Using Deep Learning for Land Classification and Change Detection within the Konza Prairie, 1985-2011

Authors: Caitlin Alyssa Sliva*, University of Missouri, Clayton F. Blodgett, University of Missouri
Topics: Remote Sensing
Keywords: Deep Learning, Remote Sensing, Konza Prairie, Land Classification, Change Detection
Session Type: Virtual Paper
Day: 4/8/2021
Start / End Time: 1:30 PM / 2:45 PM
Room: Virtual 13
Presentation File: No File Uploaded


Machine learning has been around for decades, but deep learning is the new focus of study within machine learning. The goals of implementing deep learning into remote sensing are resulting in much faster and accurate results for much larger amounts of data. The field of remote sensing has focused on increasing the accuracy of land classification and change detection. A possible solution for increasing accuracy is the use of a deep learning network that have been producing greater accuracy in image classifying and change detection. This study focuses on classification and change detection within the Konza Prairie in Geary County, Kansas. The images are from Landsat 4 and 5 spanning the years 1985-2011 and are trained and tested through a deep learning network. The experimental results show the possibility of a deep learning network producing results that could then be implement for much larger regions.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login