Land cover change often times happens gradually over time, and land cover fraction mapping and updating aims to express this change in a more precise way compared to conventional discrete mapping. Such land cover fraction and change information is useful for many applications, such as climate predictions and SDG monitoring, which require reliable information on land cover and its change.
Land cover can be expressed as fractions of each land cover class (e.g. grassland, shrubs, water) in each pixel. Likewise, land cover change can be expressed as the change in land cover fractions over time. However, monitoring land cover change correctly is challenging, since small changes in model inputs can lead to false indications of change. It is also challenging to visualise such changes, since there are many possibilities for classes to shift from one class to another, also gradually over an extended period of time. How gradual changes translate to changes in fractions has not been studied extensively so far.
In this thesis, the student will examine the potential of applying techniques to make land cover change more robust (e.g. by employing Markov Random Fields adapted to regression output) and fuzzy land cover change visualisation techniques (e.g. RGB change maps and change vectors) in a case study area of the student’s choosing, potentially in Africa.
- Derive yearly land cover fractions from satellite imagery
- Reduce reported spurious change with a post-processing technique
- Investigate ways to visualise gradual changes in land cover over time
- Hengl, T., Walvoort, D. J. J., Brown, A., & Rossiter, D. G. (2004). A double continuous approach to visualization and analysis of categorical maps. International Journal of Geographical Information Science, 18(2), 183–202.
- Ahmed, B., Ahmed, R., & Zhu, X. (2013). Evaluation of Model Validation Techniques in Land Cover Dynamics. ISPRS International Journal of Geo-Information, 2(3), 577–597.
- Leinenkugel, P., Wolters, M. L., Kuenzer, C., Oppelt, N., & Dech, S. (2014). Sensitivity analysis for predicting continuous fields of tree-cover and fractional land-cover distributions in cloud-prone areas. International Journal of Remote Sensing, 35(8), 2799–2821.
Theme(s): Modelling & visualisation, Integrated Land Monitoring