Using new data from the European Sentinel-1 and 2 satellites in combination with Artificial Intelligence, it is now possible to accurately map cocoa growing areas and detect the associated deforestation. But how does this work and why was it not achievable before? Satelligence and partners Touton and SNV recently shared the exciting progress of accurately mapping cocoa and detecting deforestation at the invitation of Cocoa & Forests Initiative (CFI) stakeholders in Ghana. 

Niels Wielaard, director of Satelligence, gives us insights on the new approach towards deforestation-free cocoa supply chain monitoring in West-Africa.

The ability to accurately map cocoa growing areas and detect the associated deforestation has been explored by Daniel Tutu Benefor and Kwabena Asubonteng: explain how this new data collection approach is different?

NW: The improved resolution, scale and timeliness of map information based on Sentinel imagery enable cocoa sector stakeholders to better assess deforestation risk and work with farmers to achieve viable livelihoods without the encroachment of parks and reserves. All stakeholders in the sector will be able to use the data to better and faster complete risk assessments and end deforestation and forest degradation in the global cocoa supply chain.’

Why was it a challenge to map cocoa at farm level?

NW: Until recently, it has been impossible because cocoa trees show up as forest in traditional satellite images, and the use of spatially detailed imagery is found expensive especially where smallholders are concerned.’ So far, companies that have committed to eliminating deforestation in their supply chains were struggling to demonstrate measurable reduction in deforestation in their supply chains, due to lack of appropriate and cost-effective forest monitoring systems and reliable imagery.

Combining the cocoa distribution map with near real time vegetation change, our team could identify 8 priority locations for more targeted and effective risk management (see black circles below). Progressive changes elsewhere related to mining (‘Galamsey’) and logging can also be observed weekly.’


Image 1 : Input Sentinel-1 radar imagery and recent vegetation change map. Black circles indicate 8 prioritised change alert areas with active deforestation in parks and reserves (vegetation clearing in 2018: shown in red). Here, ground visits should take place to verify whether the clearing is related to newly planted cocoa or not.


The use of satellite imagery is not new, explain what is different about your approach?

NW: For our new approach we used freely available Sentinel-1 and 2 satellite imagery and built on scientific methods developed in Ghana. Engaging local knowledge and feedback from local experts, we improved these methods with the combined use of imagery at 10m detail, advanced radar imagery that can better capture forest and cocoa structure, and new machine learning techniques that achieve higher accuracy than previously possible.


The most common obstacles linked to this kind of mapping is cloud or haze cover. How did you tackle this?

NW: One way of dealing with this is to use Sentinel-1 radar that can ‘see’ through the clouds and haze. Secondly, we had to implement an automated cloud removal and tedious haze correction process to clean up all usable pixels of Sentinel-2 imagery collected every 5 days throughout the entire year.


Image 2: Sentinel-2 imagery collected every 5 days throughout the entire year


What has been the greatest breakthrough?

NW: The real excitement came when we overlaid Touton SA’s ground-based farm boundary data on the satellite-derived cocoa land cover map. Although both datasets have been generated independently, their alignment is spot-on. You can see that Touton’s farms follow the straight boundary of the forest of Bia natural park exactly. Even the farms less than 1 hectare have been identified correctly using the Sentinel imagery. Using field data collected by the Forestry Commission we established that the accuracy is very high. Thanks to Copernicus’ free and open data policy, this approach can now be feasibly scaled up to map all cocoa in the world.


Image 3: Farm data produced by Touton (black lines) overlaid on map product produced by Satelligence. Courtesy 3PRCL landscape project led by Touton. Partnership for Productivity Protection and Resilience in Cocoa Landscape. Colour scheme according to local expert preference.



Image 4: Comparison of Pleiades 0.5m imagery with our Sentinel-based 10m cocoa land cover map. Despite a 3 year difference, clusters of trees correlate very well with the agroforestry cocoa (light green) and forest (dark green) patterns in our map based on 10m Sentinel data. Pleiades Image ©CNES/Airbus


Considering these exciting developments what are the next steps  towards making Deforestation-Free supply chain monitoring a reality?

NW: The first step supporting cocoa sector stakeholders to refine the cocoa mapping results further, and scale it to entire West Africa. Moreover, we will have to determine the exact potential and limitations of the implementation of a deforestation monitoring service together with the experts in Ghana including the leading Resource Management Support Centre (RMSC) at the Forestry Commission.

The second step is the follow up of stakeholders on the ground – lead by the authorities – to verify drivers of change. And plan for rehabilitation of illegal cocoa farms in parks and reserves, providing local people with alternatives. Such a ground-based multi-stakeholder approach can build on the great example set by our partners WRI, with Cargill, PepsiCo and Proforest  on pre-competitive landscape-level palm oil supply chain collaboration in Indonesia.’

The successful delineation of cocoa from other tree cover is part of activities being implemented under the Shaded Cocoa Agroforestry Systems project and Partnership for Productivity, Protection and Resilience Landscapes project being funded by the German Ministry of Environment, The Nature Conservation and Nuclear Safety (BMU) and the UK government under partnerships for Forest Programme respectively.
The views expressed in this article are those of the author alone and not the Tropical Forest Alliance.

Follow Us

The Tropical Forest Alliance is a global public-private partnership in which partners take voluntary
actions, individually and in combination, to reduce tropical deforestation. Follow us below.