Exploring the Application of Particle Swarm Optimization in Vegetation Remote Sensing

Abstract

Particle swarm optimization (PSO) is an algorithm belonging to the family of swarm intelligence and metaheuristics, designed to solve optimization problems. It is a nature inspired algorithm. Specifically, PSO mimics the collective behaviour of fish and birds. These organisms are simple organisms that achieved complex tasks through information sharing and learning from experience. The collective and cognitive behaviours are imitated in PSO using only two simple mathematical equations. Owing to the simplicity of the algorithm, PSO had been widely applied to various real-world problems. Despite its simplicity PSO reported a good performance. This study aims to examine the application of PSO in the field of remote sensing focusing on vegetation. Vegetation remote sensing focusses on vegetation data from satellite. This data is used for monitoring and managing agriculture, forestry, environmental condition, and land usage. The findings show that PSO has been popularly used by researchers in vegetation remote sensing field. The applications cover multiple areas; nonetheless, the topic remains relevant, and further research opportunities can be explored.