Remote Sensing Spatiotemporal Fusion with Deep and Generative Models
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 28 February 2027 | Viewed by 109
Special Issue Editors
Interests: remote sensing image processing; image/video super-resolution; object recognition; quantitative remote sensing inversion
2. University of Chinese Academy of Sciences, Beijing 100049, China
Interests: spatial–temporal–spectral image fusion; land cover land use change; lakeshore remote sensing
Special Issue Information
Dear Colleagues,
Satellite remote sensing inherently suffers from a fundamental trade‑off between the spatial and temporal resolution of a single sensor. Spatiotemporal fusion (STF) aims to overcome this limitation by blending high‑spatial but low‑temporal resolution imagery (e.g., Landsat/Sentinel-2) with high‑temporal but low‑spatial imagery (e.g., MODIS/Sentinel-3), thereby generating high-spatiotemporal resolution Earth observations. Such capability is essential for capturing rapid land surface dynamics and supporting timely environmental monitoring. Over the past decade, deep learning has revolutionized STF, with architectures such as convolutional neural networks (CNNs), Transformers, and increasingly generative models—including generative adversarial networks (GANs), diffusion models, and flow models—demonstrating remarkable capabilities in capturing complex spatiotemporal dynamics and generating high‑fidelity fused images.
This Special Issue invites articles that advance deep and generative models for spatiotemporal image fusion in remote sensing. It seeks to bridge methodological innovation with practical applications, aligning closely with the scope of the journal Remote Sensing in advancing Earth observation science, data fusion techniques, and geospatial analytics. Contributions are expected to address both theoretical advancements and real-world implementations, as well as emerging challenges such as data scarcity, model generalization, uncertainty quantification, and cross-sensor inconsistencies.
We welcome original research articles, reviews, technical notes, and application-oriented studies. Suggested topics include, but are not limited to:
- Deep learning architectures (CNNs, GANs, Transformers, diffusion models) for STF;
- Generative models for time‑series reconstruction, cloud removal, and gap‑filling;
- Multi‑sensor data fusion (optical, SAR, thermal) with generative frameworks;
- Physics‑informed and weakly‑supervised deep learning for STF;
- Spatiotemporal super‑resolution using generative models;
- Benchmark datasets, evaluation metrics, and open‑source implementations;
- Uncertainty analysis and model interpretability;
- Spatial–temporal–spectral fusion;
- Downstream applications of STF in land cover change, environmental monitoring, agriculture, disaster response, etc.
Prof. Dr. Huihui Song
Dr. Yongquan Zhao
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-blind 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
- spatiotemporal fusion
- remote sensing
- deep learning
- generative model
- diffusion model
- generative adversarial network (GAN)
- transformer architecture
- time‑series reconstruction
- multi‑source data fusion
- high-spatiotemporal resolution monitoring
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.
