Abstract
Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.
| Original language | English |
|---|---|
| Pages (from-to) | 190-215 |
| Number of pages | 26 |
| Journal | IEEE Geoscience and Remote Sensing Magazine |
| Volume | 13 |
| Issue number | 3 |
| DOIs | |
| State | Published - 2025 |
Funding
This work was supported by NSF 2419793, HAA-293452-23, Vanderbilt Seeding Success Grant, Vanderbilt Discovery Grant, and VISR Seed Grant. We extend gratitude to NVIDIA for their support by means of the NVIDIA hardware grant. This work was also supported by NSF NAIRR Pilot Award NAIRR240055. This manuscript has been coauthored by ORNL, operated by UT-Battelle, LLC under Contract DE-AC05-00OR22725 with the U.S. Department of Energy. James R. Zimmer-Dauphinee (james.r.zimmer-dauphinee@ vanderbilt.edu) received his B.A. degree in anthropology and his B.S. degree in mathematics from Georgia Southern University in 2011, his M.A. degree in anthropology from the University of Arkansas in 2014, and his Ph.D. degree in anthropology from Vanderbilt University in 2023. He is currently a postdoctoral fellow in the Spatial Analysis Research Laboratory, Vanderbilt University, Nashville, TN 37235 USA, funded by the GeoPACHA 2.0 Grant from the National Endowment for the Humanities. His research interests include developing deep learning models for large-scale autonomous archaeological satellite imagery surveys, geophysical methods, and spatial modeling to understand the impact of colonization on indigenous peoples.