Mapping Forest Burn Extent from Hyperspatial Imagery Using Machine Learning

Support vector machines are shown to be highly effective in mapping burn extent from hyperspatial imagery in grasslands. Unfortunately, this pixel-based method is hampered in forested environments that have experienced low-intensity fires because unburned tree crowns obstruct the view of the surface...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Dale Hamilton, Kamden Brothers, Cole McCall, Bryn Gautier, Tyler Shea
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2021-09-01
Serija:	Remote Sensing
Teme:	mask region-based convolutional neural network support vector machine small unmanned aircraft system wildland fire burn extent hyperspatial imagery
Online dostop:	https://www.mdpi.com/2072-4292/13/19/3843
Oznake:	Označite Brez oznak, prvi označite!