Landslide susceptibility mapping using ensemble machine learning methods: a case study in Lombardy, Northern Italy

ABSTRACT

This study compares the performance of ensemble machine learning methods stacking, blending, and soft voting for Landslide susceptibility mapping (LSM) in a highly affected Northern Italy region, Lombardy. We first created a spatial database based on open data ensuring the accessibility to relevant information for landslide-influencing factors, historical landslide records, and areas with a very low probability of landslide occurrence called ‘No Landslide Zone’, an innovative concept introduced in this study. Then, open-source software was employed for developing five Machine Learning classifiers (Bagging, Random Forests, AdaBoost, Gradient Tree Boosting, and Neural Networks) which were tested at a basin scale by implementing different combinations of training and testing schemes using three use cases. The three classifiers with the highest generalization performance (Random Forests, AdaBoost, and Neural Networks) were selected and combined by ensemble methods. The soft voting showed the highest performance among them. The best model to generate the LSM for the Lombardy region was a Neural Network model trained using data from three basins, achieving an accuracy of 0.93 in Lombardy. The LSM indicates that 37% of Lombardy is in the highest landslide susceptibility categories. Our findings highlight the importance of openness in advancing LSM not only by enhancing the reproducibility and transparency of our methodology but also by promoting knowledge-sharing within the scientific community.

KEYWORDS:

• Landslide susceptibility mapping
• machine learning
• ensemble methods
• geoprocessing
• openness
• free and open source software

Author Contributions

Conceptualization, M.A.B., V.Y., Q.X. and L.A.; methodology, M.A.B., V.Y. and Q.X.; software, V.Y. and Q.X.; validation, Q.X.; formal analysis, M.A.B., V.Y. and Q.X.; investigation, Q.X.; resources, V.Y. and Q.X.; data curation, V.Y. and Q.X.; writing – original draft preparation, Q.X. and L.A.; writing – review and editing, M.A.B. and V.Y.; visualization, Q.X.; supervision, M.A.B. and V.Y.; project administration, M.A.B.; funding acquisition, M.A.B. All authors have read and agreed to the published version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Code availability

The code is available at GEOlab Github - Landslide Susceptibility Mapping

Data availability statement

The data that support the findings of this study are openly available in Zenodo. The relevant input datasets are available at https://doi.org/10.5281/zenodo.8185734.

 Google Scholar

, the outputs from ensemble machine learning models are available at https://doi.org/10.5281/zenodo.8185870,

 Google Scholar

. The estimated No Landslide Zone for Lombardy Regions is available at https://doi.org/10.5281/zenodo.8185887

 Google Scholar

.

Additional information

Funding

This research 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.