Graded Assignment: GI-Project
This worksheet introduces your GI-project which is focusing a research question based on the findings of the ungraded assignment reliable algorithm for tree delineation in the Marburg Open Forest (MOF)
The big picture
The whole project will be wrapped up in a paper that is comprising the methodology and interpretation of:
- Tree crown segmentation
- Forest structure and tree competition
- if enrolled (RS course) - Prediction of tree species
This cross-linking of the courses has an important implication on the planing of this project. One cannot specify the actual data set requirements at this stage and but one must iteratively adjust the requirements based on insights and knowledge gained in the parallel work. Hence, this dual project workflow acts quite similar to other knowledge gaps one might have at the beginning of a project, e.g related to computing images based on focal operations. Acting under uncertainty is a key competence on job and in science - just keep it in mind.
The Assignment
Please develop a project that at least uses the results and data from the course work (ungraded assignment) to answer a self-chosen (research) question.
This question can emphasize the methodological aspects or address an application-focused problem.
If enrolled in both courses, the remote results must be integrated.
Please consider the principles of transparency, reproducibility and communication mentioned in the basics. That is, the source code should be available on GitHub and the resulting article should follow the usual conventions of good scientific practice.
The graded course certificate will be an article following the type “Practical Tools” (but up to 3,000 words) of Methods in Ecology and Evolution that describes the project from its motivation and intention over the methods and results to the discussion of the final information.
There will only be one article for both courses (the remote sensing and the GIS course).
Even if pretty much more comprehensive The following publications can be used as inspiration for the article.
- Improved Classification of Urban Trees Using a Widespread Multi-Temporal Aerial Image Dataset
- Individual Tree Crown Delineation from UAS Imagery Based on Region Growing and Growth Space Considerations
- Quantifying Understory and Overstory Vegetation Cover Using UAV-Based RGB Imagery in Forest Plantation
Please note that it should be a short communication. The page number of your article should be clearly less than ten pages.
Further Notes
Please use the upcoming spotlight units as a sort of guideline and a source of inspiration for the compilation.