Improvements of Machine Learning-based landslide prediction models can be made by optimizing scale, customizing training samples to provide sets with the best examples, feature selection, etc. Herein, a novel approach, named Cross-Scaling, is proposed that includes the mixing of training and testing set resolutions. Hypothetically, training on a coarser resolution dataset and testing the model on a finer resolution should help the algorithm to better generalize ambiguous examples of landslide classes and yield fewer over/underestimations in the model. This ...
Uroš Đurić, Miloš Marjanović, Zoran Radić, Biljana Abolmasov. " Machine learning based landslide assessment of the Belgrade metropolitan area: Pixel resolution effects and a cross-scaling concept" in Engineering Geology , Elsevier (2019). https://doi.org/10.1016/j.enggeo.2019.05.007
