Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015779580> ?p ?o ?g. }
- W3015779580 endingPage "107201" @default.
- W3015779580 startingPage "107201" @default.
- W3015779580 abstract "The choice of model parameters in landslide susceptibility mapping makes a major determinant of model accuracy. The purpose of this study is to optimize the hyperparameters based on a Bayesian optimization algorithm, and to obtain a high accuracy random forest landslide susceptibility evaluation model. The research steps are detailed as follows. Firstly, taking a typical landslide prone mountainous area as an example, 16 conditioning factors, such as elevation, annual average rainfall, distance from roads, distance from buildings and so on, were preliminarily selected as the conditioning factors of landslide susceptibility. Combined with 1520 historical landslide events, a geospatial database was established with 30 m resolution. Secondly, the geospatial data sample set was constructed by random sampling according to ratio of historical landslides and non-landslides of 1:10. Based on the whole sample set, the random forest model adopted the Bayesian optimization algorithm to optimize the hyperparameters. Next, the optimal hyperparameters were selected to be trained to get the evaluation model of landslide susceptibility. In addition, they were carried out the analysis of landslide susceptibility mapping for the whole study area. After that, the recursive feature elimination method was used to screen out the dominant conditioning factors that can explain the degree of landslide susceptibility. The results indicated that the area under curve (AUC) values of receiver operating characteristic (ROC) curve in training data set, verification data set and regional simulation were 0.95, 0.87 and 0.93, respectively. 65% of the historical landslides fell between the high susceptibility and very high susceptibility regions, which made up <20% of the research area. The model was in good agreement to the distribution characteristics of historical landslides in the study area. We noted that all the three recent landslides with impact on the study area occurred at the locations predicted by the model to have high or very high susceptibility in terms of typical landslides in the near future. As for conditioning factors, the contribution related to human activities accounted for a large proportion. In conclusion, an evaluation model with high precision for random forest landslide susceptibility can be built based on hyperparameter optimization with Bayesian optimization algorithm. Simultaneously, using recursive feature elimination method, a random forest landslide susceptibility model with fewer dominant conditioning factors and guaranteed evaluation accuracy can also be built to save the running time and input data resources of the model." @default.
- W3015779580 created "2020-04-17" @default.
- W3015779580 creator A5020688619 @default.
- W3015779580 creator A5052065564 @default.
- W3015779580 creator A5060752718 @default.
- W3015779580 creator A5087139878 @default.
- W3015779580 date "2020-08-01" @default.
- W3015779580 modified "2023-10-18" @default.
- W3015779580 title "A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm" @default.
- W3015779580 cites W1979486410 @default.
- W3015779580 cites W2040895371 @default.
- W3015779580 cites W2044579603 @default.
- W3015779580 cites W2061798849 @default.
- W3015779580 cites W2081175096 @default.
- W3015779580 cites W2116209708 @default.
- W3015779580 cites W2117090927 @default.
- W3015779580 cites W2145427519 @default.
- W3015779580 cites W2287278712 @default.
- W3015779580 cites W2548562885 @default.
- W3015779580 cites W2567326027 @default.
- W3015779580 cites W2584860397 @default.
- W3015779580 cites W2754252800 @default.
- W3015779580 cites W2792546905 @default.
- W3015779580 cites W2793831793 @default.
- W3015779580 cites W2802235618 @default.
- W3015779580 cites W2803006902 @default.
- W3015779580 cites W2880239935 @default.
- W3015779580 cites W2946007918 @default.
- W3015779580 cites W2980417643 @default.
- W3015779580 cites W4210949798 @default.
- W3015779580 cites W4212883601 @default.
- W3015779580 doi "https://doi.org/10.1016/j.geomorph.2020.107201" @default.
- W3015779580 hasPublicationYear "2020" @default.
- W3015779580 type Work @default.
- W3015779580 sameAs 3015779580 @default.
- W3015779580 citedByCount "196" @default.
- W3015779580 countsByYear W30157795802020 @default.
- W3015779580 countsByYear W30157795802021 @default.
- W3015779580 countsByYear W30157795802022 @default.
- W3015779580 countsByYear W30157795802023 @default.
- W3015779580 crossrefType "journal-article" @default.
- W3015779580 hasAuthorship W3015779580A5020688619 @default.
- W3015779580 hasAuthorship W3015779580A5052065564 @default.
- W3015779580 hasAuthorship W3015779580A5060752718 @default.
- W3015779580 hasAuthorship W3015779580A5087139878 @default.
- W3015779580 hasConcept C105795698 @default.
- W3015779580 hasConcept C107673813 @default.
- W3015779580 hasConcept C11413529 @default.
- W3015779580 hasConcept C114793014 @default.
- W3015779580 hasConcept C124101348 @default.
- W3015779580 hasConcept C127313418 @default.
- W3015779580 hasConcept C154945302 @default.
- W3015779580 hasConcept C169258074 @default.
- W3015779580 hasConcept C186295008 @default.
- W3015779580 hasConcept C207201462 @default.
- W3015779580 hasConcept C2524010 @default.
- W3015779580 hasConcept C33923547 @default.
- W3015779580 hasConcept C37054046 @default.
- W3015779580 hasConcept C41008148 @default.
- W3015779580 hasConcept C58489278 @default.
- W3015779580 hasConcept C62649853 @default.
- W3015779580 hasConcept C8642999 @default.
- W3015779580 hasConcept C9770341 @default.
- W3015779580 hasConceptScore W3015779580C105795698 @default.
- W3015779580 hasConceptScore W3015779580C107673813 @default.
- W3015779580 hasConceptScore W3015779580C11413529 @default.
- W3015779580 hasConceptScore W3015779580C114793014 @default.
- W3015779580 hasConceptScore W3015779580C124101348 @default.
- W3015779580 hasConceptScore W3015779580C127313418 @default.
- W3015779580 hasConceptScore W3015779580C154945302 @default.
- W3015779580 hasConceptScore W3015779580C169258074 @default.
- W3015779580 hasConceptScore W3015779580C186295008 @default.
- W3015779580 hasConceptScore W3015779580C207201462 @default.
- W3015779580 hasConceptScore W3015779580C2524010 @default.
- W3015779580 hasConceptScore W3015779580C33923547 @default.
- W3015779580 hasConceptScore W3015779580C37054046 @default.
- W3015779580 hasConceptScore W3015779580C41008148 @default.
- W3015779580 hasConceptScore W3015779580C58489278 @default.
- W3015779580 hasConceptScore W3015779580C62649853 @default.
- W3015779580 hasConceptScore W3015779580C8642999 @default.
- W3015779580 hasConceptScore W3015779580C9770341 @default.
- W3015779580 hasFunder F4320321001 @default.
- W3015779580 hasFunder F4320336026 @default.
- W3015779580 hasLocation W30157795801 @default.
- W3015779580 hasOpenAccess W3015779580 @default.
- W3015779580 hasPrimaryLocation W30157795801 @default.
- W3015779580 hasRelatedWork W1509177177 @default.
- W3015779580 hasRelatedWork W2140186469 @default.
- W3015779580 hasRelatedWork W2775233965 @default.
- W3015779580 hasRelatedWork W3183136280 @default.
- W3015779580 hasRelatedWork W4225647658 @default.
- W3015779580 hasRelatedWork W4280563792 @default.
- W3015779580 hasRelatedWork W4311551265 @default.
- W3015779580 hasRelatedWork W4318559728 @default.
- W3015779580 hasRelatedWork W4318719684 @default.
- W3015779580 hasRelatedWork W4386295066 @default.
- W3015779580 hasVolume "362" @default.
- W3015779580 isParatext "false" @default.