Establishing a common data base of ice experiments and using machine learning to understand and predict ice behavior

TL;DR

This paper creates a shared ice experiment database and applies machine learning to analyze how parameters like temperature affect ice behavior and peak stress.

Contribution

It introduces a standardized small-scale ice experiment database and demonstrates machine learning's use in understanding ice behavior.

Findings

Parameters like temperature significantly influence peak stress.

Machine learning models can predict ice behavior based on experimental data.

A common database facilitates future research in ice mechanics.

Abstract

Machine learning and statistical tools are applied to identify how parameters, such as temperature, influence peak stress and ice behavior. To enable the analysis, a common and small scale experimental data base is established.