and satellite communication; earth Observation; machine learning; modeling; Semantic communication; And satellite communication; Channel conditions; Earth observation systems; Earth observations; Loss functions; Machine-learning; Modeling; Satellite communications; Task oriented machine-learning; Artificial Intelligence; Computer Networks and Communications; Signal Processing; Control and Optimization
Abstract :
[en] The integration of machine learning (ML) has significantly enhanced the capabilities of Earth Observation (EO) systems by enabling the extraction of actionable insights from complex datasets. However, the performance of data-driven EO applications is heavily influenced by the data collection and transmission processes, where limited satellite bandwidth and latency constraints can hinder the full transmission of original data to the receivers. To address this issue, adopting the concepts of Semantic Communication (SC) offers a promising solution by prioritizing the transmission of essential data semantics over raw information. Implementing SC for EO systems requires a thorough understanding of the impact of data processing and communication channel conditions on semantic loss at the processing center. This work proposes a novel data-fitting framework to empirically model the semantic loss using real-world EO datasets and domain-specific insights. The framework quantifies two primary types of semantic loss: (1) source coding loss, assessed via a data quality indicator measuring the impact of processing on raw source data, and (2) transmission loss, evaluated by comparing practical transmission performance against the Shannon limit. Semantic losses are estimated by evaluating the accuracy of EO applications using four task-oriented ML models, EfficientViT, MobileViT, ResNet50-DINO, and ResNet8-KD, on lossy image datasets under varying channel conditions and compression ratios. These results underpin a framework for efficient semantic-loss modeling in bandwidth-constrained EO scenarios, enabling more reliable and effective operations.
Disciplines :
Electrical & electronics engineering
Author, co-author :
NGUYEN, Ti Ti ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
LE, Thanh-Dung ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
HA, Vu Nguyen ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Chou, Hong-Fu ✱; University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg
Eappen, Geoffrey ✱; University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg
Tran, Duc-Dung ✱; University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg
NGUYEN, Kha Hung ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Thiruvasagam, Prabhu ✱; University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg
GARCES SOCARRAS, Luis Manuel ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
Gonzalez-Rios, Jorge L. ✱; University of Luxembourg, Interdisciplinary Centre for Security, Reliability and Trust (SnT), Luxembourg
MERLANO DUNCAN, Juan Carlos ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
CHATZINOTAS, Symeon ✱; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SigCom
✱ These authors have contributed equally to this work.
External co-authors :
no
Language :
English
Title :
A Semantic-Loss Function Modeling Framework With Task-Oriented Machine Learning Perspectives
Publication date :
2025
Event name :
2025 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN)
Event place :
Barcelona, Esp
Event date :
26-05-2025 => 29-05-2025
Main work title :
2025 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN 2025
Publisher :
Institute of Electrical and Electronics Engineers Inc.
This work was funded by the Luxembourg National Research Fund (FNR), with granted SENTRY project corresponding to grant reference C23/IS/18073708/SENTRY.
I. Leyva-Mayorga et al., "Satellite edge computing for real-time and very-high resolution earth observation, " IEEE Trans. Commun., vol. 71, no. 10, pp. 6180-6194, 2023.
A. Singh and K. Gaurav, "Deep learning and data fusion to estimate surface soil moisture from multi-sensor satellite images, " Nature Scientific Reports, vol. 13, no. 1, p. 2251, 2023.
G. Fontanesi et al., "Artificial intelligence for satellite communication and non-terrestrial networks: A survey, " arXiv preprint arXiv: 2304. 13008, 2023.
M. Affek and J. Szymánski, "A survey on the datasets and algorithms for satellite data applications, " IEEE J. Sel. Topics Applied Earth Obser. Remote Sensing, 2024.
H.-f. Chou et al., "Edge ai empowered physical layer security for 6g ntn: Potential threats and future opportunities, " arXiv preprint arXiv: 2401. 01005, 2023.
S. Mahboob and L. Liu, "Revolutionizing future connectivity: A contemporary survey on AI-empowered satellite-based non-terrestrial networks in 6G, " IEEE Commun. Surveys & Tuts., 2024.
W. Yang et al., "Semantic communications for future internet: Fundamentals, applications, and challenges, " IEEE Commun. Surveys & Tuts., vol. 25, no. 1, pp. 213-250, 2022.
H.-f. Chou et al., "On-air deep learning integrated semantic inference models for enhanced earth observation satellite networks, " arXiv preprint arXiv: 2409. 15246, 2024.
Z. Qin, X. Tao, J. Lu, W. Tong, and G. Y. Li, "Semantic communications: Principles and challenges, " arXiv preprint arXiv: 2201. 01389, 2021.
H.-f. Chou et al., "Cognitive semantic augmentation leo satellite networks for earth observation, " arXiv preprint arXiv: 2410. 21916, 2024.
X. Liu et al., "Efficientvit: Memory efficient vision transformer with cascaded group attention, " Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 14 420-14 430, 2023.
S. Mehta and M. Rastegari, "Separable self-attention for mobile vision transformers, " arXiv preprint arXiv: 2206. 02680, 2022.
T.-D. Le et al., "Semantic knowledge distillation for onboard satellite earth observation image classification, " arXiv preprint arXiv: 2411. 00209, 2024.
M. Goldblum et al., "Battle of the backbones: A large-scale comparison of pretrained models across comput. vision tasks, " Advances in Neural Informat. Process. Systems, vol. 36, 2024.
P. Helber, B. Bischke, A. Dengel, and D. Borth, "Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification, " IEEE J. Sel. Top. Appl. Earth. Obs. Remote Sens., vol. 12, no. 7, pp. 2217-2226, 2019.
European Telecommunications Standards Institute (ETSI), "DVB-S2 (X): Digital video broadcasting-Satellite second generation, " https: //www. etsi. org/technologies/dvb-s-s2.
V. N. Ha, T. T. Nguyen, E. Lagunas, J. C. M. Duncan, and S. Chatzinotas, "Geo payload power minimization: Joint precoding and beam hopping design, " in IEEE Global Commun. Conf. (GLOBECOM). IEEE, 2022, pp. 6445-6450.
MathWorks, "End-to-end DVB-S2 simulation with RF impairments and corrections, " https: //nl. mathworks. com/help/satcom/ug/end-to-enddvbs2-simulation-with-rf-impairments-and-corrections. html.
T. D. Le et al., "On-board satellite image classification for earth observation: A comparative study of vit models, " arXiv preprint arXiv: 2409. 03901, 2024.
T. T. Nguyen, V. N. Ha, L. B. Le, and R. Schober, "Joint data compression and computation offloading in hierarchical fog-cloud systems, " IEEE Trans. Wireless Commun., vol. 19, no. 1, pp. 293-309, 2019.
