BSc thesis “modeling species distribution in Kenya” finalised

BSc thesis “modeling species distribution in Kenya” finalised

October 20, 2014

Annika Rudolph a BSc student handed in her BSc thesis on species distribution modeling in Kenya using remote sensing data and the randomForest model. It is impressive what she achieved within 8 weeks without any prior R knowledge. All remote sensing data as well as statistical modeling were done in R, a lot of effort has also been put into the acquisition of relevant remote sensing imagery BSc_Rudolph_workflow.

 

In the passed decades global environmental changes such as climate and land-use changes and anthropogenic pressure increased. As a result the world’s biological diversity faces exceptional threat with following increasing rate of biodiversity loss. It becomes important to assess and
monitor actual or potential geographic distribution of species to prevent this ongoing loss. This has become an important component of conservation planning in recent years. A wide variety of modeling techniques have been developed for this purpose, such as remote sensing methods. These models ordinarily utilize associations between environmental variables and known species occurrence records to identify environmental conditions within which populations can be maintained. The spatial distribution of environments that are suitable for the species can then be estimated across a study region. In this study species distribution is estimated in Kenya using environmental variables derived
from remotely sensed data such as Moderate Resolution Imaging Spectroradiometer (MODIS). The focus of this work lies on the comparison between two approaches in terms of their appropriateness for predicting species distribution within the study area. The first approach
analyzes the species probability from statistics of all summed up species. The second approach examines species probability for each species and sums up statistics afterward. The results provide an overview of the predicted species probability in regard to their vicinity to Protected Areas.
For each approach the Pearson’s coefficient of correlation between observations and predictions (r2) and Receiver Operating Characteristics (ROC) is calculated. The results of the Random Forest algorithm reach a r2 of 0.49 for the first approach and 0.11 for the second approach. ROC is 0.88 for the first approach and 0.67 for the second approach. These results exhibit reasonable significance. This study showed that the predicted probability of species distribution is close to the actual probability for the first approach. The second approach is far from the actual probability.

you may also like:

🗺 Exploring Map Visualizations

🗺 Exploring Map Visualizations

Within our EAGLE courses our students have to learn a wide variety of skills - beside the fundamental earth observation theory and practice also skills like map creation is part of the curriculum. One of our students Ronja Seitz has created three visualizations guides...

Successful Completion of UNIversInternational Certificate

Successful Completion of UNIversInternational Certificate

In line with its internationalization strategy, the University of Würzburg supports administrative staff in their task of advising and supporting international students, guests, and academics. To this end, it has launched the "UNIversInternational" certificate...

The “Geolingual Studies” team visited the DLR EOC

The “Geolingual Studies” team visited the DLR EOC

The "Geolingual Studies" team of the University Würzburg visited the DLR-EOC on 3 and 4 July 2025. Geolingual Studies is an innovative area of research and teaching which takes a decisively applied linguistic approach and combines methodologies from linguistics,...

Course on Object-based image analysis

Course on Object-based image analysis

Dr. Michael Wurm from the German Aerospace Center (DLR) gave a class about Object-based image analysis (OBIA) using the eCognition Software for the EAGLE students. The course gives an insight into the theoretical basis of OBIA and using different datasets and tasks...