Research into 6G networks has been initiated to support a variety of critical artificial intelligence (AI) assisted applications such as autonomous driving. In such applications, AI-based decisions should be performed in a real-time manner. These decisions include resource allocation, localization, channel estimation, etc. Considering the black-box nature of existing AI-based models, it is highly challenging to understand and trust the decision-making behavior of such models. Therefore, explaining the logic behind those models through explainable AI (XAI) techniques is essential for their employment in critical applications. This manuscript proposes a novel XAI-based channel estimation (XAI-CHEST) scheme that provides detailed reasonable interpretability of the deep learning (DL) models that are employed in doubly-selective channel estimation. The aim of the proposed XAI-CHEST scheme is to identify the relevant model inputs by inducing high noise on the irrelevant ones. As a result, the behavior of the studied DL-based channel estimators can be further analyzed and evaluated based on the generated interpretations. Simulation results show that the proposed XAI-CHEST scheme provides valid interpretations of the DL-based channel estimators for different scenarios.

翻译：针对第六代（6G）网络的研究已经启动，以支持自动驾驶等各类关键人工智能辅助应用。在此类应用中，基于人工智能的决策需以实时方式执行，包括资源分配、定位、信道估计等。鉴于现有基于人工智能的模型具有"黑箱"特性，理解和信任此类模型的决策行为极具挑战性。因此，通过可解释人工智能技术阐明这些模型背后的逻辑，对于其在关键应用中的部署至关重要。本文提出一种新型基于可解释人工智能的信道估计方案，该方案为深度学习模型在双选择性信道估计中的应用提供详细合理的可解释性。所提出的XAI-CHEST方案旨在通过对不相关输入施加高噪声来识别相关模型输入，从而基于生成的解释进一步分析和评估所研究的基于深度学习的信道估计器的行为。仿真结果表明，所提出的XAI-CHEST方案在不同场景下均能为基于深度学习的信道估计器提供有效的解释。