Foundation Model-Based Multi-Modal Data Fusion in Remote Sensing

Dear Colleagues,

The rapid expansion of Earth observation systems has led to an unprecedented availability of heterogeneous remote sensing data, such as optical, hyperspectral, LiDAR, and synthetic aperture radar (SAR). These modalities provide complementary spatial, spectral, geometric, and temporal information, making multi-modal data fusion essential for accurate and robust environmental monitoring and geospatial analysis. Traditional fusion strategies, from statistical learning to convolutional neural networks (CNNs), have achieved notable progress but often struggle to model long-range dependencies and complex cross-modal interactions. Transformer-based architectures, leveraging self-attention mechanisms and global context modeling, offer a powerful alternative. Their capability to capture multi-scale dependencies and adaptively integrate heterogeneous representations has positioned them as a promising framework for next-generation multi-modal fusion in remote sensing.

This Special Issue aims to provide a dedicated platform for advances in foundation model-based multi-modal data fusion methodologies and their applications in remote sensing. We welcome contributions addressing theoretical developments, novel architectures, cross-modal representation learning, large-scale training strategies, and real-world applications across land, ocean, and atmospheric domains. This topic directly aligns with the scope of Remote Sensing, particularly in methodological innovation, advanced data processing, artificial intelligence in Earth observation, and interdisciplinary geospatial applications. By bridging deep learning theory and practical remote sensing challenges, this Special Issue seeks to foster scalable, generalizable, and operationally relevant solutions for the remote sensing community.

Articles may address, but are not limited, to the following topics:

• Foundation model-based data fusion;
• Cross-modal learning;
• Attention mechanisms in remote sensing;
• Multi-modal representation learning;
• Spatio-temporal transformers;
• Foundation models for Earth observation;
• Multi-resolution fusion;
• Cross-sensor Domain adaptation;
• Large-scale model training;
• Benchmark datasets;
• Applications in land cover, urban, disaster, agriculture, and climate studies.

Dr. Xianping Ma
Dr. Xiaokang Zhang
Dr. Zhen Wang
Dr. Jiaxin Li
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.