By Mech Frazier, Geographic Information Systems (GIS) Specialist, Northwestern University Libraries The boom of Artificial Intelligence (AI) in recent years has made a significant impact on Geographic Information Systems (GIS), including applications of Deep Learning (DL). Applications of DL have revolutionized GIS tasks, such as detecting sensitive mangrove environments 1 , identifying global building footprints 2 , and even locating beaver complexes in complex forest landscapes 3 . DL, a subset of Machine Learning (ML), uses neural networks to detect objects, classify pixels, and perform segmentation 4 . Recent advancements in DL have led to significant improvements in both model quality and usability, with prebuilt models and tools that simplify workflows. GIS applications like ArcGIS Pro and QGIS have made available tools and plug-ins to streamline the process of DL. This blog post will focus on one aspect of DL: object detection using aerial image...
Jose Anza Garcia and Milan Budhathoki, GIS and Data Service Center , University of Maryland Libraries At the University of Maryland's McKeldin Library, we are proud and fortunate to possess a map collection featuring over 200,000 items. It spans a wide degree of subject categories (topographic, nautical, aeronautical, etc.) and formats (print maps, atlases, raised relief models, etc.). In addition, through the library's designation as a Regional Depository Library by the Federal Depository Library Program, the map collection also holds countless government-produced documents of important historical and cultural value. A top-down map of the library's 4th floor, which houses the map collection (red square). Examples of different storage furniture items: at left, cabinets, and at right, atlas bookcases. However, the sheer size and scope of the map collection mean that a comprehensive catalog of all its contents does not exist at this time, making it hard for the library's...