Search

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., Comment: Under revisions

Earth observation (EO) systems are essential for mapping, catastrophe monitoring, and resource management, but they have trouble processing and sending large amounts of EO data efficiently, especially for specialized applications like agriculture and real-time disaster response. This paper presents a novel framework for semantic communication in EO satellite networks, aimed at enhancing data transmission efficiency and system performance through cognitive processing techniques. The proposed system leverages Discrete Task-Oriented Joint Source-Channel Coding (DT-JSCC) and Semantic Data Augmentation (SA) integrate cognitive semantic processing with inter-satellite links, enabling efficient analysis and transmission of multispectral imagery for improved object detection, pattern recognition, and real-time decision-making. Cognitive Semantic Augmentation (CSA) is introduced to enhance a system's capability to process and transmit semantic information, improving feature prioritization, consistency, and adaptation to changing communication and application needs. The end-to-end architecture is designed for next-generation satellite networks, such as those supporting 6G, demonstrating significant improvements in fewer communication rounds and better accuracy over federated learning., Comment: 8 Pages, 5 figures, Magazine. arXiv admin note: substantial text overlap with arXiv:2409.15246

Earth Observation (EO) systems are crucial for cartography, disaster surveillance, and resource administration. Nonetheless, they encounter considerable obstacles in the processing and transmission of extensive data, especially in specialized domains such as precision agriculture and real-time disaster response. Earth observation satellites, outfitted with remote sensing technology, gather data from onboard sensors and IoT-enabled terrestrial objects, delivering important information remotely. Domain-adapted Large Language Models (LLMs) provide a solution by enabling the integration of raw and processed EO data. Through domain adaptation, LLMs improve the assimilation and analysis of many data sources, tackling the intricacies of specialized datasets in agriculture and disaster response. This data synthesis, directed by LLMs, enhances the precision and pertinence of conveyed information. This study provides a thorough examination of using semantic inference and deep learning for sophisticated EO systems. It presents an innovative architecture for semantic communication in EO satellite networks, designed to improve data transmission efficiency using semantic processing methodologies. Recent advancements in onboard processing technologies enable dependable, adaptable, and energy-efficient data management in orbit. These improvements guarantee reliable performance in adverse space circumstances using radiation-hardened and reconfigurable technology. Collectively, these advancements enable next-generation satellite missions with improved processing capabilities, crucial for operational flexibility and real-time decision-making in 6G satellite communication., Comment: 17 pages, 7 figures, Journal

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 compare the performance of traditional CNN-based, ResNet-based, and various pre-trained vision Transformer models. Our findings demonstrate that pre-trained Vision Transformer (ViT) models, particularly MobileViTV2 and EfficientViT-M2, outperform models trained from scratch in terms of accuracy and efficiency. These models achieve high performance with reduced computational requirements and exhibit greater resilience during inference under noisy conditions. While MobileViTV2 has excelled on clean validation data, EfficientViT-M2 has proved more robust when handling noise, making it the most suitable model for onboard satellite EO tasks. Our experimental results demonstrate that EfficientViT-M2 is the optimal choice for reliable and efficient RS-IC in satellite operations, achieving 98.76 % of accuracy, precision, and recall. Precisely, EfficientViT-M2 delivers the highest performance across all metrics, excels in training efficiency (1,000s) and inference time (10s), and demonstrates greater robustness (overall robustness score of 0.79). Consequently, EfficientViT-M2 consumes 63.93 % less power than MobileViTV2 (79.23 W) and 73.26 % less power than SwinTransformer (108.90 W). This highlights its significant advantage in energy efficiency.

The Artificial Intelligence Satellite Telecommunications Testbed (AISTT), part of the ESA project SPAICE, is focused on the transformation of the satellite payload by using artificial intelligence (AI) and machine learning (ML) methodologies over available commercial off-the-shelf (COTS) AI-capable chips for onboard processing. The objectives include validating artificial intelligence-driven SATCOM scenarios such as interference detection, spectrum sharing, radio resource management, decoding, and beamforming. The study highlights hardware selection and payload architecture. Preliminary results show that ML models significantly improve signal quality, spectral efficiency, and throughput compared to conventional payload. Moreover, the testbed aims to evaluate the performance and the use of AI-capable COTS chips in onboard SATCOM contexts., Comment: 6 pages, 4 figures

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.

