Downloads · 30 days
0
vietnam-deforestation-risk-logistic
MahdiFattahi/vietnam-deforestation-risk-logistic
vietnam-deforestation-risk-logistic is a machine learning model from MahdiFattahi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
An interpretable logistic-regression baseline for predicting forest-loss risk at grid-cell level in Gia Lai Province, Vietnam.
Access
Public
Updated Jul 26, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 47%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026
- SHA
- 145cf98a
Model card
From the Hugging Face model README
🌳 Vietnam Deforestation Risk Logistic Model
An interpretable logistic-regression baseline for predicting forest-loss risk at grid-cell level in Gia Lai Province, Vietnam.
Model Details
- Architecture: Logistic Regression (scikit-learn
StandardScalernormalized). - Inputs: 1 km aggregated raster features (elevation, slope, precipitation, historical forest loss, baseline canopy).
- Target: Binary deforestation indicator.
Performance Metrics (Manuscript Table 3)
- Provided Split (Out-of-sample):
- AUC:
0.931 - AP:
0.926 - F1:
0.881 - Capture@10%:
0.190
- AUC:
- Area Transfer (K’Bang → Mang Yang):
- AUC:
0.743 - Capture@10%:
0.170
- AUC:
Ethical Considerations & Intended Use
For proactively identifying high-risk deforestation zones to support local conservation patrols and reserve boundary allocation. This model must NOT be used to justify punitive commercial land claims or displacement of forest communities without on-the-ground human verification.
Source Code & Reproducibility
- Source Pipeline Code: Borino88/deforestation-risk-vietnam
- Interactive Explorer Space: MahdiFattahi/deforestation-risk-explorer
- License
- mit
- Languages
- en
- Created
- Jul 26, 2026
- Updated
- Jul 26, 2026