Two examples of expert knowledge based system for avalanche forecasting and protection

Buisson, Laurent; Giraud, G.

doi:10.1007/bf00665742

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Buisson and Charlier (1993) showed an approach for the analysis of the characteristics of avalanche paths (ELSA). An approach for the forecasting of the avalanche triggering probability (SAFRAN-CROCUS-MEPRA) was demonstrated by Buisson and Giraud (1995) and Durand et al (1999). Kleemayr et al (2000) developed a numerical avalanche prediction model (NAFT) based on the combination of statistical analysis, artificial neural networks and a fuzzy-expert system.…”

Section: Introductionmentioning

confidence: 99%

Modelling the system behaviour of wet snow avalanches using an expert system approach for risk management on high alpine traffic roads

Zischg¹,

Fuchs²,

Keiler

et al. 2005

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. The presented approach describes a model for a rule-based expert system calculating the temporal variability of the release of wet snow avalanches, using the assumption of avalanche triggering without the loading of new snow. The knowledge base of the model is created by using investigations on the system behaviour of wet snow avalanches in the Italian Ortles Alps, and is represented by a fuzzy logic rule-base. Input parameters of the expert system are numerical and linguistic variables, measurable meteorological and topographical factors and observable characteristics of the snow cover. Output of the inference method is the quantified release disposition for wet snow avalanches. Combining topographical parameters and the spatial interpolation of the calculated release disposition a hazard index map is dynamically generated. Furthermore, the spatial and temporal variability of damage potential on roads exposed to wet snow avalanches can be quantified, expressed by the number of persons at risk. The application of the rule base to the available data in the study area generated plausible results. The study demonstrates the potential for the application of expert systems and fuzzy logic in the field of natural hazard monitoring and risk management.

show abstract

Section: Introductionmentioning

confidence: 99%