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).

Optimal Linear Precoding Under Realistic Satellite Communications Scenarios

In this paper, optimal linear precoding for the multibeam geostationary earth orbit (GEO) satellite with the multi-user (MU) multiple-input-multiple-output (MIMO) downlink scenario is addressed. Multiple-user interference is one of the major issues faced by the satellites serving the multiple users operating at the common time-frequency resource block in the downlink channel. To mitigate this issue, the optimal linear precoders are implemented at the gateways (GWs). The precoding computation is performed by utilizing the channel state information obtained at user terminals (UTs). The optimal linear precoders are derived considering beamformer update and power control with an iterative per-antenna power optimization algorithm with a limited required number of iterations. The efficacy of the proposed algorithm is validated using the In-Lab experiment for 16X16 precoding with multi-beam satellite for transmitting and receiving the precoded data with digital video broadcasting satellite-second generation extension (DVB- S2X) standard for the GW and the UTs. The software defined radio platforms are employed for emulating the GWs, UTs, and satellite links. The validation is supported by comparing the proposed optimal linear precoder with full frequency reuse (FFR), and minimum mean square error (MMSE) schemes. The experimental results demonstrate that with the optimal linear precoders it is possible to successfully cancel the inter-user interference in the simulated satellite FFR link. Thus, optimal linear precoding brings gains in terms of enhanced signal-to-noise-and-interference ratio, and increased system throughput and spectral efficiency.

User-Centric Beam Selection and Precoding Design for Coordinated Multiple-Satellite Systems

This paper introduces a joint optimization framework for user-centric beam selection and linear precoding (LP) design in a coordinated multiple-satellite (CoMSat) system, employing a Digital-Fourier-Transform-based (DFT) beamforming (BF) technique. Regarding serving users at their target SINRs and minimizing the total transmit power, the scheme aims to efficiently determine satellites for users to associate with and activate the best cluster of beams together with optimizing LP for every satellite-to-user transmission. These technical objectives are first framed as a complex mixed-integer programming (MIP) challenge. To tackle this, we reformulate it into a joint cluster association and LP design problem. Then, by theoretically analyzing the duality relationship between downlink and uplink transmissions, we develop an efficient iterative method to identify the optimal solution. Additionally, a simpler duality approach for rapid beam selection and LP design is presented for comparison purposes. Simulation results underscore the effectiveness of our proposed schemes across various settings.

Performance Evaluation of Neuromorphic Hardware for Onboard Satellite Communication Applications

Spiking neural networks (SNNs) implemented on neuromorphic processors (NPs) can enhance the energy efficiency of deployments of artificial intelligence (AI) for specific workloads. As such, NP represents an interesting opportunity for implementing AI tasks on board power-limited satellite communication spacecraft. In this article, we disseminate the findings of a recently completed study which targeted the comparison in terms of performance and power-consumption of different satellite communication use cases implemented on standard AI accelerators and on NPs. In particular, the article describes three prominent use cases, namely payload resource optimization, onboard interference detection and classification, and dynamic receive beamforming; and compare the performance of conventional convolutional neural networks (CNNs) implemented on Xilinx's VCK5000 Versal development card and SNNs on Intel's neuromorphic chip Loihi 2.

Satellite Swarms for Narrow Beamwidth Applications

Satellite swarms have recently gained attention in the space industry due to their ability to provide extremely narrow beamwidths at a lower cost than single satellite systems. This paper proposes a concept for a satellite swarm using a distributed subarray configuration based on a 2D normal probability distribution. The swarm comprises multiple small satellites acting as subarrays of a big aperture array limited by a radius of 20000 wavelengths working at a central frequency of 19 GHz. The main advantage of this approach is that the distributed subarrays can provide extremely directive beams and beamforming capabilities that are not possible using a conventional antenna and satellite design. The proposed swarm concept is analyzed, and the simulation results show that the radiation pattern achieves a beamwidth as narrow as 0.0015-degrees with a maximum side lobe level of 18.8 dB and a grating lobe level of 14.8 dB. This concept can be used for high data rates applications or emergency systems.

Energy-Efficient On-Board Radio Resource Management for Satellite Communications via Neuromorphic Computing

The latest satellite communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization-based solutions have shown to be computationally tedious and to lack flexibility, machine learning (ML)-based methods have emerged as promising alternatives. We investigate the application of energy-efficient brain-inspired ML models for on-board radio resource management. Apart from software simulation, we report extensive experimental results leveraging the recently released Intel Loihi 2 chip. To benchmark the performance of the proposed model, we implement conventional convolutional neural networks (CNN) on a Xilinx Versal VCK5000, and provide a detailed comparison of accuracy, precision, recall, and energy efficiency for different traffic demands. Most notably, for relevant workloads, spiking neural networks (SNNs) implemented on Loihi 2 yield higher accuracy, while reducing power consumption by more than 100$\times$ as compared to the CNN-based reference platform. Our findings point to the significant potential of neuromorphic computing and SNNs in supporting on-board SatCom operations, paving the way for enhanced efficiency and sustainability in future SatCom systems.

Harnessing the Power of Swarm Satellite Networks with Wideband Distributed Beamforming

The space communications industry is challenged to develop a technology that can deliver broadband services to user terminals equipped with miniature antennas, such as handheld devices. One potential solution to establish links with ground users is the deployment of massive antennas in one single spacecraft. However, this is not cost-effective. Aligning with recent \emph{NewSpace} activities directed toward miniaturization, mass production, and a significant reduction in spacecraft launch costs, an alternative could be distributed beamforming from multiple satellites. In this context, we propose a distributed beamforming modeling technique for wideband signals. We also consider the statistical behavior of the relative geometry of the swarm nodes. The paper assesses the proposed technique via computer simulations, providing interesting results on the beamforming gains in terms of power and the security of the communication against potential eavesdroppers at non-intended pointing angles. This approach paves the way for further exploration of wideband distributed beamforming from satellite swarms in several future communication applications.

Joint Linear Precoding and DFT Beamforming Design for Massive MIMO Satellite Communication

This paper jointly designs linear precoding (LP) and codebook-based beamforming implemented in a satellite with massive multiple-input multiple-output (mMIMO) antenna technology. The codebook of beamforming weights is built using the columns of the discrete Fourier transform (DFT) matrix, and the resulting joint design maximizes the achievable throughput under limited transmission power. The corresponding optimization problem is first formulated as a mixed integer non-linear programming (MINP). To adequately address this challenging problem, an efficient LP and DFT-based beamforming algorithm are developed by utilizing several optimization tools, such as the weighted minimum mean square error transformation, duality method, and Hungarian algorithm. In addition, a greedy algorithm is proposed for benchmarking. A complexity analysis of these solutions is provided along with a comprehensive set of Monte Carlo simulations demonstrating the efficiency of our proposed algorithms.