pakflood-lora / README.md
msherry's picture
README: GitHub link
6744dd2 verified
|
Raw History Blame Contribute Delete
1.88 kB
---
license: cc-by-4.0
tags:
- flood-mapping
- sentinel-1
- sar
- terramind
- lora
- peft
- semantic-segmentation
- pakistan
datasets:
- links-ads/geoid-flood
base_model: ibm-esa-geospatial/TerraMind-1.0-base
---
# PakFlood-LoRA
Flood mapping from Sentinel-1 radar with a frozen TerraMind v1 base encoder, a rank-32 LoRA adapter (5.7 M trained encoder weights) and a UNet decoder, trained on GEOID-Flood. Every 10 m pixel of a pre/post radar pair is labelled as dry land, permanent water or flood.
- Official GEOID-Flood test split (2,417 tiles): flood IoU 0.525, equal to full fine-tuning of all 101 M weights (frozen encoder 0.433, LoRA r16 0.493).
- Pakistan official test tiles (EMSR838, August 2025, 15 tiles): flood IoU 0.786.
- The sample tiles in this Space are those 15 official test tiles; the model never saw them in training.
MS AI deep learning course project, NED University of Engineering & Technology. Author: Muhammad Shahwar Uddin. Supervisor: Dr. Sharaf Hussain.
Data: GEOID-Flood v1.1 (Chiriaco et al., Fondazione LINKS, 2026, CC BY 4.0), built from Copernicus Emergency Management Service activations. Model: TerraMind v1 base (Jakubik et al., IBM and ESA, 2025) through TerraTorch; LoRA (Hu et al., 2022) via Hugging Face PEFT.
**Live demo:** open `PakFlood_LoRA_Colab_demo.ipynb` in Google Colab ([direct link](https://colab.research.google.com/#fileId=https://huggingface.co/msherry/pakflood-lora/blob/main/PakFlood_LoRA_Colab_demo.ipynb)), run the three cells, and use the public Gradio link it prints. Or run locally: `pip install -r requirements.txt && python app.py`.
**Project code, results and figures:** see `code/`, `results/`, `figures/` and [CODE_README.md](CODE_README.md) in this repository (training and evaluation pipeline, per-tile results, all figures).
**Source code on GitHub:** https://github.com/ShahwarUddin/pakflood-lora