_version_ 1866917319657127936
author Szwarcman, Daniela
Roy, Sujit
Fraccaro, Paolo
Gíslason, Þorsteinn Elí
Blumenstiel, Benedikt
Ghosal, Rinki
de Oliveira, Pedro Henrique
Almeida, Joao Lucas de Sousa
Sedona, Rocco
Kang, Yanghui
Chakraborty, Srija
Wang, Sizhe
Gomes, Carlos
Kumar, Ankur
Truong, Myscon
Godwin, Denys
Lee, Hyunho
Hsu, Chia-Yu
Lal, Rohit
Asanjan, Ata Akbari
Mujeci, Besart
Shidham, Disha
Keenan, Trevor
Arevalo, Paulo
Li, Wenwen
Alemohammad, Hamed
Olofsson, Pontus
Hain, Christopher
Kennedy, Robert
Zadrozny, Bianca
Bell, David
Cavallaro, Gabriele
Watson, Campbell
Maskey, Manil
Ramachandran, Rahul
Moreno, Juan Bernabe
author_facet Szwarcman, Daniela
Roy, Sujit
Fraccaro, Paolo
Gíslason, Þorsteinn Elí
Blumenstiel, Benedikt
Ghosal, Rinki
de Oliveira, Pedro Henrique
Almeida, Joao Lucas de Sousa
Sedona, Rocco
Kang, Yanghui
Chakraborty, Srija
Wang, Sizhe
Gomes, Carlos
Kumar, Ankur
Truong, Myscon
Godwin, Denys
Lee, Hyunho
Hsu, Chia-Yu
Lal, Rohit
Asanjan, Ata Akbari
Mujeci, Besart
Shidham, Disha
Keenan, Trevor
Arevalo, Paulo
Li, Wenwen
Alemohammad, Hamed
Olofsson, Pontus
Hain, Christopher
Kennedy, Robert
Zadrozny, Bianca
Bell, David
Cavallaro, Gabriele
Watson, Campbell
Maskey, Manil
Ramachandran, Rahul
Moreno, Juan Bernabe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02732
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
Szwarcman, Daniela
Roy, Sujit
Fraccaro, Paolo
Gíslason, Þorsteinn Elí
Blumenstiel, Benedikt
Ghosal, Rinki
de Oliveira, Pedro Henrique
Almeida, Joao Lucas de Sousa
Sedona, Rocco
Kang, Yanghui
Chakraborty, Srija
Wang, Sizhe
Gomes, Carlos
Kumar, Ankur
Truong, Myscon
Godwin, Denys
Lee, Hyunho
Hsu, Chia-Yu
Lal, Rohit
Asanjan, Ata Akbari
Mujeci, Besart
Shidham, Disha
Keenan, Trevor
Arevalo, Paulo
Li, Wenwen
Alemohammad, Hamed
Olofsson, Pontus
Hain, Christopher
Kennedy, Robert
Zadrozny, Bianca
Bell, David
Cavallaro, Gabriele
Watson, Campbell
Maskey, Manil
Ramachandran, Rahul
Moreno, Juan Bernabe
Computer Vision and Pattern Recognition
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.
title Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.02732