Storms prediction : Logistic regression vs random forest for unbalanced data

TL;DR

This paper compares logistic regression and random forest classifiers on unbalanced satellite data for predicting convective cloud systems, crucial for thunderstorm warnings, highlighting their performance differences.

Contribution

It provides a comparative analysis of logistic regression and random forest methods on unbalanced meteorological data, illustrating their application and effectiveness.

Findings

Random forest outperforms logistic regression in unbalanced data scenarios.

Specific performance criteria are used to evaluate classifiers.

The case study demonstrates practical application in thunderstorm monitoring.

Abstract

The aim of this study is to compare two supervised classification methods on a crucial meteorological problem. The data consist of satellite measurements of cloud systems which are to be classified either in convective or non convective systems. Convective cloud systems correspond to lightning and detecting such systems is of main importance for thunderstorm monitoring and warning. Because the problem is highly unbalanced, we consider specific performance criteria and different strategies. This case study can be used in an advanced course of data mining in order to illustrate the use of logistic regression and random forest on a real data set with unbalanced classes.