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

EA-LSTM
=======

Overview
--------

``neuralhydrology_ealstm`` complements the plain LSTM adapter with a lightweight static gating path inspired by EA-LSTM style hydrology models.

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

         Flood

      .. 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

         1

      .. container:: catalog-stat-note

         Streamflow

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

      .. container:: catalog-stat-value

         :doc:`Flood Benchmark </benchmarks/flood_benchmark>`

      .. container:: catalog-stat-note

         Primary benchmark-family link used for compatible evaluation coverage.


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

``neuralhydrology_ealstm`` complements the plain LSTM adapter with a lightweight static gating path inspired by EA-LSTM style hydrology models.

It keeps the same graph-temporal input contract as the rest of the flood streamflow roadmap.

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

**Primary benchmark family:** :doc:`Flood Benchmark </benchmarks/flood_benchmark>`

**Mapped benchmark ecosystems:** :doc:`WaterBench </benchmarks/waterbench>`

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

**Paper:** `Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets <https://doi.org/10.5194/hess-23-5089-2019>`_ | **Repo:** `Repository <https://github.com/neuralhydrology/neuralhydrology>`__

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

Primary entrypoint: ``neuralhydrology_ealstm``

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

- Streamflow

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

.. code-block:: python

   import torch
   from pyhazards.models import build_model

   model = build_model(name="neuralhydrology_ealstm", task="regression", input_dim=2, out_dim=1)
   preds = model({"x": torch.randn(1, 4, 6, 2)})
   print(preds.shape)

Notes
-----

- This adapter focuses on the entity-aware gating contract, not exact repo parity.