Today, data and information play a significant role in bringing logical decision-making, intelligence and wisdom in society. In recent years, the “spatial character” of data and information is gaining prominence and greater significance.
Spatial data is generated in multitude of ways – through satellite measurements and imaging; through sensors on Unmanned Aerial Systems or aircrafts; embedded precise positioning using specialized hand-held devices; underground utilities data; indoor positions and mapping; mobile systems and Wi-Fi systems based on positions of transmitters; radio-frequency identification (RFID) using networks of fixed detectors/readers; laser imaging matched to 3D geometry and many, many more methods.
World over, society is generating, referencing, archiving and using vast amount of spatial data sets – of citizens, vehicles and automobiles, land, agriculture and crops, soils, cities, water systems, infrastructure, aviation and advanced transportation systems, environment, disasters, weather and many others.
Maps and images are used in day-to-day actions of searching points of interest, routing, districting, property assessment, taxation, deciding government spend and many other daily needs. Spatial datasets are also getting “time-stamped” – making them amenable to change detection and time-analysis.
Spatial Analytics (SA) is the logical processing of such spatial data and information entities using their topological, geometric, or geographic properties and is emerging at the forefront of advanced Geographical Information Systems (GIS) knowledge.
SA is also spurred by the increasing ability to capture and create geotagged data-rich environments. Combined with Internet-of-Things (IoT) and using Artificial Intelligence principles, SA is charting the future of geographical data processing in the Big-Data and Cloud environment.
Using advanced computational analysis, SA helps determine intrinsic geographic patterns – patterns of commonality, optimality, suitability, predictability etc and adopts advanced modeling and heuristics of self-learning principles for processing spatial datasets. SA helps definitions of “where”; metrics of distances/area/shape/ proximity/nearness etc; relationships between data by similarity; siting and locating analysis; spatial econometrics; aviation analytics; Spatial Decision Support Systems (SDSS) and simulations using interpolation methods.
All of the characters of SA are oriented to “find patterns” and “newer meaning” and for predicting a FUTURE trend. SA can unravel hidden meanings and new perspectives in data – hitherto un-available in spatial domain.