Automated Remote Sensing Forest Inventory Using Satellite Imagery
This work addresses the need for sustainable forest management in countries like Russia, Canada, and the USA, but it is incremental as it builds on existing methods without introducing a new paradigm.
The paper tackles the problem of large-scale forest inventory by using satellite imagery and machine learning, specifically comparing an Autoencoder-based approach to traditional CNNs for tree crown classification, achieving competitive results.
For many countries like Russia, Canada, or the USA, a robust and detailed tree species inventory is essential to manage their forests sustainably. Since one can not apply unmanned aerial vehicle (UAV) imagery-based approaches to large-scale forest inventory applications, the utilization of machine learning algorithms on satellite imagery is a rising topic of research. Although satellite imagery quality is relatively low, additional spectral channels provide a sufficient amount of information for tree crown classification tasks. Assuming that tree crowns are detected already, we use embeddings of tree crowns generated by Autoencoders as a data set to train classical Machine Learning algorithms. We compare our Autoencoder (AE) based approach to traditional convolutional neural networks (CNN) end-to-end classifiers.