Persistent Homology to Study Cold Hardiness of Grape Cultivars

TL;DR

This paper introduces an unsupervised method using persistent homology to analyze agricultural point cloud data, revealing divergent behaviors and seasonal patterns in grape cultivars' cold hardiness over multiple years.

Contribution

It presents a novel application of persistent homology to study plant cold hardiness, providing insights into cultivar behavior and seasonal effects from complex data.

Findings

Persistent homology effectively distinguishes cultivar behaviors.

The method identifies cultivars with variable seasonal responses.

Seasonal correlations in cold hardiness are detected.

Abstract

Persistent homology is a branch of computational algebraic topology that studies shapes and extracts features over multiple scales. In this paper, we present an unsupervised approach that uses persistent homology to study divergent behavior in agricultural point cloud data. More specifically, we build persistence diagrams from multidimensional point clouds, and use those diagrams as the basis to compare and contrast different subgroups of the population. We apply the framework to study the cold hardiness behavior of 5 leading grape cultivars, with real data from over 20 growing seasons. Our results demonstrate that persistent homology is able to effectively elucidate divergent behavior among the different cultivars; identify cultivars that exhibit variable behavior across seasons; and identify seasonal correlations.