Monday - Classes from 9:30 to 17:30

Ecological Niche Models: introduction to ENMs and main modelling work steps. We will discuss the main steps in ENMs (conceptualisation, data preparation, model fitting, model assessment, prediction)

Occurrence data: how to load your own data and how to import data from open access databases (such as GBIF). We will discuss here the different potential biases on the input data and how to address them.

Tuesday - Classes from 9:30 to 17:30

Environmental layers: how to use R as a GIS, how to extract climatic data from your occurrence points, etc.

Fitting Models: fit your first ENMs. We will start with a simple ENM technique to learn and understand the different modelling steps.

Model assessment and prediction: assess the goodness-of-fit as well as the predictive performance of ENMs. We will learn different validation approaches and performance measures, and make predictions in space and time.

Wednesday - Classes from 9:30 to 17:30

ENM algorithms: learn about available modelling techniques (distance methods, regressions, machine learning). We will learn about the different R packages to run those models, and their main differences.

Thursday - Classes from 9:30 to 17:30

Ensembles: combine different algorithms to ensemble predictions and quantify algorithmic uncertainty.

Program flow. Programming loops for working with large lists of species, models and climatic scenarios. When working in global change biology we need to automatize our scripts to make predictions over hundreds of species, trying several ENMs, and projecting the ENMs over different climatic scenarios (e.g. present and several future predictions). We will show you how you can write more efficient R-scripts for this.

Friday - Classes from 9:30 to 17:30

Student exercises. Students will present their case study (we encourage students to think about a hypothesis that they would like to test during this course in advance), their initial goals, the problems that they faced, and how they manage to solve them.