PAWI: The first high-resolution, multi-class, Pan-Arctic Wetland Inventory

Arctic wetlands are key regulators of global methane (CH 4 ) emissions, yet uncertainty in wetland spatial extent and class composition limits the accuracy of CH 4 budget models. Current mapping products lack circumpolar coverage and consistent thematic classification standards, constraining the ability to model ecosystem responses to Arctic warming. Here, we present the first high-resolution Pan-Arctic Wetlands Inventory (PAWI), produced at 10 m resolution using multi-sensor satellite imagery (e.g., Sentinel-1,…

By the Truvace deskOctober 15, 20261 min read1 sourcePeer-reviewedTRV-2026-1437· cite & verify

PAWI: The first high-resolution, multi-class, Pan-Arctic Wetland Inventory — 1002 Area- Brooks Range Mountains - DPLA - 454c2809e533021309d426864cc92770 by Department of the Interior. U.S. Fish and Wildlife Service. National Conservation Training Center. 10/1997-8888. Public domain

In brief

Researchers built the Pan-Arctic Wetlands Inventory, a 10 m resolution map covering the circumpolar Arctic. It was produced with a Random Forest classifier trained on Sentinel-1, Sentinel-2 and ALOS PALSAR-2 imagery, ArcticDEM topography, and environmental and hydrological datasets. It sorts wetlands into bog, fen, swamp, marsh and water.

Arctic wetlands strongly influence global methane emissions, but uncertain extent and class composition have limited the accuracy of methane budget models. A consistent baseline could sharpen those models and inform conservation planning. The abstract reports map accuracy, not measured improvements in methane forecasts, so downstream benefits remain prospective.

Main points

The inventory is described as the first high-resolution, multi-class, circumpolar wetland map of the Arctic.
Overall accuracy is reported as 89% with a Kappa of 0.86.
The map estimates that 20% of the Arctic landmass is wetland.
Inputs combine multi-sensor satellite imagery, ArcticDEM topography, and environmental and hydrological datasets.

The gain

A machine learning classifier applied to multi-sensor satellite and terrain data produced a consistent circumpolar wetland baseline that can improve methane flux models and conservation planning.

The rundown

The authors say existing mapping products lack circumpolar coverage and consistent thematic classification standards. That gap constrains how well models can represent ecosystem responses to Arctic warming.

The product is intended for improving methane flux modeling, assessing climate vulnerability, and supporting conservation planning. The authors also describe the work as a transferable framework for large-scale ecosystem classification in remote regions, achieved through multi-national data harmonization.