WildfireSpreadTS¶

Overview¶

wildfirespreadts models wildfire spread as a sequence-to-mask prediction task.

At a Glance¶

Hazard Family

Wildfire

Public catalog grouping used for this model.

Maturity

Implemented

Catalog maturity label used on the index page.

Tasks

Spread

Benchmark Family

Wildfire Benchmark

Primary benchmark-family link used for compatible evaluation coverage.

Description¶

wildfirespreadts models wildfire spread as a sequence-to-mask prediction task.

The PyHazards adapter uses a compact 3D convolution stack that consumes short raster history windows and predicts the next spread mask.

Benchmark Compatibility¶

Primary benchmark family: Wildfire Benchmark

Mapped benchmark ecosystems: WildfireSpreadTS

External References¶

Paper: WildfireSpreadTS: A Dataset of Multi-Modal Time Series for Wildfire Spread Prediction | Repo: Repository

Registry Name¶

Primary entrypoint: wildfirespreadts

Supported Tasks¶

Spread

Programmatic Use¶

import torch
from pyhazards.models import build_model

model = build_model(
    name="wildfirespreadts",
    task="segmentation",
    history=4,
    in_channels=6,
)
logits = model(torch.randn(2, 4, 6, 16, 16))
print(logits.shape)

Notes¶

The smoke dataset uses temporal wildfire spread tensors rather than single-frame rasters.