OSINFOR's Machine-Learning Satellite System Helps Peru Seize $19 Million in Illegal Timber

Peru manages roughly 68 million hectares of tropical rainforest, much of it in remote Amazonian regions where illegal logging is typically selective - loggers remove a handful of high-value trees per hectare rather than clearing land outright - making it very hard to detect with standard satellite change-detection, which is tuned to larger-scale deforestation.
Researchers at the University of Sheffield's Grantham Centre for Sustainable Futures (Shaun Quegan, David Edwards, Robert Bryant, Chris Bousfield and Matthew Hethcoat, the last now with the Canadian Forest Service) built a machine-learning method that analyses very-high-resolution satellite imagery to identify the removal of individual trees in near-real time. Detected logging events are cross-referenced against official data from Peru's forestry service, SERFOR, and its national forest-tracking system, SISFOR, to determine whether the activity falls inside an approved logging plan or is illegal.
OSINFOR, Peru's independent forest and wildlife oversight agency, adopted the tool to target its field inspections, formally inaugurating the technology in 2025. Across an initial 1.8 million hectares of monitored forest, the system has identified 37% of all officially reported illegal logging. Peruvian authorities used the resulting evidence to seize more than 41,000 cubic metres of illegal timber between 2023 and 2024, with a market value exceeding US$19 million, according to OSINFOR chief Williams Arellano.
Researchers describe the tool as a step-change for enforcement timing: because selective logging is detected while it is still happening rather than after satellite imagery shows a fully cleared plot months later, inspectors can intervene while evidence and, in some cases, loggers are still on site. The approach is designed to be extensible to other Amazon basin countries facing the same detection gap for selective logging, though deployment to date has been limited to Peru.

Read the full analysis: https://www.sheffield.ac.uk/news/new-technology-helping-fight-against-illegal-logging-perus-valuable-rainforest