Journal Article

FZJ-2025-05777

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications

Szwarcman, D. ; Roy, S. (Corresponding author) ; Fraccaro, P. (Corresponding author) ; Gíslason, O. E. ; Blumenstiel, B. ; Ghosal, R. ; De Oliveira, P. H. ; Almeida, J. L. d. S. ; Sedona, R.FZJ* ; Kang, Y. ; Chakraborty, S. ; Wang, S. ; Gomes, C. ; Kumar, A. ; Gaur, V. ; Truong, M. ; Godwin, D. ; Khallaghi, S. ; Lee, H. ; Hsu, C.-Y. ; Asanjan, A. A. ; Mujeci, B. ; Shidham, D. ; Balogun, R. O. ; Kolluru, V. ; Keenan, T. ; Arevalo, P. ; Li, W. ; Alemohammad, H. ; Olofsson, P. ; Mayer, T. ; Hain, C. ; Kennedy, R. ; Zadrozny, B. ; Bell, D. ; Cavallaro, G.FZJ* ; Watson, C. ; Maskey, M. ; Ramachandran, R. ; Moreno, J. B.

2025
IEEE New York, NY

This record in other databases:  

Please use a persistent id in citations: doi:10.1109/TGRS.2025.3642610  doi:10.34734/FZJ-2025-05777

Abstract: This paper presents Prithvi-EO-2.0, a new geospatial foundation model that offers significant improvements over its predecessor, Prithvi-EO-1.0. Trained on 4.2 million global time series samples from NASA’s Harmonized Landsat and Sentinel-2 data archive at 30-m resolution, the new model incorporates temporal and location embeddings for enhanced performance across various geospatial tasks. Through extensive benchmarking with GEO-Bench, the model outperforms the previous Prithvi-EO model by 8% across a range of tasks. It also outperforms six other geospatial foundation models when benchmarked on remote sensing tasks from different domains and resolutions (i.e. from 0.1 m to 15 m). The results demonstrate the versatility of the model in both classical Earth observation and high-resolution applications. Early involvement of end-users and subject matter experts (SMEs) allowed constant feedback on model and dataset design, enabling customization across diverse SME-led applications in disaster response, land cover and crop mapping, and ecosystem dynamics monitoring. Prithvi-EO-2.0 is available as an open-source model on Hugging Face and IBM TerraTorch, with additional resources on GitHub. The project exemplifies the Trusted Open Science approach embraced by all involved organizations.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)

---

Database coverage:
; ; ; Clarivate Analytics Master Journal List ; Current Contents - Engineering, Computing and Technology ; Ebsco Academic Search ; SCOPUS ; Science Citation Index ; Science Citation Index Expanded ; Web of Science Core Collection

---