Tropical Cyclone MLP¶

Overview¶

tropicalcyclone_mlp complements hurricast with a lighter-weight hurricane baseline that uses the same storm-history input contract.

At a Glance¶

Hazard Family

Tropical Cyclone

Public catalog grouping used for this model.

Maturity

Implemented

Catalog maturity label used on the index page.

Tasks

Track + Intensity

Benchmark Family

Tropical Cyclone Benchmark

Primary benchmark-family link used for compatible evaluation coverage.

Description¶

tropicalcyclone_mlp complements hurricast with a lighter-weight hurricane baseline that uses the same storm-history input contract.

The adapter is useful for practical low-cost intensity and trajectory experiments in basin-filtered settings.

Benchmark Compatibility¶

Primary benchmark family: Tropical Cyclone Benchmark

Mapped benchmark ecosystems: TCBench Alpha

External References¶

Paper: Deep Learning Experiments for Tropical Cyclone Intensity Forecasts | Repo: Repository

Registry Name¶

Primary entrypoint: tropicalcyclone_mlp

Supported Tasks¶

Track + Intensity

Programmatic Use¶

import torch
from pyhazards.models import build_model

model = build_model(name="tropicalcyclone_mlp", task="regression", input_dim=8, history=6)
preds = model(torch.randn(2, 6, 8))
print(preds.shape)

Notes¶

Outputs are lead-time sequences of latitude, longitude, and intensity targets.