Quantum key distribution (QKD) is a cryptographic technique that leverages principles of quantum mechanics to offer extremely high levels of data security during transmission. It is well acknowledged for its capacity to accomplish provable security. However, the existence of a gap between theoretical concepts and practical implementation has raised concerns about the trustworthiness of QKD networks. In order to mitigate this disparity, we propose the implementation of risk-aware machine learning techniques that present risk analysis for Trojan-horse attacks over the time-variant quantum channel. The trust condition presented in this study aims to evaluate the offline assessment of safety assurance by comparing the risk levels between the recommended safety borderline. This assessment is based on the risk analysis conducted. Furthermore, the proposed trustworthy QKD scenario demonstrates its numerical findings with the assistance of a state-of-the-art point-to-point QKD device, which operates over optical quantum channels spanning distances of 1m, 1km, and 30km. Based on the results from the experimental evaluation of a 30km optical connection, it can be concluded that the QKD device provided prior information to the proposed learner during the non-existence of Eve's attack. According to the optimal classifier, the defensive gate offered by our learner possesses the capability to identify any latent Eve attacks, hence effectively mitigating the risk of potential vulnerabilities. The Eve detection probability is provably bound for our trustworthy QKD scenario., Comment: 20 Pages, 14 figure, Journal

The incorporation of subarrays in Direct Radiating Arrays for satellite missions is fundamental in reducing the number of Radio Frequency chains, which correspondingly diminishes cost, power consumption, space, and mass. Despite the advantages, previous beamforming schemes incur significant losses during beam scanning, particularly when hybrid beamforming is not employed. Consequently, this paper introduces an algorithm capable of compensating for these losses by increasing the power, for this, the algorithm will activate radiating elements required to address a specific Effective Isotropic Radiated Power for a beam pattern over Earth, projected from a GeoStationary satellite. In addition to the aforementioned compensation, other beam parameters have been addressed in the algorithm, such as beamwidth and Side Lobe Levels. To achieve these objectives, we propose employing the array thinning concept through the use of genetic algorithms, which enable beam shaping with the desired characteristics and power. The full array design considers an open-ended waveguide, configured to operate in circular polarization within the Ka-band frequency range of 17.7-20.2 GHz.

The ultra-secure quantum network leverages quantum cryptography to deliver unsurpassed data transfer security. In principle, the well-known quantum key distribution (QKD) achieves unconditional security, which raises concerns about the trustworthiness of 6G wireless systems in order to mitigate the gap between practice and theory. The long-distance satellite-to-ground evolving quantum network distributes keys that are ubiquitous to the node on the ground through low-orbit satellites. As the secret key sequence is encoded into quantum states, it is sent through the atmosphere via a quantum channel. It still requires more effort in the physical layer design of deployment ranges, transmission, and security to achieve high-quality quantum communication. In this paper, we first review the quantum states and channel properties for satellite-based quantum networks and long-range quantum state transfer (QST). Moreover, we highlight some challenges, such as transmissivity statistics, estimation of channel parameters and attack resilience, quantum state transfer for satellite-based quantum networks, and wavepacket shaping techniques over atmospheric channels. We underline two research directions that consider the QST and wavepacket shaping techniques for atmospheric transmission in order to encourage further research toward the next generation of satellite-based quantum networks., Comment: 6 pages, 1 figure, conference

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., Comment: Globecom 2022

We carry out an explicit examination of the NP-hardness of a bi- objective optimization problem to minimize distance and latency of a single-vehicle route designed to serve a set of client requests. In addition to being a Hamiltonian cycle the route is to minimize the traveled distance of the vehicle as well as the total waiting time of the clients along the route., Comment: 6 pages, 1 figure