Transfer learning for landslide susceptibility modelling using domain adaptation and case-based reasoning.

Transferability of knowledge from well-investigated areas to a new study region is gaining importance in landslide hazard research. Considering the time-consuming compilation of landslide inventories as a prerequisite for landslide susceptibility mapping, model transferability can be key to making hazard-related information available to stakeholders in a timely manner. In this paper, we compare and combine two important transfer-learning strategies for landslide susceptibility modelling: case-based reasoning (CBR) and domain adaptation (DA). CBR gathers knowledge from previous similar situations (source areas) and applies it to solve a new problem (target area). DA, which is widely used in computer vision, selects data from a source area that has a similar distribution to the target area. We assess the performances of single- and multiple-source CBR, DA and CBR-DA strategies to train and combine landslide susceptibility models using generalized additive models (GAMs) for 10 study areas with various resolutions (1 m, 10 m and 25 m) located in Austria, Ecuador, and Italy. The performance evaluation shows that CBR and combined CBR-DA based on our proposed similarity criterion was able to achieve performances comparable to benchmark models trained in the target area itself. Particularly the CBR strategies yielded favourable results in both single- and multi-source strategies. DA tended to have overall lower performances than CBR; yet, it had promising results in scenarios when the source-target similarity was low. We recommend that future transfer learning research for landslide susceptibility modelling can build on the similarity criterion we used, as it successfully helped to achieve landslide susceptibility model transfers by discovering suitable training datasets from various regions. [ABSTRACT FROM AUTHOR]