Context and objectives
Dryland ecosystems are under increasing pressure from climate change, land degradation, and unsustainable land use, yet they are critical for biodiversity, carbon storage, and human livelihoods. Current monitoring and modelling approaches lack the spatial and temporal detail required to capture fine-scale ecosystem dynamics.
The objective of TwinDryLands is to develop a high-resolution Digital Twin for dryland ecosystems, integrating Earth observation data, artificial intelligence, and vegetation modelling to improve understanding, monitoring, and prediction of ecosystem responses to environmental change. The project focuses on identifying vegetation dynamics, their causal drivers, and their implications for land restoration.
Project outcome
Expected scientific results
• New methods for high-resolution monitoring of dryland vegetation
• Improved understanding of ecosystem dynamics and tipping points
• A scalable approach for combining AI, remote sensing, and process-based modelling
• Advances in causal analysis of ecosystem change
• Contribution to international research on Digital Twin Earth systems
Expected products and services
• High-resolution vegetation maps and datasets
• AI models and emulators for ecosystem monitoring
• A functional Digital Twin platform for drylands
• Open-source tools and workflows (via GitHub/GitLab)
• Scientific publications and stakeholder-oriented outputs
| Project leader(s): | KULeuven - Department of Earth and Environmental Sciences (EES) | |||
| Belgian partner(s) |
|
|||
| International partner(s) | ||||
| Location: |
Continent:
Region:
|
|||
| Website: | http://www.earthmapps.io/projects/TwinDryLands.html | |||