Automated Remote Sensing of Underground Features
Below ground mapping can now better utilize remotely sensed data to create more accurate maps.
Below ground mapping can now better utilize remotely sensed data to create more accurate maps.
Machine learning techniques are being used to map new urban and land use patterns that were previously difficult to detect using crowdsourcing data.
One study recently looked at about 150,000 high resolution satellite images of cities in the United States along with census data of these areas in order to understand obesity rates in the built environment.
There are both challenges and opportunities that Artificial Intelligence (AI) has in applying geospatial and GIS knowledge that also addresses issues of time and spatial bias.
Image recognition software and algorithm development is likely to be increasingly applied with spatial applications.
Mapping flood damage by manually examine imagery is a time-intensive and expensive process. New, automated methods using satellite data that compare pre and post-flood conditions are being developed.