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

AEFA
====

Overview
--------

The AEFA alignment is implemented as a synthetic-backed dense-grid forecasting adapter used by the WaveCastNet benchmark config.

It keeps the forecasting task and metric shape aligned without claiming a full AEFA data pipeline.

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

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

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

      .. container:: catalog-stat-value

         Ecosystem

      .. container:: catalog-stat-note

         Family benchmark or external ecosystem view.

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

      .. container:: catalog-stat-value

         Earthquake

      .. container:: catalog-stat-note

         Public hazard grouping used on the benchmark index page.

   .. grid-item-card:: Support Status
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         :bdg-info:`Synthetic-backed`

      .. container:: catalog-stat-note

         Current maturity of the adapter or evaluator path.

   .. grid-item-card:: Linked Models
      :class-card: catalog-stat-card

      .. container:: catalog-stat-value

         1

      .. container:: catalog-stat-note

         1 model


Benchmark Mapping
-----------------

**Shared benchmark key:** ``earthquake``

**Registered class:** ``EarthquakeBenchmark``

Mapped benchmark family
~~~~~~~~~~~~~~~~~~~~~~~

:doc:`Earthquake Benchmark </benchmarks/earthquake_benchmark>`

Primary Source
~~~~~~~~~~~~~~

`AEFA <https://github.com/chenyk1990/aefa>`_.

.. dropdown:: Supported Tasks
   :class-container: catalog-dropdown

   - Wavefield Forecasting

.. dropdown:: Key Metrics
   :class-container: catalog-dropdown

   - ``mae``
   - ``mse``

.. dropdown:: Smoke Configs
   :class-container: catalog-dropdown

   - ``wavecastnet_benchmark_smoke.yaml``

.. dropdown:: Linked Models
   :class-container: catalog-dropdown

   :doc:`WaveCastNet </modules/models_wavecastnet>`.