Advancing Remote Sensing Through Large Multimodal Foundation Models: Toward Intelligent Earth Observation

Dear Colleagues,

Global warming, rapid urbanization and intensifying anthropogenic pressures have ushered in the Anthropocene, marked by interconnected environmental crises—biodiversity loss, extreme weather, land degradation, water scarcity and pollution—that threaten progress toward the UN Sustainable Development Goals (SDGs). Addressing these challenges requires not only comprehensive Earth observation data but also intelligent systems capable of transforming it into actionable, interpretable knowledge across spatiotemporal scales. Remote sensing has long provided synoptic, multi-spectral monitoring of Earth’s systems, yet the current explosion of multimodal data—from optical, SAR, LiDAR, hyperspectral, thermal and in situ sensors—exposes the limitations of traditional, task-specific workflows that lack semantic depth and cross-modal reasoning. Emerging foundation models, including generative large language models (LLMs), multimodal foundation models (MFMs), and AI agents, offer a paradigm shift. Pre-trained on vast, diverse datasets, they enable zero- or few-shot generalization, natural-language interaction, cross-sensor fusion, anomaly detection and even autonomous analysis pipelines. When tailored to Earth observation, these models unlock semantic understanding of landscapes, simulate environmental scenarios and support human-aligned decision-making—critical capabilities for monitoring and managing the coupled human–natural systems of the Anthropocene.

This Special Issue aims to foster interdisciplinary research that bridges cutting-edge AI—particularly generative models, multimodal reasoning, visual-language models and agentic frameworks—with remote sensing. It aligns closely with the journal’s scope by promoting innovative methodologies for RS data processing, interpretation and decision support. We invite original contributions that develop, adapt or benchmark foundation models for RS tasks, design intelligent agents for autonomous analysis or create standardized multimodal datasets and evaluation protocols.

Topics of interest include but are not limited to:

• Multimodal foundation models for remote sensing (e.g., vision-language, vision-SAR, time-series fusion)
• Generative AI for synthetic RS data generation, augmentation and simulation
• LLM- and MFM-powered semantic interpretation and captioning of RS imagery
• AI agents for autonomous RS data acquisition, processing and analysis workflows
• Benchmark datasets and evaluation metrics for multimodal RS reasoning
• Cross-modal alignment and transfer learning in Earth observation
• Applications in multi-sphere Earth system monitoring (e.g., land cover change, water resources, urban dynamics)

Dr. Hao Chen
Dr. Wenyuan Li
Dr. Sen Lei
Dr. Yinxia Cao
Dr. Keyan Chen
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.