Student information

MSc thesis subject: Understanding the impact of reference datasets on land cover mapping

Land cover and land use mapping is one of the most common applications of remote sensing datasets. Such maps are also essential for policymaking and policy implementation including the implementation of sustainable development goals.

Thanks to the broad availability of remote sensing imageries and advancements in the cloud computing such as Google Earth Engine, there has been a proliferation of remote sensing-based land cover mapping efforts. One example is the sentinel based 10m global land cover map produced by Tsinghua University (Gong et al. 2019). While such developments improve the mapping quality and are useful to map users, they also bring uncertainty in choosing best maps for a particular application. This is due to the disagreements in the land cover mapping by different products (Pflugmacher et al. 2011). Even when the used remote sensing imagery is the same, the mapped land cover can be quite different. For example LC map of Africa at 20m resolution using Sentinel and Sentinel based 10m resolution map of Gong et al. (2019). Next to the satellite data, another important data source for land cover mapping is the training or calibration data set. The impact of training datasets on the resulting land cover map is less understood and often overseen. This issue is to be addressed in this thesis research.

Objectives

  • Generating land cover maps using different set of training / calibration datasets
  • Assessing source of uncertainties in land cover classification
  • Assessing the impact of different training / calibration datasets on land cover mapping

Literature

  • Gong, P., Liu, H., Zhang, M., Li, C., Wang, J., Huang, H., Clinton, N., Ji, L., Li, W., Bai, Y., Chen, B., Xu, B., Zhu, Z., Yuan, C., Ping Suen, H., Guo, J., Xu, N., Li, W., Zhao, Y., Yang, J., Yu, C., Wang, X., Fu, H., Yu, L., Dronova, I., Hui, F., Cheng, X., Shi, X., Xiao, F., Liu, Q., & Song, L. (2019). Stable classification with limited sample: transferring a 30-m resolution sample set collected in 2015 to mapping 10-m resolution global land cover in 2017. Science Bulletin, 64, 370-373
  • Pflugmacher, D., Krankina, O.N., Cohen, W.B., Friedl, M.A., Sulla-Menashe, D., Kennedy, R.E., Nelson, P., Loboda, T.V., Kuemmerle, T., Dyukarev, E., Elsakov, V., & Kharuk, V.I. (2011). Comparison and assessment of coarse resolution land cover maps for Northern Eurasia. Remote Sensing of Environment, 115, 3539-3553
  • Xiao Zhang, Liangyun Liu, Xidong Chen, Shuai Xie and Yuan Gao (2019). Fine Land-Cover Mapping in China Using Landsat Datacube and an Operational SPECLib-Based Approach. Remote Sensing, Volume 11, Issue 9.

Requirements

  • Advanced remote sensing

Theme(s): Integrated Land Monitoring