gher-uliege/DINCAE.jl
DINCAE (Data-Interpolating Convolutional Auto-Encoder) is a neural network to reconstruct missing data in satellite observations.
This tool helps oceanographers and climate scientists reconstruct missing information in satellite observations of the ocean, like sea surface temperature. It takes incomplete satellite data, often with gaps due to clouds or sensor limitations, and fills in those missing areas to provide a complete and more reliable dataset. Researchers analyzing ocean patterns or climate change would use this to get a clearer picture from their satellite imagery.
Use this if you need to accurately fill in gaps in your satellite oceanographic data to create a complete and consistent record for analysis.
Not ideal if you primarily work with CPU-only systems or do not deal with large-scale satellite image reconstruction, as performance will be significantly slower.
Stars
33
Forks
10
Language
Julia
License
GPL-3.0
Category
Last pushed
Jan 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gher-uliege/DINCAE.jl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
CliMA/Oceananigans.jl
🌊 Julia software for fast, friendly, flexible, ocean-flavored fluid dynamics on CPUs and GPUs
JuliaLang/julia
The Julia Programming Language
WassimTenachi/PhySO
Physical Symbolic Optimization
EnzymeAD/Enzyme.jl
Julia bindings for the Enzyme automatic differentiator
astroautomata/SymbolicRegression.jl
Distributed High-Performance Symbolic Regression in Julia