Skip to content

About

Fine-tuning NASA/IBM Prithvi foundation model for wildfire burn-intensity segmentation from HLS satellite imagery (UPerNet, DeepLabV3, FCN)

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

 
 

Repository files navigation

Burned Area Intensity Mapping with Prithvi

Fine-tuning NASA/IBM's Prithvi geospatial foundation model to map wildfire burn intensity (5 severity grades) from Harmonized Landsat Sentinel-2 (HLS) satellite imagery, and comparing several segmentation decoders against Prithvi's binary Burn Scar model.

Urban Computing project, Leiden University (2025), by Priyanjali Goel and Maria Kapusheva (equal contribution).

True-colour vs false-colour HLS composite of a burned area True colour (R, G, B) vs false colour (NIR, SWIR1, SWIR2). In the false-colour composite the burn scar stands out in blue.

Highlights

  • Turned Prithvi from binary burn-scar detection into multi-class burn-intensity segmentation (grades 0–4, from unburned to severely burned).
  • Compared four decoders on a pretrained Prithvi backbone: FCN, UPerNet (with and without input normalisation) and DeepLabV3.
  • The best model, UPerNet with normalised inputs, reaches F1 0.59 and accuracy 0.59, against F1 0.26 for the Burn Scar baseline. That is a ΔAccuracy of +0.22 over the baseline.
  • Built an end-to-end pipeline: HLS data preparation, an 80/10/10 split, fine-tuning with TerraTorch and Lightning, and evaluation and visualisation.

Problem

Existing burned-area methods say where a fire burned, not how badly. Burn intensity is what forest managers need to plan recovery. The research question:

Can the geospatial foundation model Prithvi be fine-tuned to map burn intensity accurately from satellite imagery?

Improvement is measured relative to the binary baseline:

ΔAccuracy = Accuracy(burn intensity model) − Accuracy(burn scar baseline)

Data

  • Source: ibm-nasa-geospatial/burn_intensity. Only the post-fire scenes (post.zip) are used.
  • Input: HLS tiles with 6 spectral bands: Blue, Green, Red, Narrow NIR, SWIR1, SWIR2. SWIR bands see through thin smoke and are sensitive to moisture and soil, which is key for separating burn severity.
  • Labels: a single-band grading mask with values 0 (unburned) to 4 (severely burned). Unlabelled pixels are set to -1.
  • Split: 296 image–mask pairs, split 80 / 10 / 10: 237 train, 30 validation, 29 test. See burn_intensity_final_dataset.py.

Method

Component Setting
Backbone Pretrained Prithvi: 100M parameters (FCN run), 300M (UPerNet / DeepLabV3 runs)
Decoders FCN (128 channels), UPerNet (512 channels, ± input normalisation), DeepLabV3 (normalised inputs)
Task Semantic segmentation, 5 burn-severity classes
Loss Cross-entropy with class weights, normalised to sum to 1, to counter class imbalance
Data module TerraTorch GenericNonGeoSegmentationDataModule, batch size 8
Training 80 epochs, validation every 10 epochs, AdamW (weight decay 0.05), T4 GPU
Monitoring TensorBoard logger, early stopping and checkpoint callbacks

Baseline: Prithvi's pretrained Burn Scar model, which is binary. To compare it fairly, the intensity test masks were binarised: grades 1–4 become burned (1) and 0 stays unburned.

Why these decoders:

  • UPerNet combines a Pyramid Pooling Module and a Feature Pyramid Network for multi-scale context.
  • DeepLabV3 uses atrous convolutions and ASPP to keep fine detail without heavy downsampling.
  • FCN is the simplest upsampling decoder and serves as a reference point.

Results

FCN decoder UPerNet (no norm) UPerNet (norm) DeepLabV3 Burn Scar baseline
F1 score 0.38 0.48 0.59 0.58 0.26
Accuracy 0.38 0.48 0.59 0.58 0.37
ΔAccuracy vs baseline 0.01 0.11 0.22 0.21 –

F1 and accuracy per architecture

Predictions by decoder

Predicted burn-intensity masks for FCN, UPerNet without normalisation and DeepLabV3

  • FCN: almost no structure. Plain transposed-convolution upsampling without multi-scale aggregation can't separate the burn grades.
  • UPerNet without normalisation: recovers large spatial regions but confuses the grades.
  • DeepLabV3: strong scores (0.58), but over-predicts grade 1 and needs sharper boundaries.

Best model vs baseline

UPerNet with normalisation vs Burn Scar baseline

UPerNet with normalised inputs gives the most accurate grade-1 boundaries and a reasonable spread of the other grades. The binary Burn Scar model misses most of the burned area in this scene.

Takeaways and future work

  • Foundation models like Prithvi can learn the spectral signature of burn severity, not just burned vs unburned.
  • Input normalisation and a multi-scale decoder (UPerNet) matter most: they account for +0.11 F1 over UPerNet without normalisation.
  • Accuracy is still moderate (~0.6), so the models aren't ready for operational use. Next steps:
    • more training data
    • adding pre-fire and temporal scenes
    • further decoder and architecture changes
  • Engineering lesson: Prithvi's tooling changed fast. MMEngine-based versions broke, so the pipeline was moved to IBM's TerraTorch fine-tuning stack.

Repository structure

final_codes_dataset_arch_results/
├── burn_intensity_final_dataset.py   # organise post.zip into train/val/test images & labels
├── results_with_UperNet_FCN.ipynb    # FCN and UPerNet (± normalisation) fine-tuning + evaluation
├── results_with_deeplabv3.ipynb      # DeepLabV3 decoder fine-tuning + evaluation
└── results_with_baseline.ipynb       # Prithvi Burn Scar baseline on binarised test masks
exploration_data_models/              # early experiments: band exploration, MMSeg-based Prithvi setup, inference
docs/images/                          # figures used in this README
BurnAreaSegmentation_Report.pdf       # full project report

Getting started

pip install terratorch lightning rioxarray rasterio torchmetrics scikit-image gradio_client
  1. Download post.zip from the burn_intensity dataset and set source_dir / base_dir in burn_intensity_final_dataset.py.
  2. Run the script to create the train/validation/test folders, or use the ready-made split below.
  3. Open the notebooks in final_codes_dataset_arch_results/. A GPU (for example a Colab T4) is recommended.

Prepared datasets (Kaggle)

Tech stack

Python · PyTorch · Lightning · TerraTorch · Prithvi (IBM/NASA) · rioxarray / rasterio · scikit-learn · matplotlib

References

  • Jakubik et al. (2023). Foundation Models for Generalist Geospatial Artificial Intelligence (Prithvi). arXiv:2310.18660
  • Xiao et al. (2018). Unified Perceptual Parsing for Scene Understanding (UPerNet). ECCV
  • Chen et al. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation (DeepLabV3). arXiv:1706.05587
  • Pinto et al. (2021). A practical method for high-resolution burned area monitoring using Sentinel-2 and VIIRS. Remote Sensing

Authors

Priyanjali Goel and Maria Kapusheva, MSc AI, Leiden University. Original repository: MariaKapusheva/BurnedAreaMapping.

About

Fine-tuning NASA/IBM Prithvi foundation model for wildfire burn-intensity segmentation from HLS satellite imagery (UPerNet, DeepLabV3, FCN)

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages