Backward automatic calibration for three-dimensional landslide models

Back-analysis is broadly used for approaching geotechnical problems when monitoring data are available and information about the soils properties of poor quality. For landslide stability assessment back-analysis calibration usually carried out by time consuming trial-and-error procedure. This paper presents a new automatic Decision Support System that supports selection soil parameters three-dimensional models landslides based on data. The method considering pool possible solutions, generated through permutation parameters, selects best ten configurations more congruent with measured displacements. reduces operator biases while other hand allows to control each step computation. final preferred solution among best-fitting solutions an operator. necessary as he may include in decision process all qualitative elements cannot be included analysis but nevertheless characterize dynamic whole epistemological subject, example base geomorphological evidence. A located Northeast Italy has been selected showing system potentiality. proposed straightforward, scalable robust could useful researchers practitioners. • Back dependent procedure, trial error. Most machine learning techniques auto-calibration opaque. We define procedure calibration, non-opaque identification small set optimal solutions. not considered optimization conserved. presented robust, scalable.