A Deep Learning Framework for Two-Dimensional, Multi-Frequency Propagation Factor Estimation

2025-05-21

AI Summary

Modeling electromagnetic wave propagation for multi-frequency radar signals in the marine atmospheric boundary layer remains computationally prohibitive using conventional parabolic equation (PE) methods, hindering real-time applications. Method: This paper proposes the first end-to-end image-to-image translation deep learning framework tailored for propagation factor estimation, mapping refractivity field images to spatially resolved, multi-frequency propagation factor distributions. It introduces a novel cross-frequency joint modeling mechanism and employs a CNN-based generator incorporating enhanced refractivity inputs. Contribution/Results: Evaluated in two-dimensional scenarios, the framework achieves accuracy comparable to high-fidelity PE numerical simulations while accelerating inference by over two orders of magnitude (>100×). This breakthrough overcomes critical computational bottlenecks, enabling efficient, real-time environmental sensing support for maritime radar system deployment.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Accurately estimating the refractive environment over multiple frequencies within the marine atmospheric boundary layer is crucial for the effective deployment of radar technologies. Traditional parabolic equation simulations, while effective, can be computationally expensive and time-intensive, limiting their practical application. This communication explores a novel approach using deep neural networks to estimate the pattern propagation factor, a critical parameter for characterizing environmental impacts on signal propagation. Image-to-image translation generators designed to ingest modified refractivity data and generate predictions of pattern propagation factors over the same domain were developed. Findings demonstrate that deep neural networks can be trained to analyze multiple frequencies and reasonably predict the pattern propagation factor, offering an alternative to traditional methods.

Problem

• Estimating multi-frequency propagation factor in marine radar
• Reducing computational cost of traditional parabolic simulations
• Predicting signal propagation impact using deep neural networks

Innovation

• Deep neural networks estimate propagation factors
• Image-to-image translation for refractivity data
• Multi-frequency analysis replaces traditional simulations