• Corpus ID: 251066596

Exploring Wilderness Characteristics Using Explainable Machine Learning in Satellite Imagery

@inproceedings{Stomberg2022ExploringWC,
  title={Exploring Wilderness Characteristics Using Explainable Machine Learning in Satellite Imagery},
  author={Timo T. Stomberg and Taylor Stone and Johannes Leonhardt and Immanuel Weber and Ribana Roscher},
  year={2022}
}
Wildernessareasofferimportantecologicalandsocialbenefitsand thereareurgentreasonstodiscoverwheretheirpositivecharacter-istics and ecological functions are present and able to flourish. We apply a novel explainable machine learning technique to satellite images which show wild and anthropogenic areas in Fennoscandia. Occluding certain activations in an interpretable artificial neural network we complete a comprehensive sensitivity analysis regarding wild and anthropogenic characteristics. Our… 

Figures and Tables from this paper

MapInWild: A Remote Sensing Dataset to Address the Question What Makes Nature Wild

To meet the pressing need to better understand the nature the authors are living in, a novel task of wilderness mapping is introduced and the MapInWild dataset is introduced – a multi-modal large-scale benchmark dataset designed for the task of Wilderness mapping from space.