Effects of Sampling Methods on Prediction Quality. The Case of Classifying Land Cover Using Decision Trees

TL;DR

This study investigates how different sampling methods affect the accuracy of classifying land cover from airborne laser scanning data using decision trees, providing insights for optimizing sampling strategies in remote sensing.

Contribution

It introduces an analysis of various sampling techniques' impact on classification accuracy in remote sensing using CARTs, with empirical results from a large survey area.

Findings

Sampling methods significantly influence classification accuracy.

Optimal sample sizes depend on the specific sampling technique.

Results guide better sampling design for remote sensing classification.

Abstract

Clever sampling methods can be used to improve the handling of big data and increase its usefulness. The subject of this study is remote sensing, specifically airborne laser scanning point clouds representing different classes of ground cover. The aim is to derive a supervised learning model for the classification using CARTs. In order to measure the effect of different sampling methods on the classification accuracy, various experiments with varying types of sampling methods, sample sizes, and accuracy metrics have been designed. Numerical results for a subset of a large surveying project covering the lower Rhine area in Germany are shown. General conclusions regarding sampling design are drawn and presented.