.. This file is generated by scripts/render_model_docs.py. Do not edit by hand.

DNN-LSTM-AutoEncoder
====================

Overview
--------

``wildfire_fpa`` is the paper-facing PyHazards entrypoint for the FPA-FOD wildfire framework described by Shen et al. (2023).

At a Glance
-----------

.. grid:: 1 2 4 4
   :gutter: 2
   :class-container: catalog-grid

   .. grid-item-card:: Hazard Family
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         Wildfire

      .. container:: catalog-stat-note

         Public catalog grouping used for this model.

   .. grid-item-card:: Maturity
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         Implemented

      .. container:: catalog-stat-note

         Catalog maturity label used on the index page.

   .. grid-item-card:: Tasks
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         2

      .. container:: catalog-stat-note

         Classification, Forecasting

   .. grid-item-card:: Benchmark Family
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         :doc:`Wildfire Benchmark </benchmarks/wildfire_benchmark>`

      .. container:: catalog-stat-note

         Primary benchmark-family link used for compatible evaluation coverage.


Description
-----------

``wildfire_fpa`` is the paper-facing PyHazards entrypoint for the FPA-FOD wildfire framework described by Shen et al. (2023).

PyHazards exposes the combined DNN-LSTM-AutoEncoder workflow through one public registry name while keeping the lower-level components internal.

Benchmark Compatibility
-----------------------

**Primary benchmark family:** :doc:`Wildfire Benchmark </benchmarks/wildfire_benchmark>`

External References
-------------------

**Paper:** `Developing risk assessment framework for wildfire in the United States <https://www.sciencedirect.com/science/article/pii/S2949926723000033>`_

Registry Name
-------------

Primary entrypoint: ``wildfire_fpa``

Supported Tasks
---------------

- Classification
- Forecasting

Programmatic Use
----------------

.. code-block:: python

   import torch
   from pyhazards.models import build_model

   model = build_model(
       name="wildfire_fpa",
       task="classification",
       in_dim=8,
       out_dim=5,
       hidden_dim=64,
       depth=2,
   )

   x = torch.randn(4, 8)
   logits = model(x)
   print(logits.shape)

Notes
-----

- This is the only retained public method from Shen et al. (2023) in the PyHazards catalog.
- Use ``task="classification"`` for the DNN stage.
- Use ``task="forecasting"`` or ``task="regression"`` for the sequence stage.