6G-Enabled Federated Intelligence and Transparent Framework for Aerial Scene Classification

Abstract

The evolution of sixth generation (6G) demands advanced sensing frameworks that integrate remote sensing (RS), communication, and navigation technologies while addressing challenges related to bandwidth constraints, privacy preservation, and adaptability in dynamic environments. Traditional centralized AI-based RS systems often suffer from inefficiencies, privacy vulnerabilities, and limited generalization. To overcome these limitations, we propose a 6G-compatible framework that unifies multitask deep learning, federated learning (FL), and Explainable AI (XAI) for environmental sensing using the SAT-6 aerial dataset. Our approach begins with a quality-assured preprocessing module, which leverages the structural similarity index and peak signal-to-noise ratio to enhance image fidelity under noisy conditions. A lightweight convolutional neural network is then trained for aerial scene classification, achieving 97% test accuracy while maintaining computational efficiency for edge deployment. To ensure privacy-aware model optimization, we implement FL, allowing decentralized clients to collaboratively train the model without sharing raw data. Our federated setup achieves 97.0% global accuracy within five communication rounds, demonstrating rapid convergence and minimal privacy budget consumption. In addition, we integrate shapley additive explanations-based explainability to interpret model decisions, providing visual explanations that enhance trust and accountability in AI-assisted sensing. This end-to-end framework aligns with 6G design principles by enabling intelligent, decentralized, and interpretable sensing optimized for real-time deployment in edge-aware and bandwidth-constrained RS and integrated sensing and communication environments.