Research Topic

Spatial Modelling of Natural Hazards Based on Deep Learning and Ensemble Learning Methods

About this Research Topic

Human society is facing more and more threats of natural hazards, which cause major socio-economic consequences. Effective and accurate natural hazard modeling is very helpful to systematically construct hazard-resistant and sustainable human settlements, thereby reducing the possibility and vulnerability of ...

Human society is facing more and more threats of natural hazards, which cause major socio-economic consequences. Effective and accurate natural hazard modeling is very helpful to systematically construct hazard-resistant and sustainable human settlements, thereby reducing the possibility and vulnerability of people to extreme hazards.

Deep learning methods, such as deep belief networks, convolutional neural networks, recurrent neural networks and generative adversarial networks, can learn higher and more abstract representations from raw data by composing simple but non-linear modules. With powerful representation extraction capabilities, deep learning methods are very good at discovering intricate structures and learn very complex functions from high-dimensional data. For natural hazards, the triggering mechanism is very complicated, and there are many factors related to the hazard. Therefore, deep learning methods have the ability to effectively capture the high-level characteristics of natural hazards and model their occurrence and development. Although some researchers have used deep learning methods for natural hazards modeling, a lot of studies are still needed to further explore the application potential of these methods.

Ensembles are well-established machine learning techniques that can obtain more accurate prediction results by integrating various base learners. Ensemble learning techniques involving homogeneous and heterogeneous ensembles use multiple learning algorithms to obtain powerful models, which show better performance than any constituent learning algorithm alone. The novel techniques mentioned previously have strong generalization capabilities and can solve various complex scenarios of natural hazard modeling.

The main objective of this Research Topic is to provide a forum to promote the successful use of deep learning and ensemble learning techniques in natural hazard modeling.

The Research Topic aims to provide an outlet for peer-reviewed publications that uses deep learning and ensemble learning methods to detect, map and assess natural hazards. The Research Topic aims to cover but not limited to the following areas:

- Detection, mapping, and assessing debris flows, landslides, floods, and wildfires
- Natural hazard and risk analysis
- Evaluating losses and damages after natural hazards
- Spatial and temporal modeling of natural hazards


Keywords: deep learning, ensemble learning, susceptibility, hazard and risk mapping, dynamic analysis, hazard detection


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.

Recent Articles

Loading..

About Frontiers Research Topics

With their unique mixes of varied contributions from Original Research to Review Articles, Research Topics unify the most influential researchers, the latest key findings and historical advances in a hot research area! Find out more on how to host your own Frontiers Research Topic or contribute to one as an author.

Topic Editors

Loading..

Submission Deadlines

23 July 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..

Topic Editors

Loading..

Submission Deadlines

23 July 2021 Manuscript

Participating Journals

Manuscripts can be submitted to this Research Topic via the following journals:

Loading..
Loading..

total views article views article downloads topic views

}
 
Top countries
Top referring sites
Loading..