Skip to content

A two-part model (exponential regression + KNN) to predict the quantity of oil produced from wells in northern Colorado.

Notifications You must be signed in to change notification settings

JamesPImes/oil_well_predictor

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Oil Production Prediction Model

This model combines exponential regression with K-nearest neighbors to predict the quantity of oil production from wells drilled in an area of northern Colorado. Without access to proprietary geological data, it uses exclusively public data downloaded or scraped from Colorado's official ECMC website.

In the example below, the orange curve is an exponential regression that was trained on this well's own data (included for reference). The green curve is a composite of 8 other exponential regressions trained on nearby wells.

Demo Notebook

Check out this demo notebook to see how it works, including hyperparameter tuning.

About

A two-part model (exponential regression + KNN) to predict the quantity of oil produced from wells in northern Colorado.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages