FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309710810> ?p ?o ?g. }

• W4309710810 endingPage "3764" @default.
• W4309710810 startingPage "3751" @default.
• W4309710810 abstract "Abstract. Landslide hazard models aim at mitigating landslide impact by providing probabilistic forecasting, and the accuracy of these models hinges on landslide databases for model training and testing. Landslide databases at times lack information on the underlying triggering mechanism, making these inventories almost unusable in hazard models. We developed a Python-based unique library, Landsifier, that contains three different machine-Learning frameworks for assessing the likely triggering mechanisms of individual landslides or entire inventories based on landslide geometry. Two of these methods only use the 2D landslide planforms, and the third utilizes the 3D shape of landslides relying on an underlying digital elevation model (DEM). The base method extracts geometric properties of landslide polygons as a feature space for the shallow learner – random forest (RF). An alternative method relies on landslide planform images as an input for the deep learning algorithm – convolutional neural network (CNN). The last framework extracts topological properties of 3D landslides through topological data analysis (TDA) and then feeds these properties as a feature space to the random forest classifier. We tested all three interchangeable methods on several inventories with known triggers spread over the Japanese archipelago. To demonstrate the effectiveness of developed methods, we used two testing configurations. The first configuration merges all the available data for the k-fold cross-validation, whereas the second configuration excludes one inventory during the training phase to use as the sole testing inventory. Our geometric-feature-based method performs satisfactorily, with classification accuracies varying between 67 % and 92 %. We have introduced a more straightforward but data-intensive CNN alternative, as it inputs only landslide images without manual feature selection. CNN eases the scripting process without losing classification accuracy. Using topological features from 3D landslides (extracted through TDA) in the RF classifier improves classification accuracy by 12 % on average. TDA also requires less training data. However, the landscape autocorrelation could easily bias TDA-based classification. Finally, we implemented the three methods on an inventory without any triggering information to showcase a real-world application." @default.
• W4309710810 created "2022-11-29" @default.
• W4309710810 creator A5035216139 @default.
• W4309710810 creator A5050313397 @default.
• W4309710810 creator A5059469450 @default.
• W4309710810 date "2022-11-22" @default.
• W4309710810 modified "2023-10-09" @default.
• W4309710810 title "Landsifier v1.0: a Python library to estimate likely triggers of mapped landslides" @default.
• W4309710810 cites W1957046493 @default.
• W4309710810 cites W1960384938 @default.
• W4309710810 cites W1991566301 @default.
• W4309710810 cites W1996226159 @default.
• W4309710810 cites W2013316404 @default.
• W4309710810 cites W2044097773 @default.
• W4309710810 cites W2058082754 @default.
• W4309710810 cites W2076634503 @default.
• W4309710810 cites W2079783228 @default.
• W4309710810 cites W2081620141 @default.
• W4309710810 cites W2123899356 @default.
• W4309710810 cites W2134702142 @default.
• W4309710810 cites W2161336914 @default.
• W4309710810 cites W2339008828 @default.
• W4309710810 cites W2500686813 @default.
• W4309710810 cites W2517757032 @default.
• W4309710810 cites W2618530766 @default.
• W4309710810 cites W2725792925 @default.
• W4309710810 cites W2766191760 @default.
• W4309710810 cites W2778020085 @default.
• W4309710810 cites W2789876780 @default.
• W4309710810 cites W2793031008 @default.
• W4309710810 cites W2809254203 @default.
• W4309710810 cites W2885156825 @default.
• W4309710810 cites W2912361013 @default.
• W4309710810 cites W3007423882 @default.
• W4309710810 cites W3047918780 @default.
• W4309710810 cites W3081183014 @default.
• W4309710810 cites W3090817451 @default.
• W4309710810 cites W3105756223 @default.
• W4309710810 cites W3118822358 @default.
• W4309710810 cites W3130741063 @default.
• W4309710810 cites W3136440917 @default.
• W4309710810 cites W3156176292 @default.
• W4309710810 cites W3156214146 @default.
• W4309710810 cites W3165474212 @default.
• W4309710810 cites W3175826166 @default.
• W4309710810 cites W3186658911 @default.
• W4309710810 cites W3195173412 @default.
• W4309710810 cites W3200116822 @default.
• W4309710810 cites W4205314579 @default.
• W4309710810 cites W4224293318 @default.
• W4309710810 cites W4285736630 @default.
• W4309710810 doi "https://doi.org/10.5194/nhess-22-3751-2022" @default.
• W4309710810 hasPublicationYear "2022" @default.
• W4309710810 type Work @default.
• W4309710810 citedByCount "3" @default.
• W4309710810 countsByYear W43097108102023 @default.
• W4309710810 crossrefType "journal-article" @default.
• W4309710810 hasAuthorship W4309710810A5035216139 @default.
• W4309710810 hasAuthorship W4309710810A5050313397 @default.
• W4309710810 hasAuthorship W4309710810A5059469450 @default.
• W4309710810 hasBestOaLocation W43097108101 @default.
• W4309710810 hasConcept C111919701 @default.
• W4309710810 hasConcept C124101348 @default.
• W4309710810 hasConcept C127313418 @default.
• W4309710810 hasConcept C138885662 @default.
• W4309710810 hasConcept C154945302 @default.
• W4309710810 hasConcept C165205528 @default.
• W4309710810 hasConcept C169258074 @default.
• W4309710810 hasConcept C181843262 @default.
• W4309710810 hasConcept C186295008 @default.
• W4309710810 hasConcept C2776401178 @default.
• W4309710810 hasConcept C41008148 @default.
• W4309710810 hasConcept C41895202 @default.
• W4309710810 hasConcept C519991488 @default.
• W4309710810 hasConcept C62649853 @default.
• W4309710810 hasConcept C81363708 @default.
• W4309710810 hasConcept C83665646 @default.
• W4309710810 hasConceptScore W4309710810C111919701 @default.
• W4309710810 hasConceptScore W4309710810C124101348 @default.
• W4309710810 hasConceptScore W4309710810C127313418 @default.
• W4309710810 hasConceptScore W4309710810C138885662 @default.
• W4309710810 hasConceptScore W4309710810C154945302 @default.
• W4309710810 hasConceptScore W4309710810C165205528 @default.
• W4309710810 hasConceptScore W4309710810C169258074 @default.
• W4309710810 hasConceptScore W4309710810C181843262 @default.
• W4309710810 hasConceptScore W4309710810C186295008 @default.
• W4309710810 hasConceptScore W4309710810C2776401178 @default.
• W4309710810 hasConceptScore W4309710810C41008148 @default.
• W4309710810 hasConceptScore W4309710810C41895202 @default.
• W4309710810 hasConceptScore W4309710810C519991488 @default.
• W4309710810 hasConceptScore W4309710810C62649853 @default.
• W4309710810 hasConceptScore W4309710810C81363708 @default.
• W4309710810 hasConceptScore W4309710810C83665646 @default.
• W4309710810 hasFunder F4320316118 @default.
• W4309710810 hasFunder F4320320875 @default.
• W4309710810 hasIssue "11" @default.
• W4309710810 hasLocation W43097108101 @default.
• W4309710810 hasLocation W43097108102 @default.

• next