Collected Item: “Concepts for Improving Machine Learning Based Landslide Assessment”
Врста публикације
Поглавље у монографији
Верзија документа
објављена
Наслов поглавља
Concepts for Improving Machine Learning Based Landslide Assessment
Језик
енглески
Аутор/и (Милан Марковић, Никола Николић)
Miloš Marjanović, Mileva Samardžić Petrović, Biljana Abolmasov, Uroš Đurić,
Наслов монографије (Наслов - поднаслов)
Natural Hazards GIS-based Spatial Modeling Using Data Mining Techniques, Advances in Natural and Technological Hazards Research 48
Уредник/ци монографије
H. R. Pourghasemi and M. Rossi
Издавач (Београд : Просвета)
Springer Nature Switzerland AG 2019
Година издавања
2019
Кратак опис поглавља
The main idea of this chapter is to address some of the key issues that were
recognized in Machine Learning (ML) based Landslide Assessment Modeling
(LAM). Through the experience of the authors, elaborated in several case studies,
including the City of Belgrade in Serbia, the City of Tuzla in Bosnia and Herzegovina, Ljubovija Municipality in Serbia, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best
practice for validating resulting models against the existing inventory). All of them
are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.
recognized in Machine Learning (ML) based Landslide Assessment Modeling
(LAM). Through the experience of the authors, elaborated in several case studies,
including the City of Belgrade in Serbia, the City of Tuzla in Bosnia and Herzegovina, Ljubovija Municipality in Serbia, and Halenkovice area in Czech Republic, eight key issues were identified, and appropriate options, solutions, and some new concepts for overcoming them were introduced. The following issues were addressed: Landslide inventory enhancements (overcoming small number of landslide instances), Choice of attributes (which attributes are appropriate and pros and cons on attribute selection/extraction), Classification versus regression (which type of task is more appropriate in particular cases), Choice of ML technique (discussion of most popular ML techniques), Sampling strategy (overcoming the overfit by choosing training instances wisely), Cross-scaling (a new concept for improving the algorithm’s learning capacity), Quasi-hazard concept (introducing artificial temporal base for upgrading from susceptibility to hazard assessment), and Objective model evaluation (the best
practice for validating resulting models against the existing inventory). All of them
are followed by appropriate practical examples from one of abovementioned case studies. The ultimate objective is to provide guidance and inspire LAM community for a more innovative approach in modeling.
Почетна страна поглавља
27
Завршна страна поглавља
58
DOI број
https://doi.org/10.1007/978-3-319-73383-8_2
ISBN број монографије
978-3-319-73382-1
Географско подручје на које се односи поглавље
Srbija
Кључне речи на српском (одвојене знаком ", ")
"Katastar klizišta", "Podložnost", "Hazard", Mašinsko učenje", Uzorkovanje", "Validacija",
Кључне речи на енглеском (одвојене знаком ", ")
"Landslide inventory", "Susceptibility", "Hazard", "Machine learning", "Sampling", "Validation", "Cross-scaling"
Линк
https://doi.org/10.1007/978-3-319-73383-8_2
Шира категорија рада према правилнику МПНТ
M10
Ужа категорија рада према правилнику МПНТ
М14
Пројекат у оквиру кога је настало поглавље
TR36009
Ниво приступа
Затворени приступ
Лиценца
All rights reserved
Формат дигиталне датотеке
.pdf