Efficient Representation Learning in Hyperspectral Remote Sensing: Dimensionality Reduction Methods and Intelligent Interpretation Applications
A Special Issue of Remote Sensing (ISSN 2072-4292) belonging to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 31 December 2026 | Viewed by 148
Editors
Interests: machine learning; hyperspectral image processing
Interests: hyperspectral image processing; imaging science and photographic technology; underwater robotics
Special Issue Information
Dear Colleagues,
Hyperspectral remote sensing captures continuous and fine-grained spectral responses of ground objects, providing critical information for characterizing surface properties, spatial patterns, and environmental dynamics. Recent advances in sensor technology and artificial intelligence have promoted a methodological shift from conventional feature engineering and empirical modeling toward efficient representation learning, intelligent interpretation, and knowledge discovery in complex remote sensing scenarios.
Despite these advances, extracting reliable and transferable information from hyperspectral observations remains challenging due to the intrinsic complexity of spectral–spatial structures, data distribution discrepancies, and limited model generalization. Efficient representation learning is therefore essential for improving the discriminability, robustness, and interpretability of hyperspectral analysis. Related research covers dimensionality reduction, feature learning, spectral–spatial modeling, deep learning, self-supervised learning, domain adaptation, multimodal fusion, and application-driven intelligent interpretation.
This Special Issue focuses on efficient representation learning and intelligent interpretation in hyperspectral remote sensing. It welcomes studies on theoretical methods, model design, algorithm optimization, data fusion, task adaptation, and application validation, with the aim of promoting efficient data representation, intelligent understanding, and practical applications in complex remote sensing scenarios. This topic aligns well with the scope of Remote Sensing by addressing advanced remote sensing methods, image processing, data analysis, and application-oriented Earth observation through efficient hyperspectral representation and intelligent interpretation.
This Special Issue welcomes original research articles and reviews on efficient representation learning, dimensionality reduction, and intelligent interpretation in hyperspectral remote sensing. Topics of interest include, but are not limited to:
* Efficient representation learning for hyperspectral imagery;
* Band selection and feature extraction;
* Spectral-spatial feature modeling and semantic representation;
* Deep learning, self-supervised learning, and foundation models for hyperspectral analysis;
* Domain adaptation, transfer learning, and generalizable hyperspectral interpretation;
* Graph learning, attention mechanisms, and transformer-based methods;
* Lightweight, efficient, and deployable hyperspectral interpretation models;
* Explainable and physically informed hyperspectral learning methods;
* Intelligent applications such as classification, target detection, anomaly detection, unmixing, change detection, and environmental monitoring.
Dr. Xiaodi Shang
Dr. Xudong Sun
Dr. Xiaopeng Wang
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
- hyperspectral remote sensing
- dimensionality reduction
- representation learning
- intelligent interpretation
- machine learning
- deep learning
- image classification
- target detection
- band selection
- feature extraction
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.
