Large-scale probabilistic identification of boreal peatlands using Google Earth Engine, open-access satellite data, and machine learning.

Evan Ross Delancey,Jason T Bried,Jennifer N Hird,Jahan Kariyeva,Stephen P Aldrich

doi:10.1371/journal.pone.0218165

Evan Ross Delancey, Jason T Bried + Show 3 more

Open Access

https://doi.org/10.1371/journal.pone.0218165

Copy DOI

Abstract

Freely-available satellite data streams and the ability to process these data on cloud-computing platforms such as Google Earth Engine have made frequent, large-scale landcover mapping at high resolution a real possibility. In this paper we apply these technologies, along with machine learning, to the mapping of peatlands–a landcover class that is critical for preserving biodiversity, helping to address climate change impacts, and providing ecosystem services, e.g., carbon storage–in the Boreal Forest Natural Region of Alberta, Canada. We outline a data-driven, scientific framework that: compiles large amounts of Earth observation data sets (radar, optical, and LiDAR); examines the extracted variables for suitability in peatland modelling; optimizes model parameterization; and finally, predicts peatland occurrence across a large boreal area (397, 958 km2) of Alberta at 10 m spatial resolution (equalling 3.9 billion pixels across Alberta). The resulting peatland occurrence model shows an accuracy of 87% and a kappa statistic of 0.57 when compared to our validation data set. Differentiating peatlands from mineral wetlands achieved an accuracy of 69% and kappa statistic of 0.37. This data-driven approach is applicable at large geopolitical scales (e.g., provincial, national) for wetland and landcover inventories that support long-term, responsible resource management.

Highlights

The Topographic Position Index (TPI) panel shows that peatlands have a much larger proportion of values around zero than mineral wetlands
Many of the Sentinel-2 variables were strongly correlated with one another (r > 0.60) while the normalized difference of polarization (NDPOL), TPI, and TWI variables showed very little correlation with other variables and are seen as the most unique variables (Table 2)
We retained REIP, PC1, TWI, TPI, NDPOL, ARI, VH, and PC2 for the peatland model based on their relative importance (Table 3), and to mitigate collinearities (Table 2; i.e. r < 0.7 among any variable pairs)

Summary

Objectives

We build on the work of [21] where wetland extent was mapped in a 13,700 km region of the Boreal Forest Natural Region of Alberta (BNR) with Sentinel-1 (SAR), Sentinel-2 (optical), and topographic data with promising results in terms of accuracy (85%), spatial resolution (10 m), and large-area scalability. We expand on [21] by providing more information on wetland type, and by establishing a data processing framework wherein large amounts of Earth observation data from different sources can be used to classify landcover at a high spatial resolution (e.g., 10 m), over larger areas (397, 958 km2) with relatively high frequency. We hope that our framework contributes to improved wetland mapping in Alberta (i.e., large-scale, high-resolution, spatially-consistent) and supports better understandings of the current state of Alberta’s peatlands, and to building a state-of-thescience, data-driven mapping framework for any landcover mapping project

Methods

Results

Discussion

Conclusion