https://github.com/blasbenito/spatialrf_talk

Talk about incorporating spatial autocorrelation into random forest models

https://github.com/blasbenito/spatialrf_talk

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: scholar.google
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (2.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Talk about incorporating spatial autocorrelation into random forest models

Basic Info
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created almost 5 years ago · Last pushed almost 5 years ago

https://github.com/BlasBenito/spatialRF_talk/blob/main/

# Autocorrelation in spatial regression with Machine Learning methods (with a focus on Random Forest)

Short talk for the workshop [**Hands on Machine Learning in Ecology**](http://ceaul.org/workshop-hands-on-machine-learning-in-ecology/) organized by [Marta M. Rufino](https://scholar.google.com/citations?user=ZMe-JxwAAAAJ&hl=es) (MARE, Faculty of Sciences, University of Lisbon) and [Tiago A. Marques](https://scholar.google.com/citations?user=SHqH7fMAAAAJ&hl=es) (University of St. Andrews). 

In this talk I focus on the nature and meaning of spatial autocorrelation, and describe how it can be incorporated into spatial regression models fitted with random forest models with the R package [spatialRF](https://blasbenito.github.io/spatialRF/).

[Link to slideshow](https://blasbenito.github.io/spatialRF_talk/talk.html#1)

Owner

  • Name: Blas Benito
  • Login: BlasBenito
  • Kind: user
  • Location: Somewhere in the beach

PhD in Quantitative Ecology, Master in Geographic Information Systems, R developer, data scientist and data engineer at @BiomeMakers.

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2