COURSE OVERVIEW - This course focuses on the use of BART (Bayesian Additive Regression Trees) for modelling species' geographical distributions based on occurrence data and environmental variables. BART is a relatively recent technique that shows very promising results in the field of species distribution and ecological niche modelling (SDM / ENM), as it produces accurate predictions (considering various aspects of model performance) without overfitting to noise or to special cases in the data. Additionally, BART allows mapping the uncertainty and credible intervals associated to each local prediction.
The course includes a combination of theoretical lectures and hands-on practicals in R, as well as open discussions about models and data for SDM applications. The practicals go through a complete worked example, from data preparation to model output analysis, with annotated R scripts that can be adapted on-the-spot by participants to work on their own species of interest. Along the course, the instructor is available for constant feedback and orientation on participants' outputs and interpretations.
Please email oliverhooker@prstatistics.com with any questions
Species Distribution Modelling With Bayesian Statistics Using R (SDMB05)
https://www.prstats.org/course/online-course-species-distribution-modelling-with-bayesian-statistics-using-r-sdmb05/
Delivered by Dr. Marcia Barbosa
21st - 23rd May 2024
Please feel free to share!
COURSE OVERVIEW - This course focuses on the use of BART (Bayesian Additive Regression Trees) for modelling species' geographical distributions based on occurrence data and environmental variables. BART is a relatively recent technique that shows very promising results in the field of species distribution and ecological niche modelling (SDM / ENM), as it produces accurate predictions (considering various aspects of model performance) without overfitting to noise or to special cases in the data. Additionally, BART allows mapping the uncertainty and credible intervals associated to each local prediction.
The course includes a combination of theoretical lectures and hands-on practicals in R, as well as open discussions about models and data for SDM applications. The practicals go through a complete worked example, from data preparation to model output analysis, with annotated R scripts that can be adapted on-the-spot by participants to work on their own species of interest. Along the course, the instructor is available for constant feedback and orientation on participants' outputs and interpretations.
Please email oliverhooker@prstatistics.com with any questions