Sentinel‐Based Inventory of Thermokarst Lakes and Ponds Across Permafrost Landscapes on the Qinghai‐Tibet Plateau.

Thermokarst lakes and ponds (hereafter referred to as thaw lakes) play an important role in the permafrost regions by regulating hydrology, ecology, and biogeochemistry. However, detailed quantitative information on thaw lake extent and distribution remains poorly resolved across the entire permafrost regions on the Qinghai‐Tibet Plateau (QTP). Here, we applied the random forest (RF) model and manual visual vectorization methods to extract thaw lake boundaries on the QTP based on Sentinel‐2 images. Accuracy assessment was comprehensively demonstrated regarding the inherent spatial resolution of imagery and RF model performance. The results showed that the accumulated uncertainty of the total thaw lake area was ±5.75 km2, and the mean accuracy (91.9%) from field‐measured boundaries of 132 thaw lakes supported the accuracy of this inventory. A total of ∼161,300 thaw lakes with sizes ranging from 500 m2 to 3 km2 were detected, with a total area of ∼2,825.45 ± 5.75 km2. Most thaw lakes were detected in the continuous permafrost type (94.1%) and within the elevations of 4,500–5,000 m (68.4%). The small thaw lakes (<10,000 m2) predominated the total lake number (78.9%) but contributed to a small portion of the total lake area (12.7%). Spatial distributions of thaw lakes in terms of different climatic and environmental conditions were also comprehensively explored, including temperature, precipitation, ground thermal stability, active layer thickness, vegetation, soil properties, and underground ice content. This inventory is expected to be incorporated into Earth system models for a more comprehensive projection of the large‐scale biogeochemical feedback of thermokarst landforms on the QTP under continued global warming. Plain Language Summary: Thaw lakes develop when warming soil melts ground ice, causing the surface to collapse and form pools of water. Such lakes can greatly influence local water resources and ecosystems, but also are important sources of greenhouse gas released into the atmosphere. Using Sentinel‐2 images, we provided robust information of thaw lake numbers, areas, and spatial distributions across the entire QTP permafrost regions by applying the random forest model and manual visual vectorization methods. The accuracy of the data set has been demonstrated in regard to the image spatial resolution, model performance, and field‐measured results. Within sizes ranging from 500 m2 to 3 km2, we extracted ∼161,300 thaw lakes with a total area of ∼2,825.45 ± 5.75 km2. We found that most thaw lakes were located in the continuous permafrost regions and within the elevations of 4,500–5,000 m. Most thaw lake sizes were smaller than 10,000 m2 but they only contributed to a little percentage of the total lake area. We also comprehensively explored the spatial distributions of thaw lakes in different climatic and environmental areas. This inventory would be useful for future Earth system models to predict the large‐scale biogeochemical feedback of thaw lakes on the Qinghai‐Tibet Plateau in the future. Key Points: Using Sentinel‐2 images, we established an inventory data set of thaw lakes on the QTP via random forest model and manual postprocessing methodsApproximately 161,300 thaw lakes with sizes ranging from 500 m2 to 3 km2 were extracted, with a total area of ∼2,825.45 ± 5.75 km2Distributions of thaw lakes were highly uneven in regard to different geospatial, climatic and environmental status [ABSTRACT FROM AUTHOR]