Scholar
Benedikt Blumenstiel
Google Scholar ID: sChSEKwAAAAJ
Research Software Engineer, IBM Research
Citations & Impact
Citations
132
H-index
6
i10-index
3
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- 1. Published paper: TerraCodec: Compressing Earth Observations
- 2. Published paper: TerraMind: Large-Scale Generative Multimodality for Earth Observation
- 3. Published paper: TerraMesh: A Planetary Mosaic of Multimodal Earth Observation Data
- 4. Published paper: Fine-tune Smarter, Not Harder: Parameter-Efficient Fine-Tuning for Geospatial Foundation Models
- 5. Published paper: Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation
- 6. Published paper: Ssl4eo-s12 v1. 1: A multimodal, multiseasonal dataset for pretraining, updated
- 7. Published paper: TerraTorch: The Geospatial Foundation Models Toolkit
- 8. Published paper: Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
- 9. Published paper: Multi-Spectral Remote Sensing Image Retrieval using Geospatial Foundation Models
Research Experience
- 1. TerraMind project: First multimodal generative foundation model for Earth Observation jointly developed with ESA.
- 2. Prithvi EO 2.0 project: Second generation EO foundation model jointly developed with NASA.
- 3. MESS Benchmark: A comprehensive benchmark covering a wide range of real-world applications for multi-modal (i.e., text-to-image) zero-shot semantic segmentation tasks.
Background
- Passionate about machine learning, innovation, and sustainability. Currently working in the AI for Climate Impact Team at IBM Research Zurich, focusing on building multi-modal foundation models for Earth observation and working on climate-related applications using satellite data.
Co-authors