gprof_ir is an open-weight model from Simonpf, released under MIT License. Its published files total 345.4 MB.
GPROF IR is a satellite precipitation retrieval for geostationary IR observations. - 11 um brightness temperatures from geostationary sensors For questions see corresponding author in reference.
Model Card
By Simonpf, published under mit, revision ee2ec969066b.
GPROF IR is a satellite precipitation retrieval for geostationary IR observations. - 11 um brightness temperatures from geostationary sensors For questions see corresponding author in reference.
Read Simonpf's full model card
Model Card: GPROF IR
Model Details
- Model Name: GPROF IR
- Developer: Simon Pfreundschuh
- License: MIT
- Model Type: Neural Network for Precipitation Retrieval
- Language: Not applicable
- Framework: PyTorch
- Repository: github.com/simonpf/gprof_ir
Model Description
GPROF IR is a satellite precipitation retrieval for geostationary IR observations.
Inputs
- 11 um brightness temperatures from geostationary sensors
Outputs
- Surface precipitation estimates
Training Data
- Training Data Source: Satellite-based observations and collocated ground truth precipitation estimates derived from GPM 2BCMB.
- Data Preprocessing: Normalization
Training Procedure
- Optimizer: AdamW
- Loss Function: Quantile regression
- Training Hardware: 2 NVIDIA RTX 6000
- Hyperparameters: Not exhaustively tuned
Performance
- Evaluation Metrics: Bias, Mean Squared Error (MSE), Mean Absolute Error (MAE), Correlation Coefficient
- Benchmark Comparisons: Compared against ground-based radar.
Intended Use
- Primary Use Case: Satellite-based precipitation retrieval for weather and climate applications
- Potential Applications: Hydrology, extreme weather forecasting, climate research
- Usage Recommendations: Performance may vary across different climate regimes
Ethical Considerations
- Bias Mitigation: Extensive validation against independent datasets
Contact
For questions see corresponding author in reference.
Identity and Version
- Repository
- simonpf/gprof_ir
- Publisher
- Simonpf
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- ee2ec969066b1713203428db5d1f294837e767be
- First published
- 2025-03-16
- Last updated
- 2026-10-18
Files and Weights
10 files, 345.4 MB in total. The weights are 6 files totalling 279.8 MB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| gprof_ir_clim_1.pt | Weights | 41.0 MB | 29189206a9ca |
| gprof_ir_clim_4.pt | Weights | 76.8 MB | d285db64f84a |
| gprof_ir_cmb.pt | Weights | 40.5 MB | 3ac45c94878a |
| gprof_ir_gmi.pt | Weights | 40.5 MB | b9927ba8c479 |
| gprof_ir_gmi_3.pt | Weights | 40.5 MB | 9286b79b07ba |
| gprof_ir_gmi_5.pt | Weights | 40.5 MB | 7cb9d67c6879 |
| README.md | Documentation | 1.6 KB | — |
| test_data/merg_2018010100_4km-pixel | Other | 65.3 MB | d29795c410ae |
| test_data/merg_2020010100_4km-pixel.nc4 | Other | 316.8 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 279.8 MB
Released by Simonpf through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 279.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gprof_ir
Can I use gprof_ir commercially?
Yes. gprof_ir is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.