We are thrilled to announce the latest Mountain Legacy Project research article led by James Tricker: Assessing the accuracy of georeferenced landcover data derived from oblique imagery using machine learning.

Published in Remote Sensing in Ecology and Conservation, the article combines emerging machine learning technology with environmental inquiry.

“In this paper, we provide an overview of two new tools, an automated deep learning classifier and intuitive georeferencing tool, and describe how they are used to derive landcover data from 19 images associated with the Mountain Legacy Project, a research team that works with the world’s largest collection of systematic high-resolution historic mountain photographs. We then combined these data to produce a contemporary landcover map for a study area in Jasper National Park, Canada.”


Landcover maps produced for the Athabasca River valley study area. Left panel: 30 cm high-resolution aerial image. Middle panel: landcover map produced using oblique photographs (2 m resolution). Right panel: landcover map produced using orthogonal imagery (30 cm resolution). Map credit: ESRI. (2021) ArcGIS pro: release 2.8.3. Redlands, CA: Environmental Systems Research Institute.

You can read the full article here: https://zslpublications.onlinelibrary.wiley.com/…/rse2.379

A well deserved congratulations to you James, and to all involved.

Authors: James Tricker, Claire Wright, Spencer Rose, Jeanine Rhemtulla, Trevor Lantz, Eric Higgs