Joint Communications and Sensing for 6G Satellite Networks: Use Cases and Challenges

Satellite Networks (SN) have traditionally been instrumental in providing two key services: communications and sensing. Communications satellites enable global connectivity, while sensing satellites facilitate applications such as Earth observation, navigation, and disaster management. However, the emergence of novel use cases and the exponential growth in service demands make the independent evolution of communication and sensing payloads increasingly impractical. Addressing this challenge requires innovative approaches to optimize satellite resources. Joint Communications and Sensing (JCAS) technology represents a transformative paradigm for SN. By integrating communication and sensing functionalities into unified hardware platforms, JCAS enhances spectral efficiency, reduces operational costs, and minimizes hardware redundancies. This paper explores the potential of JCAS in advancing the next-generation space era, highlighting its role in emerging applications. Furthermore, it identifies critical challenges, such as waveform design, Doppler effect mitigation, and multi-target detection, that remain open for future research. Through these discussions, we aim to stimulate further research into the transformative potential of JCAS in addressing the demands of 6G and beyond SN.

Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification

This study presents an innovative dynamic weighting knowledge distillation (KD) framework tailored for efficient Earth observation (EO) image classification (IC) in resource-constrained settings. Utilizing EfficientViT and MobileViT as teacher models, this framework enables lightweight student models, particularly ResNet8 and ResNet16, to surpass 90% in accuracy, precision, and recall, adhering to the stringent confidence thresholds necessary for reliable classification tasks. Unlike conventional KD methods that rely on static weight distribution, our adaptive weighting mechanism responds to each teacher model's confidence, allowing student models to prioritize more credible sources of knowledge dynamically. Remarkably, ResNet8 delivers substantial efficiency gains, achieving a 97.5% reduction in parameters, a 96.7% decrease in FLOPs, an 86.2% cut in power consumption, and a 63.5% increase in inference speed over MobileViT. This significant optimization of complexity and resource demands establishes ResNet8 as an optimal candidate for EO tasks, combining robust performance with feasibility in deployment. The confidence-based, adaptable KD approach underscores the potential of dynamic distillation strategies to yield high-performing, resource-efficient models tailored for satellite-based EO applications. The reproducible code is accessible on our GitHub repository.

On-board Satellite Image Classification for Earth Observation: A Comparative Study of Pre-Trained Vision Transformer Models

Remote sensing image classification is a critical component of Earth observation (EO) systems, traditionally dominated by convolutional neural networks (CNNs) and other deep learning techniques. However, the advent of Transformer-based architectures and large-scale pre-trained models has significantly shifted, offering enhanced performance and efficiency. This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against noisy data conditions commonly encountered during satellite-based inference. Through extensive experimentation, we compared traditional CNN-based models, ResNet-based models, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Transformer models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 excelled on clean validation data, EfficientViT-M2 proved more robust when handling noise, making it the most suitable model for onboard satellite Earth observation tasks. In conclusion, EfficientViT-M2 is the optimal choice for reliable and efficient remote sensing image classification in satellite operations, achieving 98.76\% accuracy, precision, and recall. Specifically, EfficientViT-M2 delivered the highest performance across all metrics, excelled in training efficiency (1,000s) and inference time (10s), and demonstrated greater robustness (overall robustness score at 0.79).