Leveraging Deep Neural Networks to Map Caribou Lichen in High-Resolution Satellite Images Based on a Small-Scale, Noisy UAV-Derived Map

Abstract

Lichen is an important food source for caribou in Canada. Lichen mapping using remote sensing (RS) images could be a challenging task, however, as lichens generally appear in unevenly distributed, small patches, and could resemble surficial features. Moreover, collecting lichen labeled data (reference data) is expensive, which restricts the application of many robust supervised classification models that generally demand a large quantity of labeled data. The goal of this study was to investigate the potential of using a very-high-spatial resolution (1-cm) lichen map of a small sample site (e.g., generated based on a single UAV scene and using field data) to train a subsequent classifier to map caribou lichen over a much larger area (~0.04 km2 vs. ~195 km2) and a lower spatial resolution image (in this case, a 50-cm WorldView-2 image). The limited labeled data from the sample site were also partially noisy due to spatial and temporal mismatching issues. For this, we deployed a recently proposed Teacher-Student semi-supervised learning (SSL) approach (based on U-Net and U-Net++ networks) involving unlabeled data to assist with improving the model performance. Our experiments showed that it was possible to scale-up the UAV-derived lichen map to the WorldView-2 scale with reasonable accuracy (overall accuracy of 85.28% and F1-socre of 84.38%) without collecting any samples directly in the WorldView-2 scene. We also found that our noisy labels were partially beneficial to the SSL robustness because they improved the false positive rate compared to the use of a cleaner training set directly collected within the same area in the WorldView-2 image. As a result, this research opens new insights into how current very high-resolution, small-scale caribou lichen maps can be used for generating more accurate large-scale caribou lichen maps from high-resolution satellite imagery.

Leveraging AI to Estimate Caribou Lichen in UAV Orthomosaics from Ground Photo Datasets

“…The UAV LiCNN performs best on the UAV orthomosaics where there are large lichen patches and few objects having similar RGB values, such as sand or bright logs. A limiting factor to scaling lichen mapping, as highlighted by Jozdani et al, is the lack of diversity in the small training data compared to the larger imagery [15]. Due to the larger extent of the UAV orthomosaics compared to the ground photographs, there are more opportunities for misclassifications of land covers that were not included during neural network training.…”

Remote sensing and spectroscopy of lichens

“…Data collected by sensors onboard unoccupied aerial vehicles (UAV) have recently emerged also in lichen mapping. Lichen cover has been estimated for caribou areas in Canada and the United States based on UAV data using random forest models (Macander et al., 2020 ), various machine learning methods (He et al., 2021 ) and neural networks (Jozdani, Chen, Chen, Leblanc, Lovitt, et al., 2021a , Jozdani, Chen, Chen, Leblanc, Prevost, et al., 2021b ; Richardson et al., 2021 ). While UAV data cannot be used to cover fully the extensive areas where reindeer and caribou herd, it can serve as part of a multiscale remote sensing framework which incorporates satellite and ground reference data as well as UAV data.…”

Automating Lichen Monitoring in Ecological Studies Using Instance Segmentation of Time-Lapse Images

“…Instead, it directly regresses the percentage of lichen cover as a continuous value. Jozdani et al [11] and Fraser et al [12] investigated the ability to train neural network models on high-resolution images taken with unmanned aerial drones. The method in [11] is designed to perform a binary segmentation of terricolous lichens, regardless of their species.…”

“…Jozdani et al [11] and Fraser et al [12] investigated the ability to train neural network models on high-resolution images taken with unmanned aerial drones. The method in [11] is designed to perform a binary segmentation of terricolous lichens, regardless of their species. Fraser et al [12] used a random forest model to globally quantify the cover of pale and fruticose lichens of the genus Cladonia from UAV and satellite images.…”