Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps (CA, RU)

Nitze, Ingmar; Heidler, Konrad; Barth, Sophia; Grosse, Guido

In a warming Arctic, permafrost-related disturbances, such as retrogressive thaw slumps (RTS), are becoming more abundant and dynamic, with serious implications for permafrost stability and bio-geochemical cycles on local to regional scales. Despite recent advances in the field of earth observation, many of these have remained undetected as RTS are highly dynamic, small, and scattered across the remote permafrost region. Here, we assessed the potential strengths and limitations of using deep learning for the automatic segmentation of RTS using PlanetScope satellite imagery, ArcticDEM and auxiliary datasets. We analyzed the transferability and potential for pan-Arctic upscaling and regional cross-validation, with independent training and validation regions, in six different thaw slump-affected regions in Canada and Russia. We further tested state-of-the-art model architectures (UNet, UNet++, DeepLabv3) and encoder networks to find optimal model configurations for potential upscaling to continental scales. The best deep learning models achieved mixed results from good to very good agreement in four of the six regions (maxIoU: 0.39 to 0.58; Lena River, Horton Delta, Herschel Island, Kolguev Island), while they failed in two regions (Banks Island, Tuktoyaktuk). Of the tested architectures, UNet++ performed the best. The large variance in regional performance highlights the requirement for a sufficient quantity, quality and spatial variability in the training data used for segmenting RTS across diverse permafrost landscapes, in varying environmental conditions. With our highly automated and configurable workflow, we see great potential for the transfer to active RTS clusters (e.g., Peel Plateau) and upscaling to much larger regions.

Citation

In order to use these data, you must cite this data set with the following citation:

Nitze, I.; Heidler, K.; Barth, S.; Grosse, G. Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps. Remote Sens. 2021, 13, 4294. https://doi.org/10.3390/rs13214294

Contact

Nitze, Ingmar

Metadata Access

DCAT in RDF/XML-Format

DCAT in Turtle-Format

DCAT in JSON-LD-Format

APGC Dataset Metadata in JSON-Format

Data and Resources

Additional Info

Field Value
Identifier DOI:10.3390/rs13214294
Project(s)
Institute AWI Alfred Wegener Institute Helmholtz Centre for Polar and Marine Research
Source https://github.com/initze/DL_RTS_Paper
Publication Date 2021-10-26
Version 1.0
Product Deep Learning Approach for Mapping Retrogressive Thaw Slumps
Sensor PlanetScope, ArcticDEM
Files
  1. Training Polygon Shapefile
  2. Study Site GeoJSON
  3. Processing Code
Variables [Units]
  1. image_id: PlanetScope Scene id
  2. image_date: date of the image
  3. region: region identifier
  4. site: site identifier
  5. id_ds: scene specific slump id
  6. label: class identifier (default:1)
  7. id: unique slump id
Region Circum-Arctic
Spatial Reference EPSG:4326 WGS 84
Spatial Resolution
Spatial Coverage Latitude 69.08 to 73.08, Longitude -139.10 to 124.52
Temporal Coverage 2018-07-02 to 2019-09-28
Temporal Resolution
Format Shapefile, GeoJSON, Python
Is Supplement To

Nitze, I.; Heidler, K.; Barth, S.; Grosse, G. Developing and Testing a Deep Learning Approach for Mapping Retrogressive Thaw Slumps. Remote Sens. 2021, 13, 4294. https://doi.org/10.3390/rs13214294

Related to

Dataset extent

Map data © OpenStreetMap contributors