paper
2023
Observations & remote sensing
Explainability, uncertainty & physics New model or method
Physics-informed / physics-constrainedCNN / U-NetNASA Journal
2023-01-01
047
Jan 2023
Yiding Wang, Jie Gong, Dong L. Wu et al.
IEEE Transactions on Geoscience and Remote Sensing
NASA
A physics-informed CloudMask loss improves deep networks that reconstruct 3D multilayer cloud masks from 2D satellite imagery over binary cross-entropy.
Toward Physics-Informed Neural Networks for 3-D Multilayer Cloud Mask Reconstruction
In one sentence. A physics-informed CloudMask loss improves deep networks that reconstruct 3D multilayer cloud masks from 2D satellite imagery over binary cross-entropy.
Labels
- Topic
- Observations & remote sensing, Explainability, uncertainty & physics
- Type
- New model or method
- Method
- Physics-informed / physics-constrained, CNN / U-Net
- Domain
- Global
- Data
- Satellite
- Status
- Research
- Identifiers
- DOI:10.1109/tgrs.2023.3329649 OpenAlex:W4388240334
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.