Assessing Natural Hazards through Advanced Machine Learning Methods and Remote Sensing Technology: 3rd Edition

Dear Colleagues,

Natural hazards are responsible for severe financial and human losses across the world. These hazards, which include earthquakes, floods, landslides, volcanic eruptions, wildfires, droughts, soil erosion, and degradation, result from progressive or extreme changes in climatic, tectonic, and geo-morphological processes, as well as the impacts of human activities on the geo-environment. Their complex nature, as well as variations in frequency, speed, duration, and the type of areas affected, contribute to the challenges involved in fully understanding the mechanisms behind their evolution and occurrence. The main efforts of scientists from various geophysical disciplines focus on creating conceptual models, developing intelligent computing techniques, and applying machine learning (ML) algorithms, alongside remote sensing (RS) technologies, within a geographic information system (GIS) framework. These efforts aim to capture the complex nature of natural hazards and provide accurate predictions concerning their spatial and temporal occurrences. ML algorithms offer computers a “recipe” for learning from existing data, producing knowledge, and discovering hidden and unknown patterns and trends from large databases. In parallel, GIS emerges as a significant technology equipped with tools for data manipulation and advanced modeling. In recent years, ML methodologies have evolved to include algorithms and methods based on fuzzy and neuro-fuzzy logic, decision tree models, artificial neural networks, deep learning (convolutional neural networks, recurrent neural networks, auto-encoders), ensemble methods (bagging, boosting, stacking), and evolutionary algorithms (ant colony optimization, particle swarm optimization, genetic algorithms). When combined with GIS and RS technology, these methodologies present alternative investigative tools for natural risk phenomena, susceptibility, and hazard mapping. Additionally, the integration of explainable AI (XAI) has become crucial in the field. XAI focuses on making AI systems’ decision-making processes transparent and understandable for humans. This transparency is essential for validating and trusting ML models, especially when predicting and assessing natural hazards where the stakes are high. By incorporating XAI, we can ensure that the models used not only provide accurate predictions but also offer insights into the underlying factors and rationale behind these predictions, fostering greater confidence in and adoption of practical applications. This Special Issue will provide an outlet for peer-reviewed publications that implement state-of-the-art methods and techniques incorporating RS technology, ML methods, GIS, and XAI to map, monitor, evaluate, and assess natural hazards.

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

• Regional or global case studies concerning natural risk phenomena prediction and Assessment;
• Software development and implementation of machine learning, optimization, deep learning techniques, and meta-heuristic algorithms;
• Monitoring, mapping, and assessing earthquakes, landslides, floods, wildfires, soil erosion, and land subsidence;
• Evaluating losses and damages following earthquakes, floods, landslides, wildfires, soil erosion, and land subsidence.

This Special Issue, titled “Assessing Natural Hazards through Advanced Machine Learning Methods and Remote Sensing Technology: 3rd Edition”, seeks to advance the field by integrating innovative techniques and fostering a deeper understanding of natural hazards through explainable AI and other cutting-edge technologies.

We look forward to your contributions.

Dr. Paraskevas Tsangaratos
Dr. Wei Chen
Dr. Ioanna Ilia
Dr. Haoyuan Hong
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.

• earth observation data—remote sensing technology
• geographic information systems
• machine learning and soft computing
• explainable AI in natural hazard prediction
• landslide susceptibility, hazardous, and risk mapping
• flood susceptibility mapping and disaster management
• wildfire susceptibility mapping
• soil erosion/degradation
• earthquakes/tsunamis

• Assessing Natural Hazards through Advanced Machine Learning Methods and Remote Sensing Technology in Remote Sensing (10 articles)
• Assessing Natural Hazards through Advanced Machine Learning Methods and Remote Sensing Technology II in Remote Sensing (12 articles)