Neural style transfer between observed and simulated cloud images to improve the detection performance of tropical cyclone precursors
In one sentence. Neural style transfer makes simulated cloud images resemble satellite data, raising tropical cyclone precursor classification performance by 40–90% at 3–7 days lead.
Abstract
Abstract A common observation in the field of pattern recognition for atmospheric phenomena using supervised machine learning is that recognition performance decreases for events with few observed cases, such as extreme weather events. Here, we aimed to mitigate this issue by using numerical simulation and satellite observational data for training. However, as simulation and observational data possess distinct characteristics, we employed neural style transformation learning to transform the simulation data to more closely resemble the observational data. The resulting transformed cloud images of the simulation data were found to possess physical features comparable to those of the observational data. By utilizing the transformed data for training, we successfully improved the classification performance of cloud images of tropical cyclone precursors 7, 5, and 3 days before their formation by 40.5, 90.3, and 41.3%, respectively.
Labels
- Topic
- Extremes & hazards, Observations & remote sensing
- Type
- New model or method
- Method
- CNN / U-Net
- Time scale
- 6 h–3 days
- Domain
- Regional
- Data
- Satellite, km-scale or high-res simulation
- Status
- Research
- Identifiers
- DOI:10.1017/eds.2023.15 OpenAlex:W4383040563
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.