Radar Remote Sensing

Our research utilizes radar remote sensing for unravelling human activities in and dynamics of forest ecosystems at regional to global scales, and has a strong focus on near real-time change monitoring. We develop machine learning methods using radar and multi-sensor data to monitor change dynamics, their drivers and associated greenhouse gas emissions more accurately and timely.

Satellite radar remote sensing uses long-wavelength energy that penetrates through clouds and is sensitive to changes in vegetation physical structure. These characteristics are major advantages for monitoring forest dynamics, in particular in tropical regions where cloud cover is persistent. New and near-future radar satellites provide spatially detailed information almost daily and cloud computing solutions now enable large-scale applications.

An alarming rate of human-induced forest loss combined with more frequent extreme climate events strongly increases the pressure on the Earth’s forest ecosystems. At the same time, countries and major commodity sectors commit to zero-deforestation pledges. We work on openly accessible and timely information on the dynamics and drivers of changes in forests urgently needed to empower sustainable land management, law enforcement actions against illegal activities, and climate change law implementations.

Our core research lines are:

  • Fundamental radar methods
  • Near real-time change monitoring
  • Characterising forest changes and dynamics

Current PhD, Postdoc and research projects

  • Dr. Maciej Soja (Researcher): Biomass and selective logging monitoring using high resolution radar
  • Robert Masolele (Researcher): Large scale forest dynamics and driver monitoring
  • Dr. Laura Cué la Rosa (Postdoc): Near-future deforestation prediction using deep learning
  • Johannes Balling (PhD student): Characterizing tropical forest change dynamics using multi-sensor satellite data
  • Bart Slagter (PhD Student): Mapping and characterisation of small-scale forest disturbance using satellite data and artificial intelligence
  • Anne-Juul Welsink (PhD student): Monitoring selective logging using advanced earth observation datasets
  • Sietse van der Woude (PhD student): European forest monitoring linking satellite and ground-based data streams
  • Karimon Nesha (PhD student): Progressing the use of earth observation
    and national in-situ data for monitoring of forest emissions
  • Arjen de Jonge (PhD student): Detection of drought effects on trees using near- and remote-sensing

Former colleagues

  • Dr. Adugna Mullissa (Postdoc 2018 - 2022) - continued at CTrees, United States
  • Dr. Christelle Braun (Postdoc 2018 - 2020) - continued at UNEP, Senegal
  • Dr. Wanda de Keersmaecker (Postdoc 2019 – 2021) - continued at VITO, Belgium
  • Dr. Ovidiu Csillik (Postdoc 2019-2021) - continued at JPL, USA
  • Dr. Yaqing Gou (Postdoc 2020 – 2022) – continued at Rabobank, The Netherlands
  • Dr. Milutin Milenkovic (Postdoc 2018 – 2022) – continued at IIASA, Austria

Key publications

Fundamental radar methods

Near real-time change monitoring

Characterising changes and dynamics

Available open-source software

‘Bayts’ R-package: https://github.com/jreiche/bayts.
Set of tools to apply the probabilistic machine learning approach of Reiche et al. (2015, 2018) to combine multiple Radar and/or optical satellite time series and to detect deforestation/forest cover loss in near real-time.

Code for Angular-based radiometric slope correction of Sentinel-1 on Google Earth Engine (Vollrath et al 2020): https://github.com/ESA-PhiLab/radiometric-slope-correction.

Code for deSpeckNet (Mullissa et al, 2020): Generalizing Deep Learning Based SAR Image Despeckling: https://github.com/adugnag/deSpeckNet (original Matlab code) | https://github.com/adugnag/deSpeckNet-TF-GEE (python implementation to seamlessly integrate Sentinel-1 SAR image preparation in GEE with deep learning in Tensorflow for SAR image despeckling)

Code for CV-deSpeckNet (Mullissa et al, 2021) - Despeckling Polarimetric SAR Data Using a Multistream Complex-Valued Fully Convolutional Network: https://github.com/adugnag/CV-deSpeckNet

Code for Sentinel-1 SAR Backscatter Analysis Ready Data Preparation in Google Earth Engine (Mullissa et al, 2021): https://github.com/adugnag/gee_s1_ard