14 papers
Now We Know? A Systematic Comparison of TerraMind and THOR
Frederick Schindlegger, Kenzo Bounegta, Eva Gmelich Meijling +5
Benchmarks for Geospatial Foundation Models (GFMs) increasingly rank models by aggregate score, but such rankings obscure why models differ: how much of the gap is architecture, ho…
SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation
VÃctor Barreiro, Johannes Jakubik, Francisco Argüello +1
Fine-tuning foundation models for Earth Observation is computationally expensive, with high training time and memory demands for both training and deployment. Parameter-efficient m…
TerraMind: Large-Scale Generative Multimodality for Earth Observation
Johannes Jakubik, Felix Yang, Benedikt Blumenstiel +13
We present TerraMind, the first any-to-any generative, multimodal foundation model for Earth observation (EO). Unlike other multimodal models, TerraMind is pretrained on dual-scale…
How to Embed Matters: Evaluation of EO Embedding Design Choices
Luis Gilch, Isabelle Wittmann, Maximilian Nitsche +3
Earth observation (EO) missions produce petabytes of multispectral imagery, increasingly analyzed using large Geospatial Foundation Models (GeoFMs). Alongside end-to-end adaptation…
Spectral Gaps and Spatial Priors: Studying Hyperspectral Downstream Adaptation Using TerraMind
Julia Anna Leonardi, Johannes Jakubik, Paolo Fraccaro +1
Geospatial Foundation Models (GFMs) typically lack native support for Hyperspectral Imaging (HSI) due to the complexity and sheer size of high-dimensional spectral data. This study…
TerraFlow: Multimodal, Multitemporal Representation Learning for Earth Observation
Nazar Puriy, Johannes Jakubik, Benedikt Blumenstiel +1
We propose TerraFlow, a novel approach to multimodal, multitemporal learning for Earth observation. TerraFlow builds on temporal training objectives that enable sequence-aware lear…