Global forest typology at 10-meter resolution for forest and land-use monitoring

Neumann, M., Raichuk, A., Potapov, P., Lesiv, M. ORCID: https://orcid.org/0000-0001-9846-3342, Overlan, M., Rey, M., Rajakumar, R., Conserva, M., Stanimirova, R., Sims, M., Carter, S., Goldman, E., Jiang, Y., Scheibenreif, L., Georgieva, I. ORCID: https://orcid.org/0000-0002-5556-794X, Shchepashchenko, M. ORCID: https://orcid.org/0000-0003-1081-2902, Fritz, S. ORCID: https://orcid.org/0000-0003-0420-8549, Clinton, N., Stanton, C., Morris, D., et al. (2026). Global forest typology at 10-meter resolution for forest and land-use monitoring. EarthArXiv preprint 10.31223/X58R27. (Submitted)

Preview

Text forest_typology.pdf - Submitted Version Available under License Creative Commons Attribution. Download (23MB) | Preview

Abstract

Distinguishing forest types---primary, naturally regenerating, planted, and plantation forests---from agricultural tree crops and other land uses is essential for carbon accounting, biodiversity assessment, conservation planning, and supply-chain regulation. However, no existing global dataset resolves this typology at high spatial resolution. We present the Forest Typology (ForTy) v1 dataset, a global 10-meter resolution map for 2020 that classifies all land into six categories aligned with FAO and EU Deforestation Regulation (EUDR) definitions: Primary Forest, Naturally Regenerating Forest, Planted Forest, Plantation Forest, Tree Crops and Agroforestry, and Other Land. A cascaded deep learning pipeline, trained on 1.7 million globally distributed samples, generates per-class probability maps from geospatial satellite embeddings by combining weakly supervised learning with active learning. Independent validation against 8,190 stratified random sites, each labeled by two experts, yields an overall accuracy of 90.2% for the six-class scheme, 94.8% for natural forest classification, and 95.5% for forest/non-forest classification.

Actions (login required)

View Item