Skip to content

Add regression module. - #114

Open
alarshi wants to merge 3 commits into
geodynamics:mainfrom
alarshi:add_regression_module
Open

alarshi wants to merge 3 commits into
geodynamics:mainfrom
alarshi:add_regression_module

Conversation

@alarshi

@alarshi alarshi commented Sep 28, 2026

Copy link
Copy Markdown
Collaborator

I want to test how notebooks appear on github PR. This PR addresses the suggestions from our drive.

@alarshi
alarshi force-pushed the add_regression_module branch from 380a21b to 8579d10 Compare September 28, 2026 20:38
@alarshi
alarshi force-pushed the add_regression_module branch from e9863d1 to fc82c6a Compare November 6, 2026 17:40

@JarettBakerDunn JarettBakerDunn left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just marked some typos.

"id": "JbLPlzz2puKy"
},
"source": [
"The fitted b-value, 0.79, deviates fom the typical b-value of 1 for most tectonic regions. This is because the catalog is not complete for lower magnitudes, and the limited number of large-magnitude earthquakes in the time period considered. We remove these outliers and fit the G-R law again in the next exercise."

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"deviates fom" -> "deviates from"

"\n",
"- **Bias** is error from a model that is *too simple* to capture the true pattern. For example, a degree 1 polynomial (a straight line) in our case would not be able to capture the velocity-depth curve observed in the data, leading to high bias. A model with high bias underfits even with more data because the model is not flexible enough to capture the underlying relationship.\n",
"\n",
"- **Variance** is error from a model that is *too complex* and specific to the training data. For example, a degree-15 polynomial would not only fit the velocity-depth relationship, but also the the noise that may be specific only to the training dataset. Such a model would likely perform poorly on new, unseen data because it has learned the noise in the training set rather than the underlying relationship. A model with high variance overfits the training data and does not generalize well."

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

the the noise -> the noise

"#### References\n",
"\n",
"- Wang, S. Y., & Wang, H. Y. (2016). Site-dependent shear-wave velocity equations versus depth in California and Japan. Soil Dynamics and Earthquake Engineering, [88, 8-14](https://www.sciencedirect.com/science/article/pii/S0267726116300367).\n",
"- Data availble by 2013 SEG Advanced Modeling Corporation, SEAM Open Data and downloaded from [SEG open data sets](https://wiki.seg.org/wiki/SEAM_Phase_I:_Interpretation_challenge_I_-_Depth)"

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

availble -> available

"id": "ZExRIpWJorUj"
},
"source": [
"> From the figure above, you can see that the polynomial deviates the most at the sharp seismic discontinuities, as it is smooth representation of the data. To overcome this, we can use piecewise polynomial regression, which fits separate polynomials to different segments of the data. This allows for better modeling of abrupt changes in the relationship between depth and seismic velocity."

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

as it is smooth representation -> as it is a smooth representation ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants