About us

In the past few years, we developed a number of methods to support the application of machine learning for spatial data. These methods are implemented in the R package CAST. From March 11th to 13th, our development team of the R package gathered together to implement and document new functionalities. The results:

• A Preprint describing our package: https://arxiv.org/abs/2404.06978v1
• Publication of the Package Version CAST 1.0.0 on CRAN: https://CRAN.R-project.org/package=CAST
• New and re-worked Software Tutorials: https://hannameyer.github.io/CAST/

Hanna gave an interview in the Podcast of the "Zentrum verantwortungsbewusste Digitalisierung" (ZEVEDI) in March 2023 about AI in environmental remote sensing. Listen to the Interview here.

Our master student Candy Fahrenholz was working in the Kuzikus Wildlife Reserve in Namibia as part of her master thesis. One focus of her research was to survey the small-scale landscape structures using drone-based remote sensing. With the help of this high-resolution image data, the research question "Which environmental parameters affect nest tree selection of endangered vulture species in Namibia?" will be answered.

Marvin Ludwig successfully defended his dissertation on 10.02.2023 and was awarded a doctorate in natural sciences. The title of the thesis is: „Remote sensing and machine learning for multi-scale ecosystem monitoring”. Congratulations from your working group!

Global-scale maps of the environment are an important source of information for researchers and decision makers. Often, these maps are created by training machine learning algorithms on field-sampled reference data using remote sensing information as predictors. Since field samples are often sparse and clustered in geographic space, model prediction requires a transfer of the trained model to regions where no reference data are available. However, recent studies question the feasibility of predictions far beyond the location of training data. Here, we propose a novel workflow for spatial predictive mapping that leverages recent developments in this field and combines them in innovative ways with the aim of improved model transferability and performance assessment. We demonstrate, evaluate and discuss the workflow with data from recently published global environmental maps. The publication can be found here: Ludwig, M., Moreno-Martinez, A., Hölzel, N., Pebesma, E., Meyer, H. (2023): Assessing and improving the transferability of current global spatial prediction models. Global Ecology and Biogeography.