Open-Earth-Monitor Global Workshop 2025

Tropical forests are biodiversity hotspots, providing critical ecosystem services that sustain millions of plant and animal species. However, these forests are increasingly threatened by human activities, through the expansion of commodity crops such as soy, oil palm, rubber, cocoa, coffee, corn, logging, avocado, and pasture (Masolele et al., 2022, 2024). While significant efforts have been made to monitor deforestation using satellite imagery, most initiatives stop at detecting forest loss without tracking the land use that follows (Hansen et al., 2013). Understanding post-deforestation land use is crucial for addressing deforestation's root causes and mitigating its impacts (Masolele et al., 2022, 2024).
Currently, there is no global monitoring system capable of providing annual, spatially detailed updates on the land use that follows after deforestation. Existing datasets and methods frequently lack the spatial, thematic, and temporal resolution necessary to accurately map post-deforestation land uses (Curtis et al., 2018), limiting their utility for targeted rapid policy response and regulatory compliance, such as the European Union’s Deforestation Regulation (EUDR) (European Commission., 2024). This gap poses challenges for ensuring EUDR compliance, limiting the capacity to detect and mitigate deforestation linked to commodity production. Here, we present the first high-resolution (10 m) maps of land use following deforestation covering the entire pan-tropics. We utilize an extensive reference database containing 23 different land use types (including, soy, oil palm, rubber, cocoa, coffee, corn, logging, avocado, mining, cashew, corn, sugar, rice, and pasture), and employ Sentinel-1 and Sentinel-2 data combined with deep learning algorithms, to map land use following tropical deforestation from 2001 to 2023 with an F1-score of 83%. Our approach incorporates location encodings and environmental variables, such as elevation, temperature, and precipitation, to enhance the model’s ability to distinguish various land uses across diverse geographies. In general our results shows increased deforestation as a result of expansion of key commodity crops such as cocoa in Liberia, Cameroon, Ivory Coast, Ghana, Ecuador, Peru, Papua New Guinea; oil palm, in Indonesia, Malaysia; rubber in Malyasia, Thailand, Laos, Indonesia; coffee in Central America (Guatemala, Nicaragua, Costa rica), Peru, Ethiopia, Colombia, Vietnam; soy in Brazil; pasture in Paraguay, Bolivia, Mexico, Brazil, Cashew in in Cambodia, Tanzania, Mozambique, Benin and, logging in Suriname, Guyana, Papua New Guinea, Equatorial Guinea, Gabon, Republic of Congo, and Cameroon.
This work directly supports the European Union’s Deforestation Regulation (EUDR), aimed at curbing the EU market’s contribution to global deforestation (European Commission., 2024). Our research offers crucial insights for monitoring land use following deforestation, aiding environmental conservation initiatives and advancing carbon neutrality goals by providing detailed, high-resolution maps on land use that follows after deforestation events.

Cocoa cultivation serves as a cornerstone of many agricultural economies across the globe, supporting millions of livelihoods and contributing significantly to global cocoa production. However, accurately mapping cocoa farm locations remains a challenging endeavor due to the complex and heterogeneous nature of the landscapes where cocoa is cultivated. Traditional mapping techniques often fall short in capturing the intricate spatial patterns of cocoa farming amidst dense vegetation, varying land cover types, farming practices and growing stages (Masolele et at., 2024). Moreover, the current mapping efforts mainly focus on two major producing countries, Ivory Coast, and Ghana (Kalischek et al., 2023). Thus, little is known about the location of cocoa farms in other cocoa producing regions, posing a challenge to the sustainability and economic contributions of the cocoa crop.
To address this challenge, we first present a benchmarking approach for mapping commodity crops worldwide. Here we compare different spectral, spatial, temporal and spatial-temporal methods for mapping commodity crops. The benchmarking is based on a variable combination of Sentinel-1 and Sentinel-2, locational and environmental variables (temperature and precipitation). We use a comprehensive list of reference data spanning 36 cocoa-producing countries to do this task. Higher accuracy (F1-score 87%) is obtained when using a model that employs spatial-temporal remote sensing images plus locational and environmental information, compared to other models without locational and environmental information.
Secondly, for demonstration, we employ the developed deep learning methodologies to map the locations of cocoa farms across the Globe with an F1-Score of 88%. By leveraging the rich spatio-temporal information provided by Sentinel-1 and Sentinel-2 satellite data, complemented by location encodings, temperature and precipitation data, we have developed a robust and accurate cocoa mapping framework. The developed deep learning algorithm extracts meaningful features from multi-source satellite imagery and effectively identifies cocoa farming areas. The integration of Sentinel-1 and Sentinel-2 data offers a synergistic approach, combining radar and optical sensing capabilities to overcome the limitations of individual sensor modalities. Furthermore, incorporating location encodings into the modeling process enhances the contextual understanding of cocoa farm distributions within their geographical surroundings.
Through this research effort, we provide the first high-resolution global cocoa map giving, valuable insights into cocoa farm locations, facilitating sustainable cocoa production practices, land management strategies, and conservation efforts across the pan-tropical forests, where cocoa farming occurs. The work aligns with recent European Union (EU) regulations to curb the EU market’s impact on global deforestation and provides valuable information for monitoring land use following deforestation, crucial for environmental initiatives and carbon neutrality goals (European Commission., 2024). Specifically, our product can support monitoring and compliance of the European Union (EU) Regulation on Deforestation-free Products (EUDR, No 2023/1115) by identifying the previous existing and current cocoa farm expansion after the cut-off date of December 31, 2020.
Within the framework of the ESA funded WorldAgroCommodities project, this mapping approach is now being converted into an operational cloud-based service on the Copernicus Data Space Ecosystem, allowing easy access to these crucial tools for the National Competent Authorities in light of enforcing the EUDR regulation. Furthermore, our findings hold significant implications for cocoa farmers, agricultural policymakers, and environmental stakeholders, paving the way for informed decision-making and targeted interventions to support the resilience, sustainability and traceability of cocoa farming systems worldwide.