Super-Resolution Surface Water Mapping on the Canadian Shield Using Planet CubeSat Images and a Generative Adversarial Network

Abstract

The Canadian Shield, the world’s largest exposure of glaciated crystalline bedrock, is the most lake-rich region on Earth. Recent studies using high-resolution CubeSat satellite imagery have revealed its surface water hydrology to be surprisingly dynamic at fine spatial scales. Here we test whether super-resolution (SR), the resampling of coarse imagery to a finer-than-native resolution, can detect such changes. We degrade high-resolution Planet CubeSat images of the Shield, then resample the coarsened imagery back to its native resolution using both traditional cubic resampling and a generative adversarial network, a type of neural network often used for SR. To test classification accuracy from the generated SR imagery, we apply the same water classification to both resampling methods and find similar performance based on confusion matrices with the control case of high-resolution imagery. Next, we compare fine-scale shoreline mapping in SR imagery, cubic resampling, and in-situ field surveys. SR shorelines outperform those from cubic resampling, with an increase in the modified kappa coefficient from −0.070 to 0.073. Potential applications include improved mapping of Shield lakes and retroactive application of SR to coarser-resolution satellite datasets to infer historical changes in fine-scale surface water dynamics.