High-Resolution Snow-Covered Area Mapping in Forested Mountain Ecosystems Using PlanetScope Imagery

Abstract

Improving high-resolution (meter-scale) mapping of snow-covered areas in complex and forested terrains is critical to understanding the responses of species and water systems to climate change. Commercial high-resolution imagery from Planet Labs, Inc. (Planet, San Francisco, CA, USA) can be used in environmental science, as it has both high spatial (0.7–3.0 m) and temporal (1–2 day) resolution. Deriving snow-covered areas from Planet imagery using traditional radiometric techniques have limitations due to the lack of a shortwave infrared band that is needed to fully exploit the difference in reflectance to discriminate between snow and clouds. However, recent work demonstrated that snow cover area (SCA) can be successfully mapped using only the PlanetScope 4-band (Red, Green, Blue and NIR) reflectance products and a machine learning (ML) approach based on convolutional neural networks (CNN). To evaluate how additional features improve the existing model performance, we: (1) build on previous work to augment a CNN model with additional input data including vegetation metrics (Normalized Difference Vegetation Index) and DEM-derived metrics (elevation, slope and aspect) to improve SCA mapping in forested and open terrain, (2) evaluate the model performance at two geographically diverse sites (Gunnison, Colorado, USA and Engadin, Switzerland), and (3) evaluate the model performance over different land-cover types. The best augmented model used the Normalized Difference Vegetation Index (NDVI) along with visible (red, green, and blue) and NIR bands, with an F-score of 0.89 (Gunnison) and 0.93 (Engadin) and was found to be 4% and 2% better than when using canopy height- and terrain-derived measures at Gunnison, respectively. The NDVI-based model improves not only upon the original band-only model’s ability to detect snow in forests, but also across other various land-cover types (gaps and canopy edges). We examined the model’s performance in forested areas using three forest canopy quantification metrics and found that augmented models can better identify snow in canopy edges and open areas but still underpredict snow cover under forest canopies. While the new features improve model performance over band-only options, the models still have challenges identifying the snow under trees in dense forests, with performance varying as a function of the geographic area. The improved high-resolution snow maps in forested environments can support studies involving climate change effects on mountain ecosystems and evaluations of hydrological impacts in snow-dominated river basins.

Confounding effects of snow cover on remotely sensed vegetation indices of evergreen and deciduous trees: An experimental study

“…The accuracy of snow cover estimation is subject to errors in the transformation and illumination conditions (Fedorov et al, 2016; Hinkler et al, 2002). Combining imagery collected by drone (Belmonte et al, 2021) or CubeSat (Cannistra et al, 2021; John et al, 2022) with machine learning methods may offer new approaches to deriving high spatial resolution snow coverage products. The accuracy of these methods is sensitive to forest canopy structure and landscape topography (Belmonte et al, 2021; Cannistra et al, 2021).…”

Mapping of Allergenic Tree Species in Highly Urbanized Area Using PlanetScope Imagery—A Case Study of Zagreb, Croatia

“…PlanetScope satellites have been equipped, depending on the generation of the sensor system, since 2016 with four bands (Blue, Green, Red, Near Infrared-NIR; PS2 and PS2.SD generation), while the new generation-since 2019 (SuperDove; PSB.SD) has enabled eight-bands products (Coastal Blue, Green I, Yellow, and Red-Edge spectral bands are added) [24]. Based on the newly added spectral bands, the Red-Edge band played an important role in improving the accuracy of crop classification, due to the region where the spectral reflectance of green vegetation rises rapidly [35].…”

“…To overcome these issues, PlanetScope (PS) satellite imagery [22] offers significant benefits over previous RS data due to its daily temporal resolution and 3 m spatial resolution, providing an effective solution to overcome existing issues. Hence, PS data has been successfully used, for example, in mapping rubber plantations [23], snow-covered areas in forested mountain ecosystems [24], mapping of lava flows in barren regions [25], and land-cover classification in urban areas [20]. Furthermore, in 2019, PlanetScope announced the general commercial availability of the next generation of PS Monitoring product, which includes eight spectral bands, instead of previously offering four bands [26].…”

Improving Mountain Snow and Land Cover Mapping Using Very-High-Resolution (VHR) Optical Satellite Images and Random Forest Machine Learning Models

“…Potential solutions to the "training data bottleneck" include crowd-sourcing methods [103], attempts to adapt pre-existing labeled datasets [104], and weak labeling approaches [105]. The deep learning approaches developed by Cannistra et al [106] and John et al [107] produce binary snow cover maps from 3 m PlanetScope imagery using convolutional neural networks trained on thresholded aerial lidar snow-depth products. As mentioned earlier, the training requirements for neural networks greatly exceed those for random forest models-Cannistra et al [106] trained their models on 370 million pixels compared to our ~65,000 samples per land cover class (~400,000 training pixels per model).…”