High-resolution sensors and deep learning models for tree resource monitoring

Brandt, Martin; Chave, Jerome; Li, Sizhuo; Fensholt, Rasmus; Ciais, Philippe; Wigneron, Jean-Pierre; Gieseke, Fabian; Saatchi, Sassan; Tucker, C. J.; Igel, Christian

Zusammenfassung

Trees contribute to carbon dioxide absorption through biomass, regulate the climate, support biodiversity, enhance soil, air and water quality, and offer economic and health benefits. Traditionally, tree monitoring on continental and global scales has focused on forest cover, whereas assessing biomass and species diversity, as well as trees outside closed-canopy forests, has been challenging. A new generation of commercial and public satellites and sensors provide high-resolution spatial and temporal optical data that can be used to identify trees as objects. Technologies from the field of artificial intelligence, such as convolutional neural networks and vision transformers, can go beyond detecting these objects as two-dimensional representations, and support characterization of the three-dimensional structure of objects, such as canopy height and wood volume, via contextual learning from two-dimensional images. These advancements enable reliable characterization of trees, their structure, biomass and diversity both inside and outside forests. Furthermore, self-supervision and foundation models facilitate large-scale applications without requiring extensive amounts of labels. Here, we summarize these advances, highlighting their application towards consistent tree monitoring systems that can assess carbon stocks, attribute losses and gains to underlying drivers and, ultimately, contribute to climate change mitigation.

Schlüsselwörter
Deep Learning; Artificial Intelligence; Remote Sensing; Biomass Estimation