Geospatial Big Data

Geospatial Big Data

Geospatial Big Data are becoming more prevalent as data collection methods can collect data on the sub time frames such as seconds, minutes, days, and weeks, over a long time, now nearing 30+ years, since the start of the internet era and before for some datasets. However, there are additional hurdles to understanding big data including where to find it and how to display it effectively for users.

Raster Data

Big raster datasets are becoming more prevalent through data collection methods such as Unmanned Aerial Vehicles (drones), satellites, VGI images collected through apps and social media.

Points, lines, polygons

Points, lines, polygons, and other vector data are becoming more prevalent as artificial intelligence and machine learning is automating the process of converting raster images to vector images. AI/ML has the ability to automatically identify street sign, road ways, rivers, buildings, among others and automatically digitize them; a process that historically would have taken 10s-100s of hours.

Additionally, smart phone data collection can submit points such as locations of transportation issues, field surveys, trail maintenance, buildings, and many more, all over the world, leading to hundreds and thousands of potential vector points every day.

Although many more examples of big vector data exist, a last example is geotagged social media posts, which can be extracted using AI/ML to provide innumerable amounts of data including collective emotional responses, human migration, updates on wartime and locational events, among others.