Global Offshore Wind Turbine Mapping in 2025 Using the CPEF Framework and Sentinel-1 SAR

Area of Science:

• Remote Sensing
• Geospatial Analysis
• Renewable Energy Monitoring

Background:

• Accurate offshore wind turbine (OWT) spatial data is vital for marine planning and resource assessment.
• Existing datasets lack global consistency, full-year coverage, and individual turbine detail.
• There is a need for an open-access, high-resolution global OWT dataset.

Purpose of the Study:

• To develop and validate a novel framework (CPEF) for large-scale OWT detection using Sentinel-1 SAR imagery.
• To create a global, turbine-level OWT dataset for 2025.
• To analyze the spatial distribution patterns of global OWTs.

Main Methods:

• A two-stage framework combining Constant False Alarm Rate (CFAR) detection with deep learning (EfficientNet-B0).
• Utilized PCA-aligned peak profile features fused with EfficientNet-B0 image features for accurate turbine identification.
• Composited multitemporal SAR observations into annual images to enhance target detection.

Main Results:

• The CPEF framework detected 16,270 OWTs globally in 2025 with 96.33% accuracy and 97.25% F1-score.
• Identified previously unmapped turbines in key regions like Jiangsu, Shanghai, and Dogger Bank.
• Global OWTs are concentrated in nearshore Europe and East Asia, with distinct depth distribution patterns.

Conclusions:

• CPEF provides an efficient and interpretable method for global OWT mapping.
• The generated dataset offers valuable turbine-level spatial information for offshore wind resource assessment.
• The study highlights regional differences in offshore wind farm development based on water depth.