.. _sphx_glr_examples_04_probabilistic_modeling: Probabilistic Modeling ====================== In the dynamic and often uncertain realm of subsurface exploration, probabilistic modeling emerges as a key tool. This section delves into the application of Bayesian Statistics and probabilistic approaches to address the inherent uncertainties in subsurface data. Here’s what you’ll learn: - **Embracing Uncertainty**: Gain an understanding of how to quantify and incorporate uncertainty in geological models. We focus on aleatoric uncertainty, which represents the inherent variability in subsurface data. - **Bayesian Methods with Pyro**: Discover how to apply Bayesian statistical methods using Pyro, a powerful probabilistic programming framework. These tutorials will guide you through the process of encoding uncertainty in your models, offering a robust way to handle complex geological data. - **Integrating Structural Uncertainty**: Learn to integrate structural uncertainty into your models using GemPy. This approach enhances the realism and reliability of your geological interpretations. - **Probabilistic Inversions**: Explore how geophysical data can be used as observational constraints in probabilistic inversions. This technique allows for a more comprehensive understanding of subsurface structures by incorporating both geophysical measurements and geological knowledge. .. raw:: html
.. raw:: html
.. only:: html .. image:: /examples/04_probabilistic_modeling/images/thumb/sphx_glr_01_thickness_problem_gempy_thumb.png :alt: :ref:`sphx_glr_examples_04_probabilistic_modeling_01_thickness_problem_gempy.py` .. raw:: html
2.2 - Including GemPy
.. raw:: html
.. only:: html .. image:: /examples/04_probabilistic_modeling/images/thumb/sphx_glr_02_model_1_bayesian_thumb.png :alt: :ref:`sphx_glr_examples_04_probabilistic_modeling_02_model_1_bayesian.py` .. raw:: html
Probabilistic Inversion Example: Geological Model
.. raw:: html
.. toctree:: :hidden: /examples/04_probabilistic_modeling/01_thickness_problem_gempy /examples/04_probabilistic_modeling/02_model_1_bayesian