| Title | Mapping landslides on EO data: performance of deep learning models vs. traditional machine learning models |
| Publication Type | Journal Article |
| Year of Publication | 2020 |
| Authors | Prakash, Nikhil, Andrea Manconi, and Simon Loew |
| Secondary Title | Remote Sensing |
| Volume | 12 |
| Number | 3 |
| Pagination | p.346-370 |
| Call Number | OSU Libraries: Digital Open Access |
| Keywords | coastal hazards, geology, landslides, machine learning, map, mathematical modeling, neural networks, remote sensing, Smith River, Umpqua River |
| Notes | Contemporary science has revolutionized the mapping of landslides. Using Earth Observation images from satellites, researchers have access to high-resolution imagery. Much effort has gone into teaching computers how to “read” myriad images and identify features such as landslides. This article introduces a method for identifying landslides with computers and compares it to the Statewide Landslide Information Database for Oregon (SLIDO). The study area covers land from Coos Bay to Eugene, including much of the Smith River and the Lower Umpqua River. Illustrated. This is an open-access article. |
| URL | https://www.mdpi.com/2072-4292/12/3/346/pdf |
| DOI | 10.3390/rs12030346 |
| Series Title | Remote Sensing |
