Multimodal Learning and Explainable AI for Remote Sensing Image Interpretation

Dear Colleagues,

With the development of modern space technology, remote sensing imagery has become increasingly prevalent. However, significant variances in radiometric and spatial properties across various types of remote sensing imagery pose major challenges for accurate image interpretation. Multimodal machine learning, which aims to process and integrate information from diverse modalities, offers a promising solution through machine learning approaches. Multimodal learning for the interpretation of remote sensing imagery is an emerging field in earth observation and computer vision. Given that multiple modalities contribute unequally to the final prediction, explainable AI will be necessary to elucidate their predicted contribution and identify potential biases in remote sensing image interpretation.

Multimodal machine learning remains demanding in the context of rapidly evolving remote sensing, and the complexity of current models often leads to limited explicability and transparency. This Special Issue aims to explore the recent advances, challenges, and practical applications of multimodal learning and explainable AI for interpreting multisource remote sensing imagery. Contributions may address new theories, methodologies, or applications of multimodal learning for the processing and analysis of remote sensing data, along with related challenges and opportunities.

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

• Multimodal Fusion Architectures for Heterogeneous Remote Sensing Data;
• Cross-Modal Alignment, Registration Representation, and Translation Learning;
• Interpretable Multimodal Learning Frameworks in Remote Sensing;
• Explainable AI Techniques for Transparent Multisource Data Interpretation;
• Research on Multimodal Remote Sensing Image Matching;
• Domain Adaptation and Cross-Modal Transfer Learning for Remote Sensing Data;
• Multimodal Data Reconstruction and Quality Enhancement with Explainable Fusion Strategies;
• Application of Multimodal Machine Learning for Earth Observation: Case Studies in Land Use, Ecosystem Monitoring, and Disaster Response;
• Environmental Monitoring with Multimodal Learning Technology;
• Benchmarks, Datasets, and Evaluation Metrics for Multimodal Remote Sensing.

Dr. Le Yang
Prof. Dr. Xiaoli Ding
Dr. Lei Shi
Dr. Yuchen Li
Dr. Weidong Sun
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.