Strengthening forest research for the support of Ukraine HORIZON-CL6-2027-01-CIRCBIO-10

Vision and challenge

Ukraine’s forest sector needs fast, evidence-based recovery and long-term resilience under the compounded impacts of war, climate change, and biodiversity loss. A key bottleneck is the lack of a fully digital, transparent, and continuously updated forest cadastre and monitoring capability that can directly support governance, restoration planning, and EU acquis alignment. Our proposal delivers an integrated “forest data-to-policy” pipeline that turns heterogeneous sensing and inventory data into verifiable cadastre updates, risk analytics, and auditable timber legality/traceability.

Overall objective

Build and pilot a National Digital Forest Recovery Platform that (i) digitalises and modernises cadastre workflows, (ii) establishes a continuous forest monitoring system (remote sensing + IoT + field validation), and (iii) enables trusted, privacy-preserving traceability across timber/biomass value chains—supporting policy, enforcement, education, and EU integration.

Why we can deliver

We bring a rare end-to-end capability spanning Forest 4.0 digital transformation (blockchain + IoT + AI), secure identity and smart contracts for timber legality and accountability, and AI-driven monitoring from sensors and satellites:

• Blockchain-driven identity management (SSDI) for sustainable forest supply chains with throughput/latency evaluation on Ethereum-like setups.

• Blockchain-enabled smart contracts for timber traceability with quantified throughput, energy/transaction trends, and gas-fee complexity insights.

• Adaptive sensor clustering for dynamic forest ecosystems (QFCM + RL adaptation), improving energy efficiency and robustness for WSN-based monitoring.

• AI monitoring at scale: YOLO-based individual tree detection from RGB satellite imagery with high detection performance; plus wildfire prediction and early detection using weather/audio signals.

• Decision models for resilience: regeneration dynamics (Markov + time-series decomposition), and optimisation of wood supply chains under uncertainty (two-stage stochastic MILP).

• Digital twin foundations: reinforcement-learning adaptive digital twin for forest ecosystems; plus research on scalable consensus (including quantum-inspired directions) for real-time environmental data integrity.