Evaluation of geomorphological classification uncertainty using rough set theory: A case study of Shaanxi Province, China

Abstract

Geomorphological classification is affected by classification principles, indicators, methods, and data resolution, which can lead to uncertainty in the results. Such uncertainty directly affects the quality and subsequent applications of geomorphological classification. To quantify and control the uncertainty, it is important to select an appropriate and effective method for evaluating the uncertainty of geomorphological classification. This study evaluated the uncertainty of geomorphological classification of Shaanxi Province at the ground-feature class and image scales, which derived from rough set theory: rough entropy, approximate classification quality, and approximate classification accuracy. The three indicators helped effectively assess the uncertainty of geomorphological classification at multi-scale and measured the degree to which different factors affected the uncertainty of geomorphological classification. The relative impacts of three factors on the uncertainty of classification decreased in the order of classification methods, data resolution, and classification indicators. This finding is helpful to objectively evaluate and control the uncertainty generated in the process and results of geomorphological classification, and can provide targeted reference and guidance for future geomorphological classification work, which is more conducive to decision-making and application. At the same time, this study is also a beneficial supplement to the geomorphological research based on digital terrain analysis.