Upon the introduction of machine learning (ML) and its variants, in the form that we know today, to the landslide community, many studies have been carried out to explore the usefulness of ML in landslide research and to look at some classic landslide problems from an ML point of view. ML techniques, including deep learning methods, are becoming popular to model complex landslide problems and are starting to demonstrate promising predictive performance compared to conventional methods. Almost all the studies published in the literature in recent years belong to one of the following three broad categories: landslide detection and mapping, landslide spatial forecasting in the form of susceptibility mapping, and landslide temporal forecasting. In this paper, we present a brief overview of ML techniques, provide a general summary of the landslide studies conducted, in recent years, in the three above-mentioned categories, and make an attempt to critically evaluate the use of ML methods to model landslide processes. The paper also provides suggestions for future use of these powerful data-driven techniques in landslide studies.

An inverse analysis procedure that uses construction monitoring data to update predictions of deformations for supported excavation systems is presented. The numerical procedure is used to optimize the finite element model of a 12.2-m-deep excavation through Chicago glacial clays by minimizing the errors between monitoring data and computed displacements. The field observations are obtained from inclinometer data that measured lateral movements of the soil behind the supporting walls on opposite sides of the excavation throughout construction. Five construction stages are defined for the inverse analysis. At every new construction stage, the inclinometer data relative to that stage are added to the observations already available to “recalibrate” the model of the excavation. The constitutive responses of the soils are represented by the hardening-soil (H-S) model. Of the six basic H-S input parameters, only one parameter per layer is optimized, while the other parameters are either kept constant or related...

The performance of an excavation support system for a subway station renovation project in Chicago and its effects on an adjacent, shallow-foundation supported building are presented. The 13-m-deep excavation was made through soft to medium stiff clays and was supported by a 900-mm-thick secant pile wall, one level of cross-lot bracing, and two levels of tiebacks. Design considerations are discussed and construction procedures are summarized. Field performance data were collected, including lateral soil movements at five locations, building settlements along the exterior wall and interior columns, support system loads, and observations of building damage. As planned in the design, minor damage occurred to nonload bearing portions of the building. Of the 38 mm of maximum lateral movement adjacent to the building, 9 mm occurred during wall installation, 16 mm developed as the soil was excavated, and 13 mm occurred during tunnel demolition and station renovation as a result of soil creep and reduction of wal...