.. _tutorial_tsh_al:

Active learning for TSH
==========================================

Efficient and robust active learning for surface-hopping dynamics: often, you can do surface-hopping dynamics from start to finish within a couple of days on a single GPU! See for details:

- Mikołaj Martyka, Lina Zhang, Fuchun Ge, Yi-Fan Hou, Joanna Jankowska, Mario Barbatti, `Pavlo O. Dral <http://dr-dral.com>`__. `Charting electronic-state manifolds across molecules with multi-state learning and gap-driven dynamics via efficient and robust active learning <https://doi.org/10.1038/s41524-025-01636-z>`__. *npj Comput. Mater.* **2025**, *11*, 132. DOI: 10.1038/s41524-025-01636-z. *Preprint on ChemRxiv*: https://doi.org/10.26434/chemrxiv-2024-dtc1w.

.. note:: 

   It is more efficient to do active learning with the pre-trained, universal excited-state `OMNI-P2x model <https://doi.org/10.26434/chemrxiv-2025-j207x>`__ rather than doing it from scratch with the MS-ANI model. The tutorials will come soon, if you need them urgently, please :doc:`drop us a reminder message <contact>`.

:download:`Zip with tutorial materials <tutorial_files/tutorial_namd/alnamd_tutorial.zip>` including the Jupyter notebook:

.. raw:: html
   :file: tutorial_files/tutorial_namd/alnamd.html