arXiv 2412.027322026-03-06cs.CV

Prithvi-EO-2.0：一种用于地球观测应用的多功能多时间基础模型

Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications

IBM Research（IBM研究院）；NASA Marshall Space Flight Center（NASA马歇尔航天飞行中心）；Earth System Science Center（地球系统科学中心）；School of Engineering and Natural Sciences（工程与自然科学学院）；Jülich Supercomputing Centre（julich超级计算中心）；Department of Biological Systems Engineering（生物系统工程系）；School of Geographical Sciences and Urban Planning（地理科学与城市规划学院）；College of Earth, Ocean, and Atmospheric Sciences（地球、海洋与大气科学学院）

Daniela Szwarcman, Sujit Roy, Paolo Fraccaro, Þorsteinn Elí Gíslason, Benedikt Blumenstiel, Rinki Ghosal, Pedro Henrique de Oliveira, Joao Lucas de Sousa Almeid… 展开作者

Daniela Szwarcman, Sujit Roy, Paolo Fraccaro, Þorsteinn Elí Gíslason, Benedikt Blumenstiel, Rinki Ghosal, Pedro Henrique de Oliveira, Joao Lucas de Sousa Almeida, Rocco Sedona, Yanghui Kang, Srija Chakraborty, Sizhe Wang, Carlos Gomes, Ankur Kumar, Myscon Truong, Denys Godwin, Hyunho Lee, Chia-Yu Hsu, Rohit Lal, Ata Akbari Asanjan, Besart Mujeci, Disha Shidham, Trevor Keenan, Paulo Arevalo, Wenwen Li, Hamed Alemohammad, Pontus Olofsson, Christopher Hain, Robert Kennedy, Bianca Zadrozny, David Bell, Gabriele Cavallaro, Campbell Watson, Manil Maskey, Rahul Ramachandran, Juan Bernabe Moreno

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Prithvi-EO-2.0通过多时间序列训练和用户反馈优化，提升了地球观测任务的性能和应用灵活性。

摘要：

本文介绍了Prithvi-EO-2.0，一种新的地理空间基础模型，相较于其前代Prithvi-EO-1.0有显著改进。该模型在NASA的Harmonized Landsat和Sentinel-2数据档案中训练了420万个全球时间序列样本，分辨率为30米。新模型集成了时间和位置嵌入，以在各种地理空间任务中实现更佳性能。通过与GEO-Bench的广泛基准测试，该模型在一系列任务上比之前的Prithvi-EO模型提升了8%。此外，在不同领域和分辨率（即从0.1米到15米）的遥感任务上，该模型也优于六个其他地理空间基础模型。结果表明，该模型在经典地球观测和高分辨率应用中都表现出多功能性。早期用户和领域专家（SMEs）的参与使模型和数据集设计能够持续反馈，从而在灾害响应、土地覆盖和作物制图以及生态系统动态监测等多样化的SME主导应用中实现定制化。Prithvi-EO-2.0作为开源模型可在Hugging Face和IBM TerraTorch上获得，更多资源在GitHub上。该项目体现了所有参与组织所采用的可信开放科学方法。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。