Implementing image processing workflows
Research
My research contributes to the implementation of innovative and effective remote sensing workflows to address real-world application challenges. A specific focus is on the integration of sophisticated model training strategies and powerful machine learning methods into big data workflows. Enhancing the transferability and generalization capabilities of such workflows across space, time, and/or sensors constitutes an important step toward their operational implementation.
The development of a machine learning unmixing method based on synthetic training data from spectral databases represents one of my key achievements. The approach has become a core method in several research projects and publications. The approach is implemented in the πEnMAP-Box and documented for πE-Learning purposes. The functionality is also available in the python package πHUB-Workflow and integrated into the πFORCE processing engine.
Selected publications
Okujeni, A., Kowalski, K., LewiΕska, K.E., Schneidereit, S., & Hostert, P. (2024). Multidecadal grassland fractional cover time series retrieval for Germany from the Landsat and Sentinel-2 archives. Remote Sensing of Environment, 302, 113980. https://doi.org/10.1016/j.rse.2023.113980
Kowalski, K., Okujeni, A., & Hostert, P. (2023). A generalized framework for drought monitoring across Central European grassland gradients with Sentinel-2 time series. Remote Sensing of Environment 286, 113449. https://doi.org/10.1016/j.rse.2022.113449
Okujeni, A., van der Linden, S., Suess, S., & Hostert, P. (2017). Ensemble learning from synthetically mixed training data for quantifying urban land cover with support vector regression. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10, 1640-1650. https://doi.org/10.1109/JSTARS.2016.2634859
Okujeni, A., van der Linden, S., Tits, L., Somers, B., & Hostert, P. (2013). Support vector regression and synthetically mixed training data for quantifying urban land cover. Remote Sensing of Environment, 137, 184-197. https://doi.org/10.1016/j.rse.2013.06.0079