Landslide susceptibility maps using ensemble machine learning models on basin and regional level in Lombardy, Italy

A selection of landslide susceptibility maps computed through ensemble machine learning models for the basins of Val Tartano, Upper Valtellina and Valchiavenna, and on a regional level for the Lombardy region in Italy.

A list of the used base machine learning methods:

Random Forest,

AdaBoost,

Neural Networks.

A list of the used ensemble models:

Stacking,

Blending,

Soft Voting.

A full list of the model combinations can be found in the "Case Studies" document.

The maps are in WGS 84/ UTM zone 32N (EPSG:32632).

The map production process details are discussed in Xu et al. 2024. If you use the dataset, please, cite also the paper:

Qiongjie Xu, Vasil Yordanov, Lorenzo Amici & Maria Antonia Brovelli (2024) Landslide susceptibility mapping using ensemble machine learning methods: a casestudy in Lombardy, Northern Italy, International Journal of Digital Earth, 17:1, 2346263, DOI:10.1080/17538947.2024.2346263

The maps are produced as part of the "Geoinformatics and Earth Observation for Landslide Monitoring" Italy-Vietnam.

The work is partially funded by the Italian Ministry of Foreign Affairs and International Cooperation within the project “Geoinformatics and Earth Observation for Landslide Monitoring” CUP D19C21000480001.