Artificial Intelligence and Machine Learning for Multi-Modal and Multi-Spectral Remote Sensing Image Processing

Dear Colleagues,

With the rapid development of remote sensing technology, multimodal and multispectral remote sensing data have become an indispensable source of information in fields such as Earth observation, environmental monitoring, resource management, and disaster emergency response. The fusion of multimodal remote sensing data (such as optical, radar, hyperspectral, infrared) and multispectral information can provide multidimensional and multi-scale surface feature descriptions, significantly enhancing the application value of remote sensing data. However, in the face of massive, heterogeneous, and high-dimensional remote sensing data, traditional image processing methods have limitations, such as their low efficiency, weak generalization, and reliance on manual experience in feature extraction, data fusion, target recognition, and semantic interpretation. In recent years, with the rapid development of artificial intelligence and machine learning technologies—such as convolutional neural networks, Transformers, Mamba, transfer learning, generative adversarial networks (GANs), and diffusion models—new momentum has been injected into remote sensing image processing. For example, deep learning-based end-to-end models can automatically extract spatial spectral joint features of multimodal data, significantly optimizing the accuracy of land cover classification; transfer learning alleviates the high cost of remote sensing data annotation by transferring knowledge across domains; and the diffusion model is used for data augmentation, super-resolution reconstruction, and cross-modal synthesis, effectively improving the robustness of the models. In addition, artificial intelligence technologies such as self-supervised learning, graph neural networks (GNNs), and reinforcement learning have provided more new technological paths for multimodal and multispectral remote sensing image interpretation and inference. This Special Issue aims to focus on cutting-edge research of artificial intelligence and machine learning technology in multimodal and multispectral remote sensing image processing, to promote the deep integration of theory and application, and help remote sensing technology move towards intelligence and automation.

Special Issue Submission Direction

This Special Issue invites scholars from home and abroad to submit articles on topics including, but not limited to, the following:

1. Intelligent fusion and feature extraction of multimodal remote sensing data (optical, SAR, hyperspectral, infrared, etc.).
2. Remote sensing image classification, object detection, and semantic segmentation based on deep learning.
3. Application of small-sample/weakly supervised learning in remote sensing image interpretation.
4. Generative models (such as GAN, diffusion models) and remote sensing data augmentation.
5. Dynamic analysis and prediction of time-series remote sensing data.
6. Intelligent Processing of 3D point clouds and stereoscopic remote sensing images.
7. Edge computing and remote sensing real-time processing system.
8. Research on the credibility of explainable AI and remote sensing models.
9. Innovative applications of multimodal remote sensing in fields such as ecology, agriculture, and disasters.
10. Construction of open-source remote sensing datasets and algorithm frameworks.

Prof. Dr. Tao Lei
Prof. Dr. Tao Gao
Prof. Dr. Lefei Zhang
Prof. Dr. Asoke K. Nandi
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.

• deep learning
• transformer
• diffusion model
• multi-modal remote sensing data
• multi-spectral remote sensing data
• feature representation
• feature fusion
• remote sensing interpretation