Dear Colleagues,

Natural hazards, due to their unexpected nature, often cause a lot of financial and human losses. The damages caused by different natural risk phenomena such as floods, flash-floods, droughts, landslides, gully erosion, forest fires or earthquake can cause severe economic damages and loss of human life. Moreover, these phenomena may negatively influence the economic and social development of many countries across the world, and therefore, an efficient management of these natural hazards is mandatory. In this regard, an accurate prediction of the areas that are susceptible to being affected in the future by these natural risk phenomena has a great importance. Along with the general development of intelligent computing techniques, in recent years, machine learning and geographic information system (GIS) models have been widely used to solve many real-world problems related to different natural hazards and to create efficient susceptibility maps. In recent years, new advanced techniques such as machine learning and deep learning have been developed, and also, many new hybrid models have been proposed for natural risk phenomenon susceptibility mapping. It should be noted that hybrid models are generated from the combination of multiple standalone algorithms such as those belonging to bivariate statistics, multicriteria decision making analysis, and artificial intelligence. Along with the cartographic representation achieved through the application of these modern algorithms, there is also a huge database regarding the severity of the future natural phenomena that the responsible authorities should use in order to mitigate the negative effects. Although these techniques have been and are being applied in many areas of the world, we consider that a significant increase of such studies is still needed in many areas exposed to natural hazards in order to give a more complete and correct image on the size damages that could be generated in the future. Additionally, the diversification of the methods of analysis is very necessary for estimating the potentially affected areas as accurately as possible. It should be mentioned that these studies will become more and more important in the context of global climate change, because apart from earthquakes, almost all other hazards are closely related to these changes at the planetary level.

In the light of the abovementioned aspects, the main aim of this Special Issue is to collect state-of-the-art research findings on the latest developments and challenges in the field of data mining and GIS intended to evaluate susceptibility to natural risk phenomena. High-quality original research papers that present theoretical frameworks, methodologies, and application of case studies from a single- or cross-country perspective are welcome, as are review articles.

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

• Real-world case studies in natural risk phenomenon prediction and assessment such as geohazards like landslides, flash-floods, floods, droughts, soil erosion and degradation, and related issues;
• Software development that promotes the application of data mining in natural hazard prediction and assessment;
• Cutting-edge data mining methods, such as machine learning, optimization, deep learning techniques, and metaheuristic algorithms for data mining in natural hazard prediction and assessment;
• Data mining techniques, including classification, association, outlier detection, clustering, regression, and prediction, for decision making, in natural hazard prediction and assessment.

Dr. Romulus Costache
Dr. Mohammadtaghi Avand
Dr. Gabriel Minea
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. Geosciences is an international peer-reviewed open access monthly 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 1800 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.

• Natural risk phenomena
• Susceptibility mapping
• Machine learning
• Bivariate statistics
• Multicriteria decision making
• Hybrid models
• Geographic information system (GIS)