Algorithm Based on Grey Clustering and Shannon Entropy to Assess Landscape Visual Quality

Abstract

Landscape assessment has been limited to methodologies with subjective and qualitative approaches, due to prevailing the concept of landscape as the perception of territory. In this work, the intrinsic visual quality of the landscape was evaluated using an algorithm based on grey clustering and Shannon entropy. The grey clustering method was used to determine the landscape visual quality, and Shannon entropy was applied to calculate wights of criteria used for evaluation. The case study was performed on mining project located in Cajamarca, Peru, where three landscape units were identified and four evaluation criteria were established, before and after the implementation of project. The results revealed that there is a notable effect of the change in landscape visual quality in three evaluated landscapes units. The criteria in order of evaluation were the intrinsic visual quality of the water, relief, vegetation cover, and artificial elements. Consequently, the method showed quantitative and qualitative results that could help the landscape assessment process to make better decisions regarding mining projects. Keywords—Grey clustering, Landscape visual quality, Mining project, Shannon entropy.