Post

Statistical & Predictive Analysis of Lake Ice Cover Data

A Python-based project that compares algorithm performance and models historical ice cover on Lake Mendota & Lake Monona.

Posted Updated
By Shawn Kim
1 min read
Statistical & Predictive Analysis of Lake Ice Cover Data

Summary

It includes:

  • Paired t-tests and 95% confidence intervals for algorithm F1-score comparison

  • Bootstrapping procedures to generate robust performance intervals

  • Time-series exploration and visualization of annual ice-on/off dates

  • Linear regression modeling (train/test split, MSE evaluation) to quantify long-term trends

  • Maximum likelihood estimation under a Laplace noise model for parameter inference

Relevant Coursework, Intro to Machine Learning (CSC 480)
ml/ai python
This post is licensed under CC BY 4.0 by the author.