Authors: JR Lee (Water Resources Research Center @ UH Mānoa), Prithviraj Pramanik (National Institute of Technology Durgapur, India / University of New South Wales), Veda Yakkali (Rutgers University), and Anastasiia Lehova (University of Hawaiʻi at Mānoa)
Across the United States and the world, the distributed network of Sage nodes captures over 2500 images per day. These nodes have the potential of capturing photos with important features such as smoke, wildlife, and emergencies. Each image contains unique characteristics which, until now, were hard to look for without manually searching through the Sage database. With both the images and users in mind, this project has two goals: harness the power of machine learning to describe photos as they are taken, and build a user-friendly system to allow others to find what they are looking for within our database.
Authors: Sajan Neupane (University of Utah) and Pratik Kharade (University of Utah – SCI Institute)
Authors: Di Fan (University of Florida), Levi Johnson (Colorado State University), John Blackwell (Colorado State University), and Atefeh Hosseini (University of Kansas)
LIDAR technology, with its ability to create detailed maps of atmospheric environments, can potentially solve the issue of blockers by providing precise information about the location and height of obstructions. It proposes many benefits that can’t be offered by a regular camera, especially the fact that it provides accurate data in all different types of weather conditions including fog, rain, and low light. This information can be used to adjust solar irradiance estimates and sky predictions, making them more accurate in any setting. Current models experience difficulties in the presense of blockers and unfamiliar sky conditions. We believe LiDAR can potentially solve this issue and allow us to deploy these nodes in urban areas.