Automated mapping of Portulacaria afra canopies for restoration monitoring with convolutional neural networks and heterogeneous unmanned aerial vehicle imagery

Abstract

Ecosystem restoration and reforestation often operate at large scales, whereas monitoring practices are usually limited to spatially restricted field measurements that are (i) time- and labour-intensive, and (ii) unable to accurately quantify restoration success over hundreds to thousands of hectares. Recent advances in remote sensing technologies paired with deep learning algorithms provide an unprecedented opportunity for monitoring changes in vegetation cover at spatial and temporal scales. Such data can feed directly into adaptive management practices and provide insights into restoration and regeneration dynamics. Here, we demonstrate that convolutional neural network (CNN) segmentation algorithms can accurately classify the canopy cover of Portulacaria afra Jacq. in imagery acquired using different models of unoccupied aerial vehicles (UAVs) and under variable light intensities. Portulacaria afra is the target species for the restoration of Albany Subtropical Thicket vegetation, endemic to South Africa, where canopy cover is challenging to measure due to the dense, tangled structure of this vegetation. The automated classification strategy presented here is widely transferable to restoration monitoring as its application does not require any knowledge of the CNN model or specialist training, and can be applied to imagery generated by a range of UAV models. This will reduce the sampling effort required to track restoration trajectories in space and time, contributing to more effective management of restoration sites, and promoting collaboration between scientists, practitioners and landowners.

Deep learning–based radiomic nomograms for predicting Ki67 expression in prostate cancer

“…Convolutional neural networks (CNNs), a representative class of deep learning algorithms which comprise convolutional, pooling, excitation, and fully connected layers, have been applied extensively in radiomics. Models constructed using CNNs can automatically learn to extract and select image features used to make predictions; such models facilitate deep mining of image information [ 14 ] and have extensive application prospects.…”

From simple labels to semantic image segmentation: Leveraging citizen science plant photographs for tree species mapping in drone imagery

“…However, generating models that are transferable across various landscapes and remote sensing data characteristics requires large amounts of training data Galuszynski et al, 2022). In particular, when neighboring plant species bear a similar resemblance, a wealth of training data becomes essential, allowing the model to discern the subtle distinctions between these species Schiefer et al, 2020).…”

“…In an ideal setting for species mapping applications, the species labels would delineate the regions or pixels belonging to a species (The pixels in the right corner of image i represents species j ). Such labels (known as masks) could be used to train CNN-based segmentation models, which can predict a species probability for each individual pixel of an image (or tile of an orthoimage) (Galuszynski et al, 2022;Schiefer et al, 2020).…”