Deep Learning for Landslide Detection and Geological Disaster Recognition

Dear Colleagues,

(1) Introduction, including scientific background and highlighting the importance of this research area.

Geological disasters always have direct and high impacts on the development and economic progress of countries all over the world. Landslides are a serious natural disaster next to earthquakes and floods. It is well known that landslides can cause human injury, loss of life, and economic devastation, destroying construction works and causing many other damages. Thus, early landslide detection and prediction play important roles in disaster prevention, disaster monitoring, and several other applications. From another perspective, a huge number of images can now be easily generated by autonomous platforms such as UAVs or satellite sensors, which can contribute to the fast surge in the amount of nonorganized information that may swamp data storage facilities and help in landslide detection and risk analysis. Image analysis and classification in the earth sciences and remote sensing has a successful history that has now taken a huge step forward due to the capability of computers to manage and process big data with artificial intelligence-based approaches. In this regard, deep learning models have recently shown excellent performance in various computer vision and digital image-related applications such as object detection, segmentation, and classification. These breakthroughs in deep learning and related machine learning models have also generated tremendous interest in the computer vision and remote sensing communities to explore deep learning for different topics, including landslide detection and risk analysis.

(2) Aim of the Special Issue and how the subject relates to the journal scope.

This Special Issue aims to address the most up-to-date impacts of deep learning techniques on landslide detection and geological disaster recognition research and serves as a forum for researchers all over the world to discuss their works and recent advancements in the field. Both theoretical studies and state-of-the-art practical applications are welcome for submission. All the submitted papers will be peer-reviewed and selected based on their quality and relevance to the theme of this Special Issue.

(3) Suggested themes and article types for submissions.

Topics of interest include, but are not limited to:

• Hybrid algorithms using evolutionary computation, neural networks, and fuzzy systems for landslide detection;
• Dimensionality reduction of large-scale and complex data and sparse modeling for landslide detection applications;
• Novel deep learning approaches in the application of image/signal processing related to landslide detection and geological disaster recognition;
• Trends in computer vision for landslide detection and geological disaster recognition;
• Deep learning-based approaches for geological hazards analysis: data, models, and applications;
• Landslide detection using randomization-based deep and shallow learning techniques;
• Attention-based feature fusion in deep neural networks for detecting/recognizing occluded objects and semantic segmentation;
• Graph convolutional networks/graph neural networks-based weakly supervised learning approaches for landslide detection;
• Effective feature fusion in deep neural networks for detecting/recognizing small objects;
• Deep learning for 3D scene understanding, stereo vision, decision making, reconstruction, and object detection;
• Deep learning for landslide detection of hyperspectral remote sensing data;
• Earthquake-triggered landslide detection from multispectral sentinel-2 imagery;
• Review remote sensing methods for landslide detection.

Dr. Mahmoud Hassaballah
Dr. Parvathaneni Naga Srinivasu
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. Sensors 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 2600 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.

• landslide detection
• geological disaster recognition
• remote sensing
• object detection and recognition
• machine learning
• deep learning
• evolutionary computation
• neural networks