Vision and Causal Learning Based Channel Estimation for THz Communications

2025-12-03

AI Summary

To address the low accuracy and poor generalizability of channel estimation in 6G terahertz (THz) massive MIMO systems under urban non-line-of-sight (NLoS) conditions, this paper proposes a novel channel estimation algorithm integrating visual perception and causal learning. We introduce variational causal dynamics (VCD) — for the first time — into THz channel modeling, explicitly capturing causal relationships between dynamic obstacles (e.g., buildings, vehicles, trees) and multipath propagation mechanisms (reflection/diffraction) using computer vision–extracted environmental features. Unlike conventional data-driven approaches, our method eliminates reliance on large-scale labeled channel datasets and achieves strong generalization to unseen urban scenarios. Experimental results demonstrate approximately 100% improvement in channel estimation accuracy over state-of-the-art traditional and AI-based methods, with significantly enhanced robustness and prediction reliability—particularly under complex NLoS conditions.

Technology Category

• Machine Learning: Causal Learning
• Intelligent Robots: State Estimation
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

The use of terahertz (THz) communications with massive multiple input multiple output (MIMO) systems in 6G can potentially provide high data rates and low latency communications. However, accurate channel estimation in THz frequencies presents significant challenges due to factors such as high propagation losses, sensitivity to environmental obstructions, and strong atmospheric absorption. These challenges are par- ticularly pronounced in urban environments, where traditional channel estimation methods often fail to deliver reliable results, particularly in complex non-line-of-sight (NLoS) scenarios. This paper introduces a novel vision-based channel estimation tech- nique that integrates causal reasoning into urban THz communi- cation systems. The proposed method combines computer vision algorithms with variational causal dynamics (VCD) to analyze real-time images of the urban environment, allowing for a deeper understanding of the physical factors that influence THz signal propagation. By capturing the complex, dynamic interactions between physical objects (such as buildings, trees, and vehicles) and the transmitted signals, the model can predict the channel with up to twice the accuracy of conventional methods. This model improves estimation accuracy and demonstrates supe- rior generalization performance. Hence, it can provide reliable predictions even in previously unseen urban environments. The effectiveness of the proposed method is particularly evident in NLoS conditions, where it significantly outperforms traditional methods such as by accounting for indirect signal paths, such as reflections and diffractions. Simulation results confirm that the proposed vision-based approach surpasses conventional artificial intelligence (AI)-based estimation techniques in accuracy and robustness, showing a substantial improvement across various dynamic urban scenarios.

Problem

• Addresses THz channel estimation challenges in urban environments
• Integrates vision and causal learning to improve NLoS accuracy
• Enhances prediction reliability in dynamic, unseen urban scenarios

Innovation

• Vision-based channel estimation with causal reasoning
• Integrates computer vision and variational causal dynamics
• Predicts THz channels using real-time urban environment images