Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285679287> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4285679287 abstract "Landslide susceptibility assessment is often hindered by the lack of historical landslide records. In this study, we propose a transfer learning-based approach for landslide susceptibility assessment, aiming at substantially improving susceptibility prediction using knowledge outside the target domain, especially for regions with limited landslide data. The proposed method first trains a deep learning landslide susceptibility model (i.e., pre-trained model or source model) in a data-rich region (i.e., source domain). Transfer learning techniques are then applied to transfer the knowledge from the source domain to a new region (i.e., target domain) through model transfer and fine-tuning. The transferred model not only carries knowledge from the source domain but is also retrained with data from the target domain, hence achieving a much-improved performance in the new region even with very limited new data. A comprehensive case study in Hong Kong is conducted to investigate the feasibility of the proposed method and the influence of source domain scale on the transfer learning efficiency. Substantial improvements can be found with the proposed method: the accuracies on the test set of the target domain can be increased by 30% and the logarithmic losses can be decreased by 62%. We also reveal that transferring models from larger source domains can accomplish more improvements in both data-rich and data-limited cases. As the very first study that introduces deep transfer learning to landslide susceptibility assessment, the proposed method enables the sharing of landslide knowledge between regions, and is shown to be an intelligent and promising way for improving landslide susceptibility assessment for data-limited regions." @default.
- W4285679287 created "2022-07-17" @default.
- W4285679287 creator A5053275663 @default.
- W4285679287 creator A5055736577 @default.
- W4285679287 creator A5066504632 @default.
- W4285679287 date "2022-07-01" @default.
- W4285679287 modified "2023-10-14" @default.
- W4285679287 title "Transfer learning improves landslide susceptibility assessment" @default.
- W4285679287 cites W1680670471 @default.
- W4285679287 cites W1988650824 @default.
- W4285679287 cites W2017920701 @default.
- W4285679287 cites W2023203753 @default.
- W4285679287 cites W2070638918 @default.
- W4285679287 cites W2080134555 @default.
- W4285679287 cites W2102531694 @default.
- W4285679287 cites W2105714409 @default.
- W4285679287 cites W2165698076 @default.
- W4285679287 cites W2202883548 @default.
- W4285679287 cites W2469862374 @default.
- W4285679287 cites W2770617885 @default.
- W4285679287 cites W2911974410 @default.
- W4285679287 cites W2996991292 @default.
- W4285679287 cites W3008537971 @default.
- W4285679287 cites W3010757542 @default.
- W4285679287 cites W3015779580 @default.
- W4285679287 cites W3017258208 @default.
- W4285679287 cites W3022926677 @default.
- W4285679287 cites W3082129780 @default.
- W4285679287 cites W3087676330 @default.
- W4285679287 cites W3144445321 @default.
- W4285679287 cites W3199763347 @default.
- W4285679287 cites W3203997044 @default.
- W4285679287 cites W3217696356 @default.
- W4285679287 cites W4206280001 @default.
- W4285679287 doi "https://doi.org/10.1016/j.gr.2022.07.008" @default.
- W4285679287 hasPublicationYear "2022" @default.
- W4285679287 type Work @default.
- W4285679287 citedByCount "9" @default.
- W4285679287 countsByYear W42856792872022 @default.
- W4285679287 countsByYear W42856792872023 @default.
- W4285679287 crossrefType "journal-article" @default.
- W4285679287 hasAuthorship W4285679287A5053275663 @default.
- W4285679287 hasAuthorship W4285679287A5055736577 @default.
- W4285679287 hasAuthorship W4285679287A5066504632 @default.
- W4285679287 hasConcept C119857082 @default.
- W4285679287 hasConcept C124101348 @default.
- W4285679287 hasConcept C127313418 @default.
- W4285679287 hasConcept C134306372 @default.
- W4285679287 hasConcept C138885662 @default.
- W4285679287 hasConcept C150899416 @default.
- W4285679287 hasConcept C154945302 @default.
- W4285679287 hasConcept C165205528 @default.
- W4285679287 hasConcept C171041071 @default.
- W4285679287 hasConcept C186295008 @default.
- W4285679287 hasConcept C2776960227 @default.
- W4285679287 hasConcept C2779178101 @default.
- W4285679287 hasConcept C33923547 @default.
- W4285679287 hasConcept C36503486 @default.
- W4285679287 hasConcept C39927690 @default.
- W4285679287 hasConcept C41008148 @default.
- W4285679287 hasConcept C41895202 @default.
- W4285679287 hasConcept C56739046 @default.
- W4285679287 hasConceptScore W4285679287C119857082 @default.
- W4285679287 hasConceptScore W4285679287C124101348 @default.
- W4285679287 hasConceptScore W4285679287C127313418 @default.
- W4285679287 hasConceptScore W4285679287C134306372 @default.
- W4285679287 hasConceptScore W4285679287C138885662 @default.
- W4285679287 hasConceptScore W4285679287C150899416 @default.
- W4285679287 hasConceptScore W4285679287C154945302 @default.
- W4285679287 hasConceptScore W4285679287C165205528 @default.
- W4285679287 hasConceptScore W4285679287C171041071 @default.
- W4285679287 hasConceptScore W4285679287C186295008 @default.
- W4285679287 hasConceptScore W4285679287C2776960227 @default.
- W4285679287 hasConceptScore W4285679287C2779178101 @default.
- W4285679287 hasConceptScore W4285679287C33923547 @default.
- W4285679287 hasConceptScore W4285679287C36503486 @default.
- W4285679287 hasConceptScore W4285679287C39927690 @default.
- W4285679287 hasConceptScore W4285679287C41008148 @default.
- W4285679287 hasConceptScore W4285679287C41895202 @default.
- W4285679287 hasConceptScore W4285679287C56739046 @default.
- W4285679287 hasLocation W42856792871 @default.
- W4285679287 hasOpenAccess W4285679287 @default.
- W4285679287 hasPrimaryLocation W42856792871 @default.
- W4285679287 hasRelatedWork W2890837360 @default.
- W4285679287 hasRelatedWork W2960456850 @default.
- W4285679287 hasRelatedWork W2964665600 @default.
- W4285679287 hasRelatedWork W3081798076 @default.
- W4285679287 hasRelatedWork W3181845641 @default.
- W4285679287 hasRelatedWork W4213299466 @default.
- W4285679287 hasRelatedWork W4220756431 @default.
- W4285679287 hasRelatedWork W4281382123 @default.
- W4285679287 hasRelatedWork W4308262314 @default.
- W4285679287 hasRelatedWork W4318834068 @default.
- W4285679287 isParatext "false" @default.
- W4285679287 isRetracted "false" @default.
- W4285679287 workType "article" @default.