Failure Mechanisms, Prediction, and Risk Assessment of Natural and Engineering Disasters through Machine Learning and Numerical Simulation
1Nanchang University, Nanchang, China
2University of Vienna, Vienna, Austria
3University of Newcastle, Newcastle, Australia
4National Technical University of Athens, Athens, Greece
5Chinese Academy of Sciences, Nanchang, China
Failure Mechanisms, Prediction, and Risk Assessment of Natural and Engineering Disasters through Machine Learning and Numerical Simulation
Description
Natural and engineering disasters, which include engineering slope failure, landslides, rock fall, dam failure, floods, earthquakes, road and building disasters, and wildfires, appear as results of the progressive or extreme evolution of climatic, tectonic, and geomorphological processes and human engineering activities. Machine learning, which includes methods that are based on the mathematical concepts of fuzzy and neuro-fuzzy logic, decision tree models, artificial neural networks, deep learning, and evolutionary algorithms, are promising tools to analyse the spatial and temporal occurrence of complex natural and engineering disasters.
Machine learning models are characterised by their ability to produce knowledge and discover hidden and unknown patterns and trends from large databases, whereas remote sensing and geographic information systems (GIS), equipped with tools for data manipulation and advanced mathematical modelling, represent another area of promising technology. With the relentless growth in computing power, numerical simulation techniques have also been acknowledged as advanced mathematical methods capable of discovering hidden instability mechanisms, evolution processes, deformation trends, affecting factors, and risk from natural and engineering disasters.
The main objective of this Special Issue is to provide a scientific forum for advancing the successful implementation of machine learning and numerical simulation techniques in operation rules, failure mechanisms, spatial and time series prediction, susceptibility mapping, hazard assessment, vulnerability modelling, risk assessment, and early warning of complex natural and engineering disasters. We aim to provide an outlet for publications that implement state-of-the-art mathematical methods and techniques incorporating machine learning and/or numerical simulation techniques to analyse, map, monitor, and assess various natural and engineering disasters.
Potential topics include but are not limited to the following:
- Failure mechanisms, reliability analysis, and affecting factors exploration of natural and engineering disasters
- Vulnerability assessment of various hazard-affected bodies, as well as loss and damage evaluation after natural and engineering disasters
- Susceptibility, hazard and risk prediction, and mapping of regional and/or single natural and engineering disasters
- Monitoring, spatial-temporal prediction modelling, and early warning of various disasters using advanced geophysics