Heavy and prolonged rainfall and strong earthquakes trigger landslides causing severe damage to human lives and property. Reliable prediction of landslides is essential for hazard and risk mitigation which can reduce fatalities and economic losses. Physical and machine learning models are the common approaches for assessing landslide modellings. The physical-based model combines susceptibility analysis with soil and rock mechanics, establishing a physical basis for this method. It is a suitable method at a local-scale and requires site-specific geotechnical information. Nevertheless, a machine learning model uses historical landslides (inventories) and conditioning factors through machine learning algorithms. This method is appropriate for regional-scales; however, the availability of adequate training data/inventories and explainability are the main limitations of this method.
These two approaches, in fact, complement each other. The physical-based model is interpretable and offers the capability of extrapolation beyond observed conditions. In contrast, machine learning approaches are highly flexible for data adaptation. The current special issue covers integrated physical and machine learning models for explainable spatial landslide prediction and early warning.
The topics of interest include, but not limited to:
- Designing and developing explainable landslide susceptibility models.
- Evaluating and improving common physical and machine learning landslide prediction models.
- New methodologies for integrated landslide susceptibility modellings.
- Integrated physical models for landslide predictions.
- Explainable landslide deep learning/machine learning modellings.
- Susceptibility assessment and mapping, spatial statistics, and visualization of integrated sensors, data, and information.
- Applications of multi-source remote sensing data and information fusion for landslide modelling.
- Landslide detection and monitoring.
Special Issue Editor:
Professor Biswajeet Pradhan
Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS)
Faculty of Engineering and IT
University of Technology Sydney, Australia
