Advancements in Remote Sensing Data Processing with Foundation Models
A Special Issue of Remote Sensing (ISSN 2072-4292) belonging to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 31 March 2027 | Viewed by 83
Editors
Interests: multimodal data processing and system integration
Special Issues, Collections and Topics in MDPI journals
Interests: machine learning and deep learning algorithms; multi-platform remote sensing capabilities
Special Issues, Collections and Topics in MDPI journals
Interests: remote sensing image processing; data fusion; target detection; deep learning
Interests: hyperspectral image processing; object detection; semantic segmentation; deep learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Remote sensing image interpretation has advanced rapidly over the past few years, but a fundamental limitation still remains: most models follow a “one model per task” paradigm, meaning they must be rebuilt from scratch for each new scenario. The need to repeatedly reinvent the wheel has long been recognized as a major obstacle in this field. The emergence of foundational models, however, has opened up a new path—using large-scale pre-training to extract general, transferable features from massive amounts of Earth observation data, which, in theory, can significantly improve an algorithm’s adaptability to different imaging conditions. This approach has already garnered the attention of many remote sensing research teams.
However, remote sensing data present their own set of complexities compared to natural images. Long-standing problems such as multi-source heterogeneity, complex spatial structures, dynamic changes over time, and vast differences between sensors do not automatically disappear simply because models have become larger. There is still no satisfactory answer on how to build a framework that truly leverages the complementary relationships between multimodal data.
Multimodal learning has emerged as a promising research direction. Integrating data from different sensors—such as optical, SAR, infrared, and hyperspectral—significantly aids in scene understanding, detailed target characterization, and long-term environmental monitoring. However, the scarcity of labeled data and the vast range of application scenarios remain inescapable challenges. Consequently, the industry is actively exploring strategies such as parameter-efficient tuning, self-supervised learning, and domain-aware optimization, with the core objective of minimizing reliance on labeled data and enabling models to adapt rapidly to new scenarios.
Deployment is another issue that is very pressing but often overlooked. Computational power and energy on spaceborne platforms are extremely limited; no matter how powerful a model is, it is useless if it cannot run. Various approaches such as compression, distillation, quantization, neuromorphic computing, and hardware-aware design are being explored one by one, with the goal of enabling foundational models to truly operate and make decisions in real time in space.
This Special Issue focuses on large models in remote sensing data processing and welcomes submissions covering theory, methods, and applications.
Dr. Jie Guo
Dr. Frank Zhang
Dr. Yuxuan Zheng
Dr. Yanzi Shi
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.
Keywords
- remote sensing foundation models
- large pre-training models for remote sensing
- multimodal earth observation and data fusion
- self-supervised learning
- vision-language models
- efficient onboard artificial intelligence for remote sensing
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
