The EPOS AI Platform is a versatile solution that simplifies the technological barriers for utilizing and creating Machine Learning applications in the field of Seismology. It streamlines the process of applying artificial intelligence algorithms in research projects by enabling the execution of pre-trained models. Additionally, it provides the capability to retrain these models with custom, including private, datasets. Researchers can conduct training experiments and easily compare them with prior results, facilitating the optimization of methods to identify the most effective model. Furthermore, the platform supports the development of new models, and extensions to existing ones.

The EPOS AI Platform facilitates the sharing of results with close collaborators. The libraries utilized to construct the tools and create example solutions are de facto standards within the research community. This makes it possible not only to share the outcomes but also the models themselves.

These features were developed within EPOS PL+, Polish national project co-financed from European Regional Development Fund.

Contents of this guide

This guide will introduce you to creating and managing your own AI models with the EPOS AI platform. You will learn how to store and evaluate your models in the EPOS AI Workbench as well as how to train them using computing infrastructure and, ultimately, how to publish it and use as a Custom Application of the EPISODES Platform. All these steps are further described on the subsequent pages of this documentation.

Entry-level AI Solutions

A straightforward approach to incorporating AI into your research is to employ pre-existing AI models and software to execute particular tasks:

Advanced AI Use Cases

A more advanced route involves the retraining of existing AI models or even the conception and development of customized models and software from the ground up:


The development of the EPOS AI platform and its integration with the EPISODES Platform was partially funded by the EPOS-PL+ project (No POIR.04.02.00-00-C005/19-00), co-financed by the European Union from the funds of the European Regional Development Fund (ERDF).

We want to express our appreciation for the excellent efforts of the Seisbench developers, and we strongly advise citing their publication:

Woollam, J., Münchmeyer, J., Tilmann, F., Rietbrock, A., Lange, D., Bornstein, T., Diehl, T., Giuchi, C., Haslinger, F., Jozinović, D., Michelini, A., Saul, J., & Soto, H. (2022). SeisBench - A Toolbox for Machine Learning in Seismology. in Seismological Research Letters

We express our gratitude to Weights & Biases for generously granting us an academic license of their web platform service.

  • No labels