Landscape mapping using remote sensing and neural networks

September 12th, 2018
The Science: 

Develop high-resolution maps of Arctic vegetation using machine learning and satellite imagery (e.g., NASA)

The Impact: 

Remote sensing products were combined and maps of vegetation distribution evaluated against field data for the Seward Peninsula

Summary: 

A convolutional neural network (CNN) approach produced highly accurate vegetation classifications. Hyper-spectral datasets (e.g., AVIRIS) were most useful for our machine learning approaches. Accurate and high-resolution datasets generated using our approach are needed for Arctic models.

A clustering-based stratification method previously used to map vegetation at NGEE Arctic field sites near Utqiaġvik, AK(Langford et al. 2016).

Contacts: 

Forrest Hoffman

Oak Ridge National Laboratory