Machine Learning and Landslide Assessment in a GIS Environment
Abstract
This chapter introduces theoretical and practical aspects for applying GIS and geocomputation methods in landslide assessment problems. Machine Learning techniques in combination with GIS are proven useful for computation and building of complex non-linear spatial models, which is why they have been chosen in our work. Modeling principles that include basic Machine Learning techniques (Artificial Neural Networks, Decision trees, Support Vector Machines) and additional useful procedures are described to show how they can be applied to address a complex problem such as landslide assessment. Two types of models are proposed in the work herein that are useful for describing landslide susceptibility and landslide prediction. The region of Halenkovice in Czech Republic is presented as a case study to illustrate and bring closer the practical aspects of landslide assessment. These aspects consider data preparation and preprocessing, scale effects, model optimization, and evaluation. The resul...ts show that Support Vector Machines and similar Machine Learning (ML) techniques can be successfully applied to address the zoning of landslide susceptibility, which might be an important breakthrough for potential applications in regional planning and decision-making.
Source:
GeoComputational Analysis and Modeling of Regional Systems, 2018, 191-213Publisher:
- Cham: Springer International Publishing
Note:
- Thill, Jean-Claude; Dragicevic, Suzana
Collections
Institution/Community
GraFarTY - CHAP AU - Đurić, Uroš AU - Bajat, Branislav AU - Abolmasov, Biljana AU - Kovačević, Miloš PY - 2018 UR - https://grafar.grf.bg.ac.rs/handle/123456789/1101 AB - This chapter introduces theoretical and practical aspects for applying GIS and geocomputation methods in landslide assessment problems. Machine Learning techniques in combination with GIS are proven useful for computation and building of complex non-linear spatial models, which is why they have been chosen in our work. Modeling principles that include basic Machine Learning techniques (Artificial Neural Networks, Decision trees, Support Vector Machines) and additional useful procedures are described to show how they can be applied to address a complex problem such as landslide assessment. Two types of models are proposed in the work herein that are useful for describing landslide susceptibility and landslide prediction. The region of Halenkovice in Czech Republic is presented as a case study to illustrate and bring closer the practical aspects of landslide assessment. These aspects consider data preparation and preprocessing, scale effects, model optimization, and evaluation. The results show that Support Vector Machines and similar Machine Learning (ML) techniques can be successfully applied to address the zoning of landslide susceptibility, which might be an important breakthrough for potential applications in regional planning and decision-making. PB - Cham: Springer International Publishing T2 - GeoComputational Analysis and Modeling of Regional Systems T1 - Machine Learning and Landslide Assessment in a GIS Environment EP - 213 SP - 191 DO - 10.1007/978-3-319-59511-5_11 ER -
@inbook{ author = "Đurić, Uroš and Bajat, Branislav and Abolmasov, Biljana and Kovačević, Miloš", year = "2018", abstract = "This chapter introduces theoretical and practical aspects for applying GIS and geocomputation methods in landslide assessment problems. Machine Learning techniques in combination with GIS are proven useful for computation and building of complex non-linear spatial models, which is why they have been chosen in our work. Modeling principles that include basic Machine Learning techniques (Artificial Neural Networks, Decision trees, Support Vector Machines) and additional useful procedures are described to show how they can be applied to address a complex problem such as landslide assessment. Two types of models are proposed in the work herein that are useful for describing landslide susceptibility and landslide prediction. The region of Halenkovice in Czech Republic is presented as a case study to illustrate and bring closer the practical aspects of landslide assessment. These aspects consider data preparation and preprocessing, scale effects, model optimization, and evaluation. The results show that Support Vector Machines and similar Machine Learning (ML) techniques can be successfully applied to address the zoning of landslide susceptibility, which might be an important breakthrough for potential applications in regional planning and decision-making.", publisher = "Cham: Springer International Publishing", journal = "GeoComputational Analysis and Modeling of Regional Systems", booktitle = "Machine Learning and Landslide Assessment in a GIS Environment", pages = "213-191", doi = "10.1007/978-3-319-59511-5_11" }
Đurić, U., Bajat, B., Abolmasov, B.,& Kovačević, M.. (2018). Machine Learning and Landslide Assessment in a GIS Environment. in GeoComputational Analysis and Modeling of Regional Systems Cham: Springer International Publishing., 191-213. https://doi.org/10.1007/978-3-319-59511-5_11
Đurić U, Bajat B, Abolmasov B, Kovačević M. Machine Learning and Landslide Assessment in a GIS Environment. in GeoComputational Analysis and Modeling of Regional Systems. 2018;:191-213. doi:10.1007/978-3-319-59511-5_11 .
Đurić, Uroš, Bajat, Branislav, Abolmasov, Biljana, Kovačević, Miloš, "Machine Learning and Landslide Assessment in a GIS Environment" in GeoComputational Analysis and Modeling of Regional Systems (2018):191-213, https://doi.org/10.1007/978-3-319-59511-5_11 . .