Antenna Near-Field Reconstruction from Far-Field Data Using Convolutional Neural Networks

2025-04-23

AI Summary

This work addresses the non-analytic inverse mapping from far-field (FF) antenna measurements to near-field (NF) distributions. We propose an end-to-end deep learning approach that requires neither prior physical models nor numerical integration. For the first time, a convolutional neural network (CNN) is employed to directly learn the highly nonlinear FF-to-NF mapping, circumventing conventional reliance on electromagnetic modeling and iterative optimization. The model is trained on paired simulated FF/NF data using mean squared error (MSE) as the supervised loss. The optimized model achieves MSEs of 0.0199 on the training set and 0.3898 on the test set. Visual evaluation confirms high-fidelity reconstruction of both amplitude and phase distributions for complex near-fields, demonstrating substantial improvements in reconstruction efficiency and generalization capability over traditional methods.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Learning & Optimization for NLP
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Electromagnetic field reconstruction is crucial in many applications, including antenna diagnostics, electromagnetic interference analysis, and system modeling. This paper presents a deep learning-based approach for Far-Field to Near-Field (FF-NF) transformation using Convolutional Neural Networks (CNNs). The goal is to reconstruct near-field distributions from the far-field data of an antenna without relying on explicit analytical transformations. The CNNs are trained on paired far-field and near-field data and evaluated using mean squared error (MSE). The best model achieves a training error of 0.0199 and a test error of 0.3898. Moreover, visual comparisons between the predicted and true near-field distributions demonstrate the model's effectiveness in capturing complex electromagnetic field behavior, highlighting the potential of deep learning in electromagnetic field reconstruction.

Problem

• Reconstruct antenna near-field from far-field data
• Use CNNs for Far-Field to Near-Field transformation
• Avoid reliance on explicit analytical transformations

Innovation

• CNNs transform far-field to near-field data
• Deep learning replaces analytical transformations
• Training uses paired field data with MSE