FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894655723> ?p ?o ?g. }

• W2894655723 endingPage "2970" @default.
• W2894655723 startingPage "2954" @default.
• W2894655723 abstract "Abstract Advances in data acquisition and statistical methodology have led to growing use of machine‐learning methods to predict geomorphic disturbance events. However, capturing the data required to parameterize these models is challenging because of expense or, more fundamentally, because the phenomenon of interest occurs infrequently. Thus, it is important to understand how the nature of the data used to train predictive models influences their performance. Using a database of cliff failure prediction and associated covariates from Auckland, New Zealand, we assess the performance of seven machine‐learning algorithms under different sampling strategies. Three sampling components are investigated: (i) the number of data points used in model training (sample size), (ii) the prevalence of occurrences (presences) in the data, and (iii) random versus spatial sampling strategy. Across the seven algorithms, small sample sizes can produce models that perform relatively well, especially if the prime concern is identifying key predictors rather than quantifying risk or predicting categorical outcome. Our analyses show that for the same effort (i.e., number of samples), sampling around multiple locations provides better predictions than sampling at just one or a few locations. Predictive performance may be further improved by considering issues such as the nature of what absences actually represent and paying careful attention to decisions about hyperparameter tuning, training‐testing data splits, and threshold optimization. It is well known that big data can inform complex data‐driven modeling, but here we show that careful sampling can facilitate informative event prediction even from small data." @default.
• W2894655723 created "2018-10-12" @default.
• W2894655723 creator A5005227632 @default.
• W2894655723 creator A5087326896 @default.
• W2894655723 date "2018-11-01" @default.
• W2894655723 modified "2023-10-05" @default.
• W2894655723 title "Using Machine Learning to Predict Geomorphic Disturbance: The Effects of Sample Size, Sample Prevalence, and Sampling Strategy" @default.
• W2894655723 cites W1487536649 @default.
• W2894655723 cites W1494196016 @default.
• W2894655723 cites W1513618424 @default.
• W2894655723 cites W1604012267 @default.
• W2894655723 cites W1613165158 @default.
• W2894655723 cites W1710732412 @default.
• W2894655723 cites W1751153847 @default.
• W2894655723 cites W1910582249 @default.
• W2894655723 cites W1912463333 @default.
• W2894655723 cites W192021582 @default.
• W2894655723 cites W1941919908 @default.
• W2894655723 cites W1990748933 @default.
• W2894655723 cites W2006047816 @default.
• W2894655723 cites W2006333257 @default.
• W2894655723 cites W2023203753 @default.
• W2894655723 cites W2026492654 @default.
• W2894655723 cites W2032536435 @default.
• W2894655723 cites W2032589890 @default.
• W2894655723 cites W2038281504 @default.
• W2894655723 cites W2039875746 @default.
• W2894655723 cites W2040247202 @default.
• W2894655723 cites W2042130715 @default.
• W2894655723 cites W2047096745 @default.
• W2894655723 cites W2052030669 @default.
• W2894655723 cites W2055764609 @default.
• W2894655723 cites W2074074333 @default.
• W2894655723 cites W2075785321 @default.
• W2894655723 cites W2076053517 @default.
• W2894655723 cites W2081614715 @default.
• W2894655723 cites W2097601813 @default.
• W2894655723 cites W2098827790 @default.
• W2894655723 cites W2101807845 @default.
• W2894655723 cites W2105189544 @default.
• W2894655723 cites W2111796869 @default.
• W2894655723 cites W2115268776 @default.
• W2894655723 cites W2119202692 @default.
• W2894655723 cites W2123379755 @default.
• W2894655723 cites W2124286013 @default.
• W2894655723 cites W2126244767 @default.
• W2894655723 cites W2130369392 @default.
• W2894655723 cites W2145726494 @default.
• W2894655723 cites W2153656222 @default.
• W2894655723 cites W2155653793 @default.
• W2894655723 cites W2157963336 @default.
• W2894655723 cites W2191761327 @default.
• W2894655723 cites W2192976093 @default.
• W2894655723 cites W2230353612 @default.
• W2894655723 cites W2298958503 @default.
• W2894655723 cites W2507432949 @default.
• W2894655723 cites W2580591509 @default.
• W2894655723 cites W2600681398 @default.
• W2894655723 cites W2757787785 @default.
• W2894655723 cites W2792919287 @default.
• W2894655723 cites W2793845033 @default.
• W2894655723 cites W3125937743 @default.
• W2894655723 cites W429766147 @default.
• W2894655723 doi "https://doi.org/10.1029/2018jf004640" @default.
• W2894655723 hasPublicationYear "2018" @default.
• W2894655723 type Work @default.
• W2894655723 sameAs 2894655723 @default.
• W2894655723 citedByCount "19" @default.
• W2894655723 countsByYear W28946557232019 @default.
• W2894655723 countsByYear W28946557232020 @default.
• W2894655723 countsByYear W28946557232021 @default.
• W2894655723 countsByYear W28946557232022 @default.
• W2894655723 countsByYear W28946557232023 @default.
• W2894655723 crossrefType "journal-article" @default.
• W2894655723 hasAuthorship W2894655723A5005227632 @default.
• W2894655723 hasAuthorship W2894655723A5087326896 @default.
• W2894655723 hasBestOaLocation W28946557231 @default.
• W2894655723 hasConcept C105795698 @default.
• W2894655723 hasConcept C106131492 @default.
• W2894655723 hasConcept C119043178 @default.
• W2894655723 hasConcept C119857082 @default.
• W2894655723 hasConcept C124101348 @default.
• W2894655723 hasConcept C129848803 @default.
• W2894655723 hasConcept C140779682 @default.
• W2894655723 hasConcept C154945302 @default.
• W2894655723 hasConcept C185592680 @default.
• W2894655723 hasConcept C198531522 @default.
• W2894655723 hasConcept C2777317252 @default.
• W2894655723 hasConcept C31972630 @default.
• W2894655723 hasConcept C33923547 @default.
• W2894655723 hasConcept C41008148 @default.
• W2894655723 hasConcept C43617362 @default.
• W2894655723 hasConcept C5274069 @default.
• W2894655723 hasConcept C75917345 @default.
• W2894655723 hasConcept C8642999 @default.
• W2894655723 hasConceptScore W2894655723C105795698 @default.
• W2894655723 hasConceptScore W2894655723C106131492 @default.
• W2894655723 hasConceptScore W2894655723C119043178 @default.

• next