Mapping coastal forest retreat using convolutional neural networks and different satellite imagery
Titilayo T Tajudeen, Marcelo Ardon, Mirela Tulbure, Katherine L Martin · 2026
Read Mapping coastal forest retreat using convolutional neural networks and different satellite imagery by Titilayo T Tajudeen, Marcelo Ardon, Mirela Tulbure, Katherine L Martin (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0357346.txt.
Description
Titilayo T Tajudeen led a team of four authors mapping retreating coastal forests, published in PLOS ONE in 2026. Coastal forests are shrinking under pressure from storms, sea level rise, and land clearing. Satellites can track that retreat, but reading their images by hand is slow. The team applied convolutional neural networks to different kinds of satellite imagery.
Tajudeen's AI-generated maps give conservationists the retreat's true extent, free from guesswork. Comparing imagery types shows which source gives the most reliable map for the least cost. Coastal forests protect shorelines and store carbon, so their loss is a double blow. Timely maps let agencies target planting and protection where retreat is fastest, and prove losses that ground surveys would miss.
Catalog record
| CREATOR | Titilayo T Tajudeen, Marcelo Ardon, Mirela Tulbure, Katherine L Martin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68239 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |