1 Overview
This website serves as an introduction to the modelling challenge to estimate drought impacts on the light use efficiency of photosynthesis from multispectral remote sensing data. The modelling target are time series of the fractional reduction of the light use efficiency of photosynthesis, driven by soil moisture stress - termed fLUE. Time series are available from a set of sites and were generated by Stocker et al. (2018). The aim is to predict fLUE from multispectral remote sensing, paired with climate data and some limited site meta information.
The modelling challenge is devised as a competition where participants can submit their predictions of fLUE on a new set of sites that were not seen during model training. The submissions enter a leaderboard.
This modelling challenge and competition forms part of the course Applied Geodata Science 2, held at University of Bern (part of the Master programme in Geography and in Climate Sciences).
This modelling challenge (exercise) requires prior knowledge of programming in R, usage of git and Github, and a basis in supervised machine learning, covered in Chapters 10 and 11 of the free online book Applied Geodata Science.
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Original sources are attributed. Content without attribution is our own and shared under the license below. If there are any errors or any content you find concerning with regard to licensing or other, please contact us or report an issue. Any feedback, positive or negative, is welcome.
How to cite this book
No DOI available yet. Please cite website URL.
