Artificial Intelligence Remote Sensing for Earth Observation

Dear Colleagues,

Remote sensing imaging captures electromagnetic radiation across various wavelengths, producing multimodal images with rich information. Consequently, remote sensing images have a wide range of applications in Earth observation, including environmental monitoring, agriculture, urban planning, and geological exploration. The development of artificial intelligence (AI) presents both opportunities and challenges for remote sensing-based Earth observations. Over the past decade, researchers have observed significant advancements in remote sensing image processing techniques driven by deep learning.

In recent years, the field of AI has experienced new developments. The remarkable success of ChatGPT has sparked a renewed wave of interest in AI, and advancements in visual language models (VLMs) have pushed this enthusiasm to new heights. Similar to previous developments, remote sensing is also embracing these new advancements and reaching a new level. Technological advancements have enabled us to design more efficient and lightweight AI models to handle specific remote sensing tasks. These advancements even allow us to move beyond traditional discriminative models, using a generative paradigm to solve problems that were previously impossible to model. However, the application of new technologies such as Mamba, TTT, and VLM in the field of remote sensing is still relatively limited. At the same time, the use of these new technologies also needs to overcome certain challenges unique to the field of remote sensing, such as modality gaps and resolution differences. Therefore, more effort should be paid to exploiting advanced AI techniques, e.g., CLIP, VLM, Mamba, and large-foundation modelling, facilitating the wide application of remote sensing images.

For this Special Issue, we encourage submissions that utilise advanced AI techniques to address remote sensing image processing tasks. This includes both traditional tasks such as image segmentation and fusion, and emerging tasks such as remote sensing-based visual question answering (VQA) and AI for scientific applications.

This Special Issue welcomes high-quality submissions that provide the community with the most recent advancements in remote sensing for Earth observation, including but not limited to the following:

• Spatial and spectral remote sensing image super-resolution;
• Remote sensing image segmentation/classification;
• Multimodal remote sensing image fusion;
• Remote sensing object detection;
• Contrastive language and remote sensing image pretraining;
• Remote sensing image-based visual language model for Earth observation;
• Other topics on applications of remote sensing for Earth observation.

Prof. Dr. Haokui Zhang
Prof. Dr. Jie Feng
Dr. Xizhe Xue
Dr. Chen Ding
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 100 words) can be sent to the Editorial Office for announcement on this website.

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.

• image super-resolution
• image segmentation
• image classification
• multimodal fusion
• language–image contrastive learning
• visual language model