首页 > , Vol. , Issue () : -
Currently, remote sensing technology has realized the acquisition of big data for full coverage image recording (space), rapid information updating (time) and multiple measure collaborative observation (attribute) on the earth surface. Meanwhile, the gap between remote sensing data and geographic information and knowledge is becoming increasingly prominent. Granular computing with data granulation as the basic is a frontier direction in the field of big data processing, which simulates human thinking and solves large-scale complex problems. It helps to improve the accuracy and efficiency of pattern mining and knowledge discovery by means of structure and association. According to the evolution route from "visual understanding of external scene" to "relationship perspective of internal generation mechanism (spectrum analysis)", this paper analyzes the granular structure of remote sensing big data and its multi-level and multi-granularity characteristics from three dimensions of space, time and attribute. In addition, we built a methodology of remote sensing granular computing based on geo-parcels, which integrates the basic models of "zonal-stratified perception, spatiotemporal collaborative inversion, and multi-granularity decision making". The case for precision agriculture application shows that granular computing meets the needs of remote sensing big data intelligent computing from multiple perspectives. It is verified that the theory and method proposed in this paper can realize orderly deconstruction and step-by-step solution for the multi-level complex problems of agricultural remote sensing. The case study also demonstrates its potential ability to help domain precision application.