HUANG Bo1, WU Bo1, LIU Biao2, et al. Spatial Intelligence:Advancement of Geographic Information Science[J]. Journal of Remote Sensing, 2008, (5): 766-771. DOI: 10.11834/jrs.200805100.
Spatial Intelligence:Advancement of Geographic Information Science
Notwithstanding the astounding growth achieved by Geographic Information Systems(GIS) in recent decades
some critical bottlenecks still continue to pose challenges to the advancement of this technology.The inability to handle large and diverse datasets and the lack of functionalities to solve complex spatial problems such as combinatorial location problems is essential one among these hurdles.Recent advances in Computational Intelligence(CI) and Operations Research have
however
opened up new avenues to overcome these obstacles to the development of GIScience.Judicious integration of the aforementioned techniques into GIScience could possibly lead to an innovative discipline
namely spatial intelligence.This paper presents our preliminary investigation on this subject
including its framework
major acquisition methods
and sample applications.The basic concept of spatial intelligence derived from psychology refers to the mental process associated with the brain’s attempts to interpret certain types of information received.This information basically includes any kind of mental input
such as visual pictures
maps
and plans.Based on this concept
we propose that the introduction of spatial intelligence within the domain of GIScience is an ability to discover and apply spatial patterns
which is usually elicited through analysis/mining
optimization
and simulation.Two characteristics of spatial intelligence are highlighted here.One is the ability of spatial cognition
and the other is the self learning capability.Spatial cognition refers to the process of recognizing
encoding
saving
expressing
decomposing
constructing and generalizing spatial objects
which can be obtained from spatial observation
spatial perception
spatial indexing
and spatial deductive inference.Self learning includes enforcing learning
adaptive learning
and knowledge acquiring abilities to actively dig up knowledge from observation data.Promoting spatial intelligence is a logical requirement for higher level analysis and application of GIScience.Through active learning and searching process in complex spatiotemporal data
we emphasize the use of meta-heuristic and other intelligent algorithms to address complex geospatial problems.A three-tiered structure is proposed for the spatial intelligence framework.At the bottom of the framework
spatial statistics
programming
and intelligence computation are used to provide the foundation of spatial analysis
simulation
and optimization.The middle level consists of spatial intelligence
self learning
and spatial cognition for analyzing
simulating
interpreting
and decision making for geospatial processes and phenomena.At the top of the framework
GIScience laws and regularities are used to mine unknown patterns.To realize the goal of spatial intelligence
a solid research that integrates key topics with the concepts and modeling approaches derived from Information Science and Operations Research to advance GIS theories have been developed.The core supporting methods and techniques pertinent to the proposed framework include spatial analysis
simulation
and optimization.The development of spatial analytical models to represent spatial and temporal features and their relationships forms a vital aspect of this research.Spatial optimization is employed to maximize or minimize a planning objective
given the limited area
finite resources
and spatial relationships for a location-specific problem
once spatiotemporal patterns have been discovered.Simulation is an important tool to evaluate and improve models and spatial patterns.Some successful applications of spatial analysis
optimization
and simulation are also reported in this paper.Logistic regression models
e.g.
binomial
multinomial
and Nested Logit
are applied and examined to predict various spatiotemporal changes
including rural to commercial
rural to recreational
and rural to other land uses.A range of heuristic algorithms
such as Genetic Algorithms(GA) and Ant Colony Systems(Ant)
to troubleshoot complex routing and location problems
and multi-objective optimization for spatial decision making are studied.A case study of integrating agent-based modeling with analytical models by drawing upon microscopic traffic simulations for emulating real-time traffic conditions is also conducted.