Thesis subject

MSc thesis topic: Characterising RADD forest disturbance alerts using high resolution Planet data

Timely information on deforestation is crucial to effectively manage and protect forest resources in the tropics. Poorly managed and illegal activities (e.g. mining, logging) cause a wide range of negative environmental effects and significant financial costs.

In the past 10 years, satellite-based alert systems (e.g. Reiche et al., 2021, Hansen et al. 2016, Watanabe et al., 2018) have emerged as the primary tool to provide near real-time information on newly disturbed tropical forest areas. A wide range of stakeholders, including governments, NGOs, private sector actors and communities across the tropics have recognized the value of satellite-based disturbance alert products to empower sustainable land management and law enforcement actions against illegal forest activities (Lynch et al 2013, Finer et al 2018, Weisse et al 2019, Tabor and Holland 2020). Limited data availability due to persistent cloud cover in the tropics, however, limits the capacity of optical-based systems (e.g. GLAD alerts; Hansen et al, 2016). With the new RADD (Radar for Detecting Deforestation) alerts (Reiche et al., 2021), for the first time high resolution (10 m) radar-based forest disturbance information (every 6 – 12 days) are provided.

Providing the location of new forest disturbance alerts only, however, does not provide information on the driver of deforestation – crucial information for understanding the deforestation dynamics and for potential intervention. Providing information on the driver of newly deforested areas as soon as possible after the event occurred is among the major needs of stakeholders in tropical regions.

Since early 2021, pre-processed monthly mosaics of high resolution optical Planet data (3 m resolution) are available openly for the tropical regions. This data holds a great potential for the rapid characterisation of detected forest disturbances.

RADD alerts:
WUR RADD website:
Planet access:


  • Generate a dataset of different types of RADD alert events (selective logging, mining, smallholder agriculture)
  • Study the distribution of Planet reflectance and difference texture measures across RADD alert events
  • Generate a model (e.g. Random Forest) to predict the type of RADD alert events based on Planet data


  • Reiche J, Mullissa A, Slagter B, Gou Y, Tsendbazar N-E, Odongo-Braun C, Vollrath A, Weisse MJ, Stolle F, Pickens A, Donchyts G, Clinton N, Gorelick N, and Herold M (2021). Forest Disturbance alerts for the Congo Basin using Sentinel-1. Environmental Research Letters
  • Tyukavina et al., (2018). Congo Basin forest loss dominated by increasing smallholder clearing. Science Advances, Vol. 4, no. 11, eaat2993. DOI: 10.1126/sciadv.aat2993
  • Finer et al., (2018): Combating deforestation: From satellite to intervention. Science.


  • Advanced Earth Observation course
  • Geo-scripting course (Good knowledge in scripting is an asset; e.g. R, python, java script)

Theme(s): Sensing & measuring; Modelling & visualisation