Sea Clutter Suppression Method Based on a Self-Attention Spatio-Temporal Prediction Network

The prediction and suppression of sea clutter have long been challenging issues in the field of maritime target detection. Traditional sea clutter prediction algorithms often struggle to effectively model complex sea clutter data. When predicting sea clutter based on temporal correlations, the clutter data from adjacent range cells can influence each other, resulting in low prediction accuracy. To address these challenges, this article analyzes the spatio-temporal correlation of sea clutter and designs a spatio-temporal prediction network based on a self-attention mechanism, which comprehensively analyzes sea clutter data across multiple range cells. Subsequently, the cross-spectrum was employed to compare the frequency coherence between the predicted sea clutter and the measured sea clutter. A bandpass filter was then designed to accurately suppress the clutter by targeting the specific frequency band of the target signal. The proposed spatio-temporal prediction model and suppression algorithm were evaluated using three sea clutter measured datasets collected from IPIX radar, X-band radar, and UHF-band radar. The results demonstrate that, compared with a temporal LSTM model, the proposed prediction algorithm reduced the overall average mean squared error by 0.06 and improved prediction accuracy by approximately 26.18%, while the suppression algorithm effectively enhanced the signal-to-clutter ratio of the radar echo, achieving an improvement of 17.03 dB.

• Publication year

  2025

• Venue

  IEEE Transactions on Aerospace and Electronic Systems

• Publication date

  2025-12-01

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/TAES.2025.3584010
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Research on Sea Clutter Simulation Method Based on Deep Cognition of Characteristic Parameters

  2024cited by this paper
• A Data-Driven Optimization Method for Simulating Arbitrarily Distributed and Spatial–Temporal Correlated Radar Sea Clutter

  2023cited by this paper
• Sequence-Feature Detection of Small Targets in Sea Clutter Based on Bi-LSTM

  2022cited by this paper
• A sea clutter detection method based on LSTM error frequency domain conversion

  2021cited by this paper
• Prediction of Sea Clutter Based on Recurrent Neural Network

  2021cited by this paper
• A Novel Sea Clutter Suppression Method Based on Deep Learning with Exploiting Time-Frequency Features

  2021cited by this paper
• Review on Convolutional Neural Networks (CNN) in vegetation remote sensing

  2021cited by this paper
• A Novel Sea Clutter Suppression Method based on Neural Network

  2021cited by this paper
• Annual Progress of the Sea-detecting X-band Radar and Data Acquisition Program

  2021cited by this paper
• Status and Prospects of Feature-Based Detection Methods for Floating Targets on Sea Surface

  2020cited by this paper
• Self-Attention ConvLSTM for Spatiotemporal Prediction

  2020cited by this paper
• Sea Clutter Amplitude Prediction Using a Long Short-Term Memory Neural Network

  2019cited by this paper
• Sea Clutter Suppression Based on Selective Reconstruction of Features

  2019cited by this paper
• SVM-Based Sea-Surface Small Target Detection: A False-Alarm-Rate-Controllable Approach

  2018cited by this paper
• Artificial intelligence techniques for small boats detection in radar clutter. Real data validation

  2018cited by this paper
• Unsupervised Anomaly Detection With LSTM Neural Networks

  2017cited by this paper
• A machine learning approach to radar sea clutter suppression

  2017cited by this paper
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting

  2015cited by this paper
• New Spatial Correlation Models for Sea Clutter

  2015cited by this paper
• Sea-Spike Detection in High Grazing Angle X-Band Sea-Clutter

  2013cited by this paper
• Another look at measures of forecast accuracy

  2006cited by this paper
• Prediction of noisy chaotic time series using an optimal radial basis function neural network

  2001cited by this paper
• Sea-clutter modeling using a radial-basis-function neural network

  2001cited by this paper
• Summarizing multiple aspects of model performance in a single diagram

  2001cited by this paper
• The Nature of Statistical Learning Theory

  2000cited by this paper
• New method for the simulation of correlated K-distributed clutter

  1994cited by this paper

• No citing papers are available for this paper.