ForestUNLOCK: A multi-modal Multiscale Benchmark Dataset for AI-Driven Boreal Forest Monitoring and Carbon Accounting

Visual for ForestUNLOCK; Building the first consistent multi-modal single tree benchmark for forest structure and carbon stock assessments of the northern boreal forest

Image: Open white spruce forest with glacier in background in the Chugach Mountains, Alaska, US ©Stefan Kruse, AWI

What is the project about?

Precise carbon budgeting in boreal forests needs tree-level monitoring, but complex structure and scarce data hinder scaling. ForestUNLOCK delivers a pioneering multi-modal, multi-scale benchmark dataset, integrating spatially co-registered, multi-temporal terrestrial, airborne, and spaceborne data for structure and carbon stock inference.

What motivated you to apply for UNLOCK, and how does the project align with the initiative’s vision?

Through our collaboration in the newly launched Helmholtz Imaging project POINTR, we recognized the uniqueness of our data, which in the context of ForestUNLOCK provides a novel foundation for individual tree benchmarking.

What gap in the scientific community led to the creation or expansion of this benchmarking dataset?

Individual tree-level datasets are scarce, yet they are essential for analyzing forest structure. Scaling these data to satellite observations enables continuous, large-scale, and continent-wide forest assessments.

How does the benchmark dataset support reproducibility, robustness, and fairness in AI research?

The datasets will be publicly released on a dedicated FAIR-compliant online platform developed specifically for this purpose