Spatial Cross-Validation of Species Distribution Models in R: Introducing the blockCV Package

Post provided by Roozbeh Valavi

این پست به فارسی موجود است

Modelling species distributions involves relating a set of species occurrences to relevant environmental variables. An important step in this process is assessing how good your model is at figuring out where your target species is. We generally do this by evaluating the predictions made for a set of locations that aren’t included in the model fitting process (the ‘testing points’).

Random splitting of the species occurrence data into training and testing points

Random splitting of the species occurrence data into training and testing points

The normal, practical advice people give about this suggests that, for reliable validation, the testing points should be independent of the points used to train the model. But, truly independent data are often not available. Instead, modellers usually split their data into a training set (for model fitting) and a testing set (for model validation), and this can be done to produce multiple splits (e.g. for cross-validation). The splitting is typically done randomly. So testing points sometimes end up located close to training points. You can see this in the figure to the right: the testing points are in red and training points are in blue. But, could this cause any problem? Continue reading

Issue 7.2: Demography Beyond the Population

Issue 7.2 is now online!

Sagebrush steppe in eastern Idaho, USA

© Brittany J. Teller

The February issue of Methods is now online! As you may have seen already, it includes the BES cross-journal Special Feature: “Demography Beyond the Population“. There are also eight other wonderful articles to read.

We have four articles in the Demography Beyond the Symposium Special Feature. You can read an overview of them by two of the Feature’s Guest Editor Sean McMahon and Jessica Metcalf here (Sean and Jessica are also Associate Editors of Methods).

If you’d like to find out more about each of the individual papers before downloading them, we have blog posts about each one. Daniel Falster and Rich Fitzjohn discuss the development of plant and provide some advice on creating simulation models in Key Technologies Used to Build the plant Package (and Maybe Soon Some Other Big Simulation Models in R). There is a look back at the evolution of Integral Projection Models from Mark Rees and Steve Ellner in How Did We Get Here From There? A Brief History of Evolving Integral Projection Models. In Inverse Modelling and IPMs: Estimating Processes from Incomplete Information Edgar González explains how you can estimate process that you can’t observe. And keep an eye out for Brittany Teller’s blog post coming next week!

Don’t wait too long to get the Demography Beyond the Population Special Feature papers though, they’re freely available for a limited time only

Continue reading