ANANSI v1 โ€” Nigeria Sovereign Terrain Intelligence Model

Developed by: Krystallx Shield ยท Engr. Ahmadu Yusuf Soje
Classification: Sovereign Development Asset
Territory: Federal Republic of Nigeria
Last Updated: States trained: Rivers, Borno

Training Coverage

  • States trained: 2 / 37 (36 states + FCT)
  • Total chips: ~4,132
  • Completed states: Rivers, Borno
  • Remaining states: 35 to go

Architecture

  • Base: ViT-Base (Vision Transformer, 86M params)
  • Fine-tuned classification head for 6 Nigerian terrain classes
  • Input: Sentinel-2 L2A RGB (B02, B03, B04) @ 224ร—224px @ 10m

Terrain Classes

ID Class Description
0 Urban/Built-up Roads, buildings, settlements
1 Vegetation/Savanna Guinea savanna, shrubland
2 Water Rivers, lakes, creeks
3 Bare Soil/Laterite Exposed soil, mining sites
4 Agriculture Farmlands, crop fields
5 Forest Dense forest, mangroves

Intended Use

Sovereign defense intelligence, illegal mining detection, flood mapping, encampment detection, and geospatial threat analysis for Nigerian government and defense institutions via the Krystallx Shield C4ISR platform.

Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support