Explainable AI Methods for Remote Sensing Images Interpretation
A special issue of Remote Sensing (ISSN 2072-4292). This special issue belongs to the section "Remote Sensing Image Processing".
Deadline for manuscript submissions: 30 June 2026
Special Issue Editors
Interests: explainable artificial intelligence; signal processing; nonlinear systems; non Gaussian statistics; sea surface remote sensing
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
(1) Introduction, including scientific background and highlighting the importance of this research area.
The ability of neural networks to design highly nonlinear frontiers between data samples and thus achieve high performances for a wide range of tasks, from classification to image pairing, has been known for several decades. In recent years, due to the increase in computational capability, these performances have reached such a level that they are (and will be) difficulty tied by unsupervised approaches. However, the difficult understanding of the decision-making mechanisms has raised several concerns, from distrust of the results to the difficulty in improving these results (for instance to be able to detect biases in training databases). Explainable Artificial Intelligence (XAI) aims to bridge theses gaps. This is especially true in the remote sensing domain, in which comprehension of the images/data requires a certain level of expertise (for instance radar images) increasing the complexity of the answers provided by XAI. In fact, XAI sits at the crossroads of applied mathematics and cognitive science. Additionally, the first XAI aim is to develop algorithms (jointly or after the NN training) extracting the features and their combination in the decision-making process (for only one sample or for the entire database) of a Neural network, and secondly to design explanations according to a social context that is the requirements and the cognitive biases of the human being.
(2) Aim of the Special Issue and how the subject relates to the journal scope.
This Special Issue aims to propose the updated breakthroughs in the understanding of the AI results in the remote sensing domain. It seeks to advance the development of transparent, robust, and human-understandable AI models that not only deliver accurate results but also provide clear explanations for their predictions. The subject is central to the journal's scope, which focuses on innovative methodologies and technological breakthroughs in acquiring, processing, and analyzing remotely sensed data. By fostering research in XAI, this collection will enhance the scientific credibility and practical utility of AI in geospatial sciences.
(3) Suggested themes and article types for submissions.
We welcome submissions on themes including, but not limited to, the following:
- Novel XAI architectures (e.g., attention mechanisms, inherently interpretable models) for remote sensing;
- Post hoc/Ante hoc explanation techniques (e.g., saliency maps, feature attribution, algorithm unwrapping) for satellite and aerial imagery; automatic target recognition, evaluation metrics and benchmarks for XAI in remote sensing;
- Human–computer interaction studies for explanation visualization.
Dr. Jean-Marc Le Caillec
Dr. Didier Gueriot
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
- explainability vs. interpretability
- ante-hoc vs. post-hoc methods
- global vs. local explanations
- model agnostic vs. model specific explanation
- algorithm unwrapping
- target recognition, image/data segmentation, image registration, detection change
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.
