Neural Network-Assisted CLEAN for Channel Modeling in Low-SNR Regimes

2026-07-29

AI Summary

This work addresses the limitations of traditional CLEAN algorithms—high computational complexity under low signal-to-noise ratio (SNR) conditions—and purely data-driven approaches, which suffer from poor physical interpretability and weak generalization. The authors propose NN-CLEAN, a hybrid framework that seamlessly integrates a multi-head residual neural network into the CLEAN iterative loop, replacing exhaustive grid search with efficient neural network inference while preserving the physical model for residual subtraction. This design ensures both physical consistency and highly parallelizable computation, effectively preventing the accumulation of non-physical errors. Experimental results demonstrate that at 5 dB SNR, NN-CLEAN achieves over 96% parameter estimation accuracy—comparable to GS-CLEAN—but with substantially reduced computational complexity. Moreover, its runtime and memory consumption remain nearly constant with increasing batch size, significantly outperforming subspace-based methods and end-to-end neural networks.

Abstract

Accurate multipath parameter estimation is critical for modern wireless communication systems, particularly in challenging low-SNR environments. Traditional Maximum Likelihood Estimation algorithms, such as CLEAN, provide high-resolution parameter extraction but suffer from prohibitive computational complexity due to exhaustive grid search. Conversely, purely data-driven deep learning approaches lack physical grounding and struggle to generalize across variable multipath densities and off-grid parameters. To address these limitations, this paper proposes Neural Network-Assisted CLEAN (NN-CLEAN), a hybrid framework that embeds a multi-head residual network directly into the iterative CLEAN extraction loop. By replacing the exhaustive grid search with rapid, parallelizable forward passes while delegating residual subtraction to exact mathematical models, NN-CLEAN isolates physical multipath parameters without accumulating non- physical errors. Extensive Monte Carlo simulations demonstrate that NN-CLEAN achieves estimation accuracy exceeding 96% at 5 dB SNR, matching the traditional Grid-Search CLEAN (GS- CLEAN) baseline, while providing a massive reduction in computational complexity and substantially outperforming subspace methods and standalone one-shot neural networks. Crucially, NN-CLEAN exhibits a near-flat scaling in execution runtime and memory consumption as batch sizes increase. This highly efficient parallelization establishes NN-CLEAN as a robust, real- time solution for channel estimation in MIMO systems.

Problem

• multipath parameter estimation
• low-SNR
• channel modeling
• computational complexity
• generalization

Innovation

• Neural Network-Assisted CLEAN
• low-SNR channel modeling
• hybrid physical-data-driven framework
• multipath parameter estimation
• computational complexity reduction