Geohazard Mapping, Monitoring and Prediction with Advanced Remote Sensing Techniques

Dear Colleagues,

Geohazards, including landslides, subsidence, and sinkholes, pose significant and increasing threats to global communities and infrastructure, a trend exacerbated by climate change and urban expansion. Traditional ground-based monitoring methods, while valuable, are often spatially limited, costly, and hazardous. The field of remote sensing has revolutionized our ability to address these challenges by providing synoptic, repetitive, and safe observations of the Earth's surface. We now operate in a multi-sensor era: optical imagery offers detailed visual context, interferometric synthetic aperture radar (InSAR) delivers millimeter-scale measurements of surface deformation, and unmanned aerial vehicles (UAVs) capture ultra-high-resolution data for rapid response and detailed site-specific analysis. This powerful combination enables comprehensive geohazard assessment across scales, ranging from regional susceptibility mapping to localized process understanding.

The critical challenge has shifted from data acquisition to intelligent information extraction. This is where machine learning (ML) and deep learning (DL) have become indispensable. The volume and complexity of data from optical, InSAR, and UAV platforms are overwhelming for manual interpretation. ML algorithms can efficiently identify patterns and anomalies within these large datasets, while DL models, particularly convolutional neural networks, automate the precise detection and segmentation of geohazard features such as landslide scars or subsidence bowls. The integration of these AI techniques allows for the fusion of multi-sensor data, transforming raw imagery into actionable intelligence for forecasting slope stability, monitoring infrastructure health, and ultimately developing robust early warning systems, making this a vital and rapidly advancing area of research.

This Special Issue, entitled “Geohazard Mapping, Monitoring and Prediction with Advanced Remote Sensing Techniques”, will collate innovative research that showcases the powerful synergy between multi-sensor remote sensing—encompassing optical, InSAR, and UAV technologies—and modern machine learning and deep learning techniques. We seek to highlight methodologies that move beyond conventional approaches, demonstrating how AI can automate and enhance the analysis of complex geospatial data for improved accuracy, efficiency, and scalability in geohazard applications. This Special Issue will serve as a platform for studies that bridge the gap between advanced data acquisition and intelligent computational analytics.

This focus is directly aligned with the scope of a journal dedicated to Remote Sensing. It underscores the journal's commitment to publishing cutting-edge research that translates technological advancements into practical solutions for risk reduction and sustainable development. By featuring contributions that integrate diverse data sources with state-of-the-art AI, this Special Issue will provide a valuable resource for the scientific community and practitioners, fostering the development of next-generation tools for proactive geohazard management.

Suggested Themes:

• Optical imagery, such as Sentinel-2 and Landsat, for Geohazard Identification and Ecological Recovery monitoring;
• Time-Series InSAR for Deformation Monitoring and/or Trend Forecasting;
• UAV Photogrammetry or LiDAR for High-Resolution 3D Change Detection;
• Machine/Deep Learning for Remote Sensing Data Processing;
• Automated Feature Detection and Classification (e.g., landslides, sinkholes, cracks) using Machine/Deep Learning methods;
• Machine Learning for Geohazard Susceptibility and Vulnerability Mapping;
• Integration of AI Models with Physical Models for Improved Hazard Forecasting;
• Big Data Analytics and Cloud Computing (e.g., Google Earth Engine) for Large-Area Geohazard Assessment;
• Transfer Learning and Semi-Supervised Learning to Address Label Scarcity in Geoscience Applications.

Suggested Article Types:

• Articles: Presenting novel methodologies, integrated workflows, and significant case studies.
• Reviews: Comprehensive overviews of specific sub-fields, such as “A Decade of Deep Learning in Landslide Mapping”.
• Technical Notes: Describing new algorithms, open-source software tools, or curated benchmark datasets.
• Communication: Short communications on breakthrough findings or novel applications.

Dr. Cheng Zhong
Dr. Peng Gao
Dr. Tomaž Podobnikar
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.