Deep learning and satellite remote sensing for biodiversity monitoring and conservation

Abstract In the context of the current nature crisis, being able to reliably and cost‐effectively track subtle changes in the biosphere across adequate spatial and temporal extents and resolutions is crucial. Deep learning represents a group of versatile approaches to image processing tasks that are increasingly combined with satellite remote sensing imagery to monitor biodiversity and inform ecology and conservation, yet an overview of the opportunities and challenges associated with this development has so far been lacking. Here, we provide an interdisciplinary perspective on current research and technological developments associated with satellite remote sensing and deep learning that have the potential to make a difference in biodiversity monitoring and wildlife conservation; highlight challenges to the broader adoption of these approaches by experts operating at the interface between satellite remote sensing and ecology and conservation; and discuss how these can be overcome. By enabling the leveraging of big data and by providing new ways to learn about biodiversity and its dynamics, deep learning approaches promise to become a powerful tool to help address current monitoring needs and knowledge gaps. In certain situations, deep learning approaches may moreover substantially reduce the time and resources required to analyse satellite imagery. However, issues relating to capacity building, reference data access, environmental costs as well as model interpretability, robustness and alignment need to be addressed to successfully capitalize on these opportunities.