

Towards a Hybrid RF/Optical Lunar Communication System (LunarComm)

The prospect of mankind returning to the Moon has garnered a great amount of attention in recent years. Dozens of lunar missions are planned for the coming decade which will require the development of a sustainable communication infrastructure with high data rates and minimal latency. Space communication systems thus far have relied on Radio Frequency (RF) links alone, but recent developments in laser communications have demonstrated that Free Space Optical (FSO) links can achieve much higher data rates. Upon considering the respective benefits and drawbacks of RF and FSO links, we make a case for the integration of these two technologies into a hybrid RF/FSO lunar communications architecture which leverages small satellites in a Low Earth Orbit (LEO) constellation. We include a case study for this technology designed in Analytical Graphics Systems Tool Kit (STK) software. Results are presented in terms of chain access duration, propagation delay, transmission loss, Signal-to-Noise Ratio (SNR), and Bit Error Rate (BER). This architecture shows potential to revolutionize extraterrestrial communications and pave the way for highly ambitious future missions in space.