5 citations · 8 across the 7 of their papers we have counts for
7 papers
Beyond Accuracy: Assessing Calibration of Geospatial Foundation Models and Their Sensitivity to Distribution Shifts
Nils Lehmann, Jakob Gawlikowski, Burak Ekim +2
Geospatial Foundation Models (GeoFMs) are most commonly ranked and selected by accuracy on standard benchmark conditions via averaged ranks. We show that this protocol is too narro…
Advancing Earth Observation Through Machine Learning: A TorchGeo Tutorial
Caleb Robinson, Nils Lehmann, Adam J. Stewart +4
Earth observation machine learning pipelines differ fundamentally from standard computer vision workflows. Imagery is typically delivered as large, georeferenced scenes, labels may…
Distribution Shifts at Scale: Out-of-distribution Detection in Earth Observation
Burak Ekim, Girmaw Abebe Tadesse, Caleb Robinson +4
Training robust deep learning models is crucial in Earth Observation, where globally deployed models often face distribution shifts that degrade performance, especially in low-data…
Mapping Land Naturalness from Sentinel-2 using Deep Contextual and Geographical Priors
Burak Ekim, Michael Schmitt
In recent decades, the causes and consequences of climate change have accelerated, affecting our planet on an unprecedented scale. This change is closely tied to the ways in which…
Explaining Multimodal Data Fusion: Occlusion Analysis for Wilderness Mapping
Burak Ekim, Michael Schmitt
Jointly harnessing complementary features of multi-modal input data in a common latent space has been found to be beneficial long ago. However, the influence of each modality on th…
MapInWild: A Remote Sensing Dataset to Address the Question What Makes Nature Wild
Burak Ekim, Timo T. Stomberg, Ribana Roscher +1
Antrophonegic pressure (i.e. human influence) on the environment is one of the largest causes of the loss of biological diversity. Wilderness areas, in contrast, are home to undist…
A Multi-Task Deep Learning Framework for Building Footprint Segmentation
Burak Ekim, Elif Sertel
The task of building footprint segmentation has been well-studied in the context of remote sensing (RS) as it provides valuable information in many aspects, however, difficulties b…