Dr Mitchell Lyons

Role: Research Fellow | Lecturer

Bio: I am a postdoc in the Centre for Ecosystem Science, and my research can be described as a mixture of Ecology, Geography and Statistics. I finished my PhD in 2013, at the University of Queensland, which focused on developing new remote sensing methods for long term monitoring and change detection in terrestrial and marine ecosystems. After this I focused on automated monitoring of seagrass environments using remote sensing and autonomous underwater vehicles (AUVs). On moving to the University of New South Wales, I shifted focus to application of modern statistical and modelling approaches for large scale vegetation classification and mapping problems, with a side interest in drone-acquired image data. I also teach remote sensing in some of the courses in the School of Biological, Earth and Environmental Sciences, as well as programming and statistics in various short courses and workshops (http://environmentalcomputing.net/). I am part-time at UNSW, and in my other part, I work primarily on a project at the University of Queensland - the Allen Coral Atlas - where I helped build the cloud-based mapping framework for mapping every coral reef in the world at high resolution.

Technically speaking, my expertise lies in remote sensing and ecological modelling (statistics and machine learning), and I generally take a computational programming (R and Python specifically, and JavaScript on the Google Earth Engine) approach. Non-technically speaking, two young kids and a small farm take up most of my time, and if there's any left over I love getting into the river or the ocean.

Research field keywords: ecology, remote sensing and GIS, ecological modelling, vegetation science, statistical ecology

Publications: see my Google Scholar profile (http://scholar.google.com.au/citations?user=9PnIKHYAAAAJ), and please contact me if you would like a copy of any of my papers.

Code + software: see my github page (https://github.com/mitchest/), and check out my R packages/tool if you are so inclined:

optimus - model-based clustering diagnostics - https://cran.r-project.org/web/packages/optimus/index.html

c2c - comparing classification and clustering solutions to eachother - https://cran.r-project.org/web/packages/c2c/index.html

online quantatative vegetation classificaiton tool -  https://mitchest.shinyapps.io/vegplot/

email: mitchell.lyons@unsw.edu.au | location: level 5, E26 (biological sciences south) | twitter: @mitchest