FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081022264> ?p ?o ?g. }

• W3081022264 endingPage "55" @default.
• W3081022264 startingPage "37" @default.
• W3081022264 abstract "Damage models for natural hazards are used for decision making on reducing and transferring risk. The damage estimates from these models depend on many variables and their complex sometimes nonlinear relationships with the damage. In recent years, data-driven modeling techniques have been used to capture those relationships. The available data to build such models are often limited. Therefore, in practice it is usually necessary to transfer models to a different context. In this article, we show that this implies the samples used to build the model are often not fully representative for the situation where they need to be applied on, which leads to a “sample selection bias.” In this article, we enhance data-driven damage models by applying methods, not previously applied to damage modeling, to correct for this bias before the machine learning (ML) models are trained. We demonstrate this with case studies on flooding in Europe, and typhoon wind damage in the Philippines. Two sample selection bias correction methods from the ML literature are applied and one of these methods is also adjusted to our problem. These three methods are combined with stochastic generation of synthetic damage data. We demonstrate that for both case studies, the sample selection bias correction techniques reduce model errors, especially for the mean bias error this reduction can be larger than 30%. The novel combination with stochastic data generation seems to enhance these techniques. This shows that sample selection bias correction methods are beneficial for damage model transfer." @default.
• W3081022264 created "2020-09-01" @default.
• W3081022264 creator A5002837843 @default.
• W3081022264 creator A5006100138 @default.
• W3081022264 creator A5025724445 @default.
• W3081022264 creator A5061947345 @default.
• W3081022264 creator A5075546175 @default.
• W3081022264 creator A5086427737 @default.
• W3081022264 creator A5088239579 @default.
• W3081022264 date "2020-08-24" @default.
• W3081022264 modified "2023-10-16" @default.
• W3081022264 title "Improved Transferability of Data‐Driven Damage Models Through Sample Selection Bias Correction" @default.
• W3081022264 cites W1498436455 @default.
• W3081022264 cites W1565176583 @default.
• W3081022264 cites W1853837125 @default.
• W3081022264 cites W1901410642 @default.
• W3081022264 cites W1986894077 @default.
• W3081022264 cites W2007396488 @default.
• W3081022264 cites W2011375988 @default.
• W3081022264 cites W2021603915 @default.
• W3081022264 cites W2023626639 @default.
• W3081022264 cites W2030787822 @default.
• W3081022264 cites W2070469752 @default.
• W3081022264 cites W2095645566 @default.
• W3081022264 cites W2119819632 @default.
• W3081022264 cites W2122000057 @default.
• W3081022264 cites W2139122730 @default.
• W3081022264 cites W2144443458 @default.
• W3081022264 cites W2148143831 @default.
• W3081022264 cites W2148631958 @default.
• W3081022264 cites W2151514073 @default.
• W3081022264 cites W2162361225 @default.
• W3081022264 cites W2169234982 @default.
• W3081022264 cites W2172165978 @default.
• W3081022264 cites W2174075503 @default.
• W3081022264 cites W2238853499 @default.
• W3081022264 cites W2488386090 @default.
• W3081022264 cites W2533416275 @default.
• W3081022264 cites W2605614336 @default.
• W3081022264 cites W2734479400 @default.
• W3081022264 cites W2757434569 @default.
• W3081022264 cites W2766300505 @default.
• W3081022264 cites W2768629074 @default.
• W3081022264 cites W2797171939 @default.
• W3081022264 cites W2801974413 @default.
• W3081022264 cites W2802771096 @default.
• W3081022264 cites W2807818819 @default.
• W3081022264 cites W2886095310 @default.
• W3081022264 cites W2896205018 @default.
• W3081022264 cites W2902913073 @default.
• W3081022264 cites W2903247972 @default.
• W3081022264 cites W2911964244 @default.
• W3081022264 cites W2929824467 @default.
• W3081022264 cites W2943160824 @default.
• W3081022264 cites W3106889297 @default.
• W3081022264 cites W4254283507 @default.
• W3081022264 cites W4376043797 @default.
• W3081022264 doi "https://doi.org/10.1111/risa.13575" @default.
• W3081022264 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7891600" @default.
• W3081022264 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32830337" @default.
• W3081022264 hasPublicationYear "2020" @default.
• W3081022264 type Work @default.
• W3081022264 sameAs 3081022264 @default.
• W3081022264 citedByCount "8" @default.
• W3081022264 countsByYear W30810222642020 @default.
• W3081022264 countsByYear W30810222642022 @default.
• W3081022264 countsByYear W30810222642023 @default.
• W3081022264 crossrefType "journal-article" @default.
• W3081022264 hasAuthorship W3081022264A5002837843 @default.
• W3081022264 hasAuthorship W3081022264A5006100138 @default.
• W3081022264 hasAuthorship W3081022264A5025724445 @default.
• W3081022264 hasAuthorship W3081022264A5061947345 @default.
• W3081022264 hasAuthorship W3081022264A5075546175 @default.
• W3081022264 hasAuthorship W3081022264A5086427737 @default.
• W3081022264 hasAuthorship W3081022264A5088239579 @default.
• W3081022264 hasBestOaLocation W30810222642 @default.
• W3081022264 hasConcept C105795698 @default.
• W3081022264 hasConcept C119857082 @default.
• W3081022264 hasConcept C124101348 @default.
• W3081022264 hasConcept C129848803 @default.
• W3081022264 hasConcept C149782125 @default.
• W3081022264 hasConcept C151730666 @default.
• W3081022264 hasConcept C154945302 @default.
• W3081022264 hasConcept C185592680 @default.
• W3081022264 hasConcept C198531522 @default.
• W3081022264 hasConcept C2779343474 @default.
• W3081022264 hasConcept C33923547 @default.
• W3081022264 hasConcept C40423286 @default.
• W3081022264 hasConcept C41008148 @default.
• W3081022264 hasConcept C43617362 @default.
• W3081022264 hasConcept C75917345 @default.
• W3081022264 hasConcept C81917197 @default.
• W3081022264 hasConcept C86803240 @default.
• W3081022264 hasConcept C93959086 @default.
• W3081022264 hasConceptScore W3081022264C105795698 @default.
• W3081022264 hasConceptScore W3081022264C119857082 @default.
• W3081022264 hasConceptScore W3081022264C124101348 @default.
• W3081022264 hasConceptScore W3081022264C129848803 @default.

• next