4 papers
Localized, High-resolution Geographic Representations with Slepian Functions
Arjun Rao, Ruth Crasto, Tessa Ooms +3
Geographic data is fundamentally local. Disease outbreaks cluster in population centers, ecological patterns emerge along coastlines, and economic activity concentrates within coun…
Measuring the Intrinsic Dimension of Earth Representations
Arjun Rao, Marc RuÃwurm, Konstantin Klemmer +1
Within the context of representation learning for Earth observation, geographic Implicit Neural Representations (INRs) embed low-dimensional location inputs (longitude, latitude) i…
Using Multiple Input Modalities Can Improve Data-Efficiency and O.O.D. Generalization for ML with Satellite Imagery
Arjun Rao, Esther Rolf
A large variety of geospatial data layers is available around the world ranging from remotely-sensed raster data like satellite imagery, digital elevation models, predicted land co…
Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models
Arjun Rao, Hanieh Alipour, Nick Pendar
This paper presents a comparison of embedding models in tri-modal hybrid retrieval for Retrieval-Augmented Generation (RAG) systems. We investigate the fusion of dense semantic, sp…