Machine Learning of Remote Sensing Imagery for Land Cover Mapping

Dear Colleagues,

Land cover is a fundamental input for territorial spatial planning and Earth system modeling and plays a critical supporting role in national development as well as scientific research. Land cover mapping, the primary approach for obtaining land cover information, relies heavily on the rapid and large-scale surface information acquisition capabilities of Earth observation through remote sensing.

In recent years, machine learning methods, such as support vector machines, probabilistic topic models, and deep learning, have achieved remarkable progress in visual image understanding, further advancing the theoretical framework and methodological paradigm of remote sensing-based land cover mapping. Current approaches often exploit the inherent characteristics of different remote sensing data modalities (including visible, hyperspectral, thermal infrared, SAR imagery, and LiDAR point clouds) by introducing suitable machine learning techniques and designing specific workflows for land cover mapping or thematic mapping of particular land cover types. These mapping results are then applied to the analysis of human settlements, to ecological civilization development, and to addressing global and national ecological security needs.

This Special Issue will bring together original research and review articles focusing on machine learning methods for land cover mapping with remote sensing data across diverse application scenarios. We welcome contributions covering all modalities of remote sensing data, all types of machine learning methods, and their applications in geography, ecology, and environmental studies. Research on multimodal remote sensing data fusion, cross-modal adaptation for land cover mapping, and novel machine learning methodologies is also encouraged.

Topics of interest include, but are not limited to, the following:

• Land cover mapping;
• Pattern recognition;
• Land cover classification;
• Land cover product assessment;
• Deep learning;
• Remote sensing foundation model;
• Generative AI;
• Domain adaptation;
• Hyperspectral image classification;
• SAR image classification;
• Three-dimensional point cloud classification;
• Thermal infrared remote sensing;
• Remote sensing image information extraction;
• Thematic mapping with remote sensing;
• Multimodal data fusion;
• Urban sustainability;
• Land use classification;
• Land use planning.

Dr. Huan Ni
Dr. Yue Chang
Dr. Na Liu
Dr. Yifu Ou
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.