.. This file is generated by scripts/render_dataset_docs.py. Do not edit by hand. IBTrACS ======= Synthetic-backed storm-track adapter aligned to the IBTrACS tropical cyclone archive. Overview -------- IBTrACS is the public storm-track adapter used by PyHazards for shared tropical cyclone benchmark runs. The current implementation is synthetic-backed, but it preserves the track-intensity forecasting surface used by the shared tropical cyclone evaluator. At a Glance ----------- .. list-table:: :widths: 28 72 :stub-columns: 1 * - Provider - NOAA NCEI International Best Track Archive for Climate Stewardship surfaced through a PyHazards adapter * - Hazard Family - Tropical Cyclone * - Source Role - Track Archive * - Coverage - Benchmark-aligned tropical cyclone track and intensity samples * - Geometry - Storm-track history sequences * - Spatial Resolution - Storm-centered best-track sequences * - Temporal Resolution - Historical track windows with forecast horizons * - Update Cadence - Generated locally for smoke and benchmark-alignment runs * - Period of Record - Synthetic-backed benchmark adapter * - Formats - PyTorch tensors via the dataset registry * - Registry Entry - ``ibtracs_tracks`` Data Characteristics -------------------- - Storm-history sequences with future latitude, longitude, and intensity targets. - Registry-backed benchmark adapter rather than a raw IBTrACS archive loader. - Supports both basin-specific hurricane models and broader tropical cyclone adapters. Typical Use Cases ~~~~~~~~~~~~~~~~~ - Hurricast smoke tests. - Shared tropical cyclone benchmark runs for track and intensity prediction. - Benchmark-aligned validation for weather-model storm adapters. Access ------ Use the links below to access the upstream source or its public documentation. - `IBTrACS product page `_ PyHazards Usage --------------- Use this adapter when you want the public IBTrACS-aligned storm-track surface exposed by the tropical cyclone benchmark. Registry Workflow ~~~~~~~~~~~~~~~~~ Primary dataset name: ``ibtracs_tracks`` .. code-block:: python from pyhazards.datasets import load_dataset data = load_dataset( "ibtracs_tracks", micro=True, history=6, horizon=5, ).load() train = data.get_split("train") print(train.inputs.shape, train.targets.shape) Related Coverage ~~~~~~~~~~~~~~~~ **Benchmarks:** :doc:`Tropical Cyclone Benchmark `, :doc:`IBTrACS ` **Representative Models:** :doc:`Hurricast `, :doc:`GraphCast TC Adapter `, :doc:`Pangu TC Adapter `, :doc:`FourCastNet TC Adapter ` Inspection Workflow ------------------- This dataset is currently surfaced as a registry-backed benchmark adapter, so there is no standalone inspection CLI documented for it. Notes ----- - This is a synthetic-backed benchmark adapter rather than a full IBTrACS ingestion pipeline. Reference --------- - `IBTrACS `_.