Landslide prediction from machine learning

Predicting where and when landslides are likely to occur in a specific region of interest remains a key challenge in natural hazards research and mitigation. While the basic mechanics of slope‐failure initiation and runout can be cast into physical and numerical models, a scarcity of sufficiently detailed and real‐time measurements of soil, rock‐mass and groundwater conditions prohibits accurate landslide forecasting. Researchers are therefore increasingly exploring multivariate data analysis techniques from the fields of data mining or machine learning in order to approximate future occurrences of landslides from past distribution patterns. This work has elucidated patterns of spatial susceptibility, but temporal forecasts have remained largely empirical. Most machine learning techniques achieve overall success rates of 75–95 percent. Whilst this may seem very promising, issues remain with data input quality, potential overfitting and commensurate inadequate choice of prediction models, inadvertent inclusion of redundant or noise variables, and technical limits to predicting only certain types and sizes of landslides. Simpler models provide only slightly inferior predictions to more complex models, and should guide the way for a more widespread application of data mining in regional landslide prediction. This approach should especially be communicated to planners and decision makers. Future research may want to develop: (1) further best‐practice guidelines for model selection; (2) predictions of occurrence and runout of large slope failures at the regional scale; and (3) temporal forecasts of landslides.