Dual-Branch State-Displacement Network for Sea Surface Temperature Super-Resolution

2026-08-15

AI Summary

This study addresses the limitations of low resolution and missing fine thermal structures in satellite sea surface temperature (SST) imagery by proposing a Dual-Branch State Displacement Network (DB-SD-Net). Integrating the discrete wavelet transform with a VGG-UNet semantic branch, this method incorporates a Structural State Space module and a displacement gating mechanism to enhance high-frequency details in the frequency domain while ensuring precise geometric reconstruction. Extensive experiments on multiple public SST datasets demonstrate that DB-SD-Net significantly outperforms existing state-of-the-art methods, effectively improving super-resolution reconstruction performance. Consequently, this approach provides robust technical support for observing micro-scale oceanic features, such as ocean fronts, thereby advancing the capability to resolve fine thermal structures in remote sensing applications.

Abstract

Sea surface temperature (SST) is a critical indicator of global climate change, yet satellite-derived SST imagery often suffers from coarse spatial resolution, limiting the ability to capture fine-scale thermal structures such as ocean fronts. To address this, we propose a Dual-Branch State-Displacement Network (DBSD-Net) for SST super-resolution. DBSD-Net adopts a dual-branch architecture: a wavelet frequency branch that explicitly separates low and high-frequency components via discrete wavelet transform for targeted processing, and a VGGUNet branch that extracts multi-scale semantic features from a frozen pre-trained VGG backbone. Within the wavelet branch, we introduce a Structural State Space Module (SSSM) with a Gated Structure Refinement (GSR) unit to efficiently capture long-range dependencies and enhance structural integrity, and a Displacement Gate Module (DGM) that learns a displacement field for geometry-aware modulation of high-frequency details, thereby mitigating spatially varying degradation. Experiments on multiple public SST datasets demonstrate that DBSD-Net outperforms existing state-of-the-art methods.

Problem

• Sea Surface Temperature
• Super-Resolution
• Spatial Resolution
• Fine-scale Thermal Structures

Innovation

• Dual-Branch Architecture
• Wavelet Transform
• Structural State Space Module
• Displacement Gate Module
• Sea Surface Temperature Super-Resolution