artificial intelligence Archives

Example results on synthesizing photos from Google Maps at 512x512 resolution using Generative Adversarial Networks (GANs). Source: Isola, Zhu, Zhou, & Efros, 2018, CC BY 4.0 https://arxiv.org/abs/1611.07004

Converting Historical Maps to Satellite-Like Imagery

November 2, 2020 by Mark Altaweel

Old maps and images can now be converted to make them similar to our modern satellite-base views, giving stylized views a more realistic appearance.

Screenshot from the Forest Observatory site.

Mapping Every Tree

November 2, 2020September 22, 2020 by Mark Altaweel

The California Forest Observatory, created by Salo Sciences, has applied a new artificial intelligence tool that maps every tree in California.

When AI Goes Wrong in Spatial Reasoning

November 15, 2020December 14, 2018 by Mark Altaweel

Machines can learn ‘wrong’ or biased information, creating large problems and poor conclusions when it comes to spatial data.

Geospatial Artificial Intelligence: Emerging Trends and Challenges

July 9, 2018July 9, 2018 by Mark Altaweel

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.

Researchers are Using Machine Learning to Better Predict Weather Patterns

August 24, 2017 by Caitlin Dempsey

The enormous amount of data from Earth-observing satellites is pushing researchers to use machine learning to mine the information and improve climate models.

Using Visual Search to Find Geographically Similar Features on Satellite Imagery

March 19, 2017March 7, 2017 by Caitlin Dempsey

Descartes Labs recently unveiled its GeoVisual Search application which uses machine learning to visually search satellite imagery for similar geographic features.

Flood susceptibility map from Tehran et al., 2015.

GIS and Innovations in Machine Learning

December 19, 2016November 9, 2016 by Mark Altaweel

Machine learning or artificial techniques has been rapidly transforming many areas related to GIS and spatial applications

The examples on the left are the query photos. In response, PlaNet will output a probability distribution on the map. In these three examples, the Eiffel Tower (a) is confidently assigned to Paris, the model believes that the fjord photo (b) could have been taken in either New Zealand or Norway. For the beach photo (c), PlaNet assigns the highest probability to southern California (correct), but some probability mass is also assigned to places with similar beaches, like Mexico and the Mediterranean. The authors use a model with a much lower spatial resolution than the full model for visualization purposes. Source: Weyand, Kostrikov, & Philbin, 2016.

Google’s PlaNet: Geolocating Photos Using Artificial Intelligence

December 19, 2016March 11, 2016 by A.J. Rohn

Google and researchers at the RheinischWestfälische Technische Hochschule Aachen University have developed an artificial intelligence system capable of identifying locations more consistently accurately than a human is able to do.

Dense settlements (left) can take advantage of short-range wireless hotspots. Sparse settlements (right) require long-range cellular technology. Images: Digitalglobe.

GIS and Artificial Intelligence Used to Build Facebook’s World Population Map

December 19, 2016March 1, 2016 by Troy Lambert

Facebook has used a combination of existing GIS data, high resolution imagery, and artificial intelligence to develop a detailed population map of the world.

Orbital Insight uses shadows detected on satellite imagery to track construction rates in Nanjing, China.

Orbital Insight Exemplifies How Artificial Intelligence (AI) Can Be Used to Study Images from Space

December 18, 2016October 20, 2015 by Zachary Romano

Orbital Insights has developed a “deep learning” processes which uses artificial intelligence to pull data from satellite imagery.