Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382204627> ?p ?o ?g. }
- W4382204627 abstract "Abstract Landslides are notoriously difficult to predict because numerous spatially and temporally varying factors contribute to slope stability. Artificial neural networks (ANN) have been shown to improve prediction accuracy but are largely uninterpretable. Here we introduce an additive ANN optimization framework to assess landslide susceptibility, as well as dataset division and outcome interpretation techniques. We refer to our approach, which features full interpretability, high accuracy, high generalizability and low model complexity, as superposable neural network (SNN) optimization. We validate our approach by training models on landslide inventories from three different easternmost Himalaya regions. Our SNN outperformed physically-based and statistical models and achieved similar performance to state-of-the-art deep neural networks. The SNN models found the product of slope and precipitation and hillslope aspect to be important primary contributors to high landslide susceptibility, which highlights the importance of strong slope-climate couplings, along with microclimates, on landslide occurrences." @default.
- W4382204627 created "2023-06-28" @default.
- W4382204627 creator A5053925403 @default.
- W4382204627 creator A5056896393 @default.
- W4382204627 creator A5072041196 @default.
- W4382204627 creator A5088446841 @default.
- W4382204627 date "2023-05-10" @default.
- W4382204627 modified "2023-10-09" @default.
- W4382204627 title "Landslide susceptibility modeling by interpretable neural network" @default.
- W4382204627 cites W1485454794 @default.
- W4382204627 cites W1533241898 @default.
- W4382204627 cites W1553152200 @default.
- W4382204627 cites W1576278180 @default.
- W4382204627 cites W1678356000 @default.
- W4382204627 cites W1964194978 @default.
- W4382204627 cites W1966352410 @default.
- W4382204627 cites W1968677651 @default.
- W4382204627 cites W1978347012 @default.
- W4382204627 cites W1981646498 @default.
- W4382204627 cites W1988988493 @default.
- W4382204627 cites W1990979404 @default.
- W4382204627 cites W1995035032 @default.
- W4382204627 cites W2002139005 @default.
- W4382204627 cites W2003049509 @default.
- W4382204627 cites W2006544565 @default.
- W4382204627 cites W2014074025 @default.
- W4382204627 cites W2015981295 @default.
- W4382204627 cites W2029816621 @default.
- W4382204627 cites W2033831971 @default.
- W4382204627 cites W2037967790 @default.
- W4382204627 cites W2048329679 @default.
- W4382204627 cites W2054512946 @default.
- W4382204627 cites W2056214587 @default.
- W4382204627 cites W2064762548 @default.
- W4382204627 cites W2066848039 @default.
- W4382204627 cites W2076744895 @default.
- W4382204627 cites W2077323522 @default.
- W4382204627 cites W2079965317 @default.
- W4382204627 cites W2080486692 @default.
- W4382204627 cites W2087272215 @default.
- W4382204627 cites W2087427486 @default.
- W4382204627 cites W2088730795 @default.
- W4382204627 cites W2090105324 @default.
- W4382204627 cites W2091455951 @default.
- W4382204627 cites W2094839437 @default.
- W4382204627 cites W2096868362 @default.
- W4382204627 cites W2098681477 @default.
- W4382204627 cites W2104219081 @default.
- W4382204627 cites W2113162852 @default.
- W4382204627 cites W2113951488 @default.
- W4382204627 cites W2133764509 @default.
- W4382204627 cites W2147031880 @default.
- W4382204627 cites W2147357873 @default.
- W4382204627 cites W2147373555 @default.
- W4382204627 cites W2147555471 @default.
- W4382204627 cites W2587598231 @default.
- W4382204627 cites W2743802779 @default.
- W4382204627 cites W2792324107 @default.
- W4382204627 cites W2792546905 @default.
- W4382204627 cites W2793831793 @default.
- W4382204627 cites W2891503716 @default.
- W4382204627 cites W2912361013 @default.
- W4382204627 cites W2916848715 @default.
- W4382204627 cites W2923717973 @default.
- W4382204627 cites W2939945347 @default.
- W4382204627 cites W2943844914 @default.
- W4382204627 cites W2945976633 @default.
- W4382204627 cites W2962905110 @default.
- W4382204627 cites W2962970834 @default.
- W4382204627 cites W2974447785 @default.
- W4382204627 cites W2982486887 @default.
- W4382204627 cites W2983592190 @default.
- W4382204627 cites W2990025414 @default.
- W4382204627 cites W2995523160 @default.
- W4382204627 cites W2999015335 @default.
- W4382204627 cites W2999729702 @default.
- W4382204627 cites W3001525167 @default.
- W4382204627 cites W3006071021 @default.
- W4382204627 cites W3011594683 @default.
- W4382204627 cites W3012313541 @default.
- W4382204627 cites W3041593396 @default.
- W4382204627 cites W3047462331 @default.
- W4382204627 cites W3048275843 @default.
- W4382204627 cites W3087676330 @default.
- W4382204627 cites W3128768470 @default.
- W4382204627 cites W3129443655 @default.
- W4382204627 cites W3134424317 @default.
- W4382204627 cites W3147265468 @default.
- W4382204627 cites W3177490604 @default.
- W4382204627 cites W4237210482 @default.
- W4382204627 cites W4281758742 @default.
- W4382204627 cites W4289097366 @default.
- W4382204627 doi "https://doi.org/10.1038/s43247-023-00806-5" @default.
- W4382204627 hasPublicationYear "2023" @default.
- W4382204627 type Work @default.
- W4382204627 citedByCount "4" @default.
- W4382204627 countsByYear W43822046272023 @default.
- W4382204627 crossrefType "journal-article" @default.
- W4382204627 hasAuthorship W4382204627A5053925403 @default.
- W4382204627 hasAuthorship W4382204627A5056896393 @default.