E2E-FANet: A Highly Generalizable Framework for Waves prediction Behind Floating Breakwaters via Exogenous-to-Endogenous Variable Attention

2025-05-10

AI Summary

Existing methods struggle to accurately model the nonlinear hydrodynamic interactions between waves and floating breakwaters (FBs) and lack the capability to characterize complex frequency-domain relationships across multiple measurement points, thereby hindering optimal design and safety enhancement of coastal engineering structures. To address this, we propose an end-to-end time–frequency collaborative perception framework. Our approach introduces, for the first time, a dual fundamental-frequency mapping module and an exogenous–endogenous cross-attention mechanism to jointly capture temporal dynamics, frequency-domain coupling, and multivariate correlations in wave-height sequences. It integrates orthogonal cosine/sine-based frequency-domain feature extraction, temporal attention, and multi-level generalization validation. Experimental results demonstrate that our method achieves over 18% higher prediction accuracy than state-of-the-art approaches under identical/different wave conditions and variable relative water depths, with significantly improved generalization performance.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Accurate prediction of waves behind floating breakwaters (FB) is crucial for optimizing coastal engineering structures, enhancing safety, and improving design efficiency. Existing methods demonstrate limitations in capturing nonlinear interactions between waves and structures, while exhibiting insufficient capability in modeling the complex frequency-domain relationships among elevations of different wave gauges. To address these challenges, this study introduces the Exogenous-to-Endogenous Frequency-Aware Network (E2E-FANet), a novel end-to-end neural network designed to model relationships between waves and structures. The E2E-FANetarchitecture incorporates a Dual-Basis Frequency Mapping (DBFM) module that leverages orthogonal cosine and sine bases to extract wave features from the frequency domain while preserving temporal information. Additionally, we introduce the Exogenous-to-Endogenous Cross-Attention (E2ECA) module, which employs cross attention to model the interactions between endogenous and exogenous variables. We incorporate a Temporal-wise Attention (TA) mechanism that adaptively captures complex dependencies in endogenous variables. These integrated modules function synergistically, enabling E2E-FANet to achieve both comprehensive feature perception in the time-frequency domain and precise modeling of wave-structure interactions. To comprehensively evaluate the performance of E2E-FANet, we constructed a multi-level validation framework comprising three distinct testing scenarios: internal validation under identical wave conditions, generalization testing across different wave conditions, and adaptability testing with varying relative water density (RW) conditions. These comprehensive tests demonstrate that E2E-FANet provides accurate waves behind FB predictions while successfully generalizing diverse wave conditions.

Problem

• Predicting waves behind floating breakwaters accurately
• Modeling nonlinear wave-structure interactions effectively
• Capturing complex frequency-domain relationships among wave gauges

Innovation

• Dual-Basis Frequency Mapping for wave features
• Exogenous-to-Endogenous Cross-Attention for interactions
• Temporal-wise Attention for variable dependencies