About this Research Topic
Natural hazards, due to their unexpected nature, often cause large financial and human losses. The damage caused by different natural risk phenomena like floods, flash-floods, droughts, landslides, gully erosion, forest fires or earthquake can cause severe economic damage 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 the intelligent computing techniques, the machine learning and geographic information system (GIS) models have been widely used, to solve many real-world problems related with different natural hazards and to create efficient susceptibility maps. In recent years, new advanced techniques like machine learning and deep learning have been developed and many new hybrid models were proposed for natural risk phenomena susceptibility mapping. It should be noted that the hybrid models are generated from the combination of multiple stand-alone algorithms like 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, also created is a huge database regarding the severity of the future natural phenomena that the responsible authorities should use in order to mitigate the effect of these hazards.
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 severity of damages that could be generated in the future. Also, 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 above-mentioned aspects, the main aim of this Research Topic 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 the 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 well as Review articles.
Potential topics of interest include but are not limited to the following:
• Real-world case studies in Natural Risk Phenomena Prediction and Assessment such as geo-hazards like landslides, flash-floods, floods, droughts, soil erosion and degradation and related issues;
• Software development that promotes the application of data mining in Natural Hazards Prediction and Assessment;
• Cutting-edge data mining methods, such as machine learning, optimization, deep learning techniques, and meta-heuristic algorithms for data mining in Natural Hazards Prediction and Assessment;
• Data mining techniques, including classification, association, outlier detection, clustering, regression, and prediction, for decision-making, in Natural Hazards Prediction and Assessment.
We would like to acknowledge Dr. Mohammadtaghi Avand has acted as coordinator and has contributed to the preparation of the proposal for this Research Topic.
Keywords: natural hazards, hybrid integration techniques, artificial intelligence approaches, 3S, Spatial modeling
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.