Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380450149> ?p ?o ?g. }
- W4380450149 abstract "Abstract Integrative taxonomy combining data from multiple axes of biologically relevant variation is a major recent goal of systematics. Ideally, such taxonomies would be backed by similarly integrative species-delimitation analyses. Yet, most current methods rely solely or primarily on molecular data, with other layers often incorporated only in a post hoc qualitative or comparative manner. A major limitation is the difficulty of deriving and implementing quantitative parametric models linking different datasets in a unified ecological and evolutionary framework. Machine Learning methods offer flexibility in this arena by learning high-dimensional associations between observations (e.g., individual specimens) across a wide array of input features (e.g., genetics, geography, environment, and phenotype) to delineate statistical clusters. Here, I implement an unsupervised method using Self-Organizing (or “Kohonen”) Maps (SOMs). Recent extensions called SuperSOMs can integrate an arbitrary number of layers, each of which exerts independent influence on the two-dimensional output clustering via empirically estimated weights. These output clusters can then be delimited into K significant units that are interpreted as species or other entities. I show an empirical example in Desmognathus salamanders with layers representing alleles, space, climate, and traits. Simulations reveal that the SOM/SuperSOM approach can detect K= 1, does not over-split, reflects contributions from all layers with signal, and does not allow layer size (e.g., large genetic matrices) to overwhelm other datasets, desirable properties addressing major concerns from previous methods. Finally, I suggest that these and similar methods could integrate conservation-relevant layers such as population trends and human encroachment to delimit management units from an explicitly quantitative framework grounded in the ecology and evolution of species limits and boundaries." @default.
- W4380450149 created "2023-06-14" @default.
- W4380450149 creator A5077347417 @default.
- W4380450149 date "2023-06-13" @default.
- W4380450149 modified "2023-10-11" @default.
- W4380450149 title "Unsupervised Machine Learning for Species Delimitation, Integrative Taxonomy, and Biodiversity Conservation" @default.
- W4380450149 cites W1769408182 @default.
- W4380450149 cites W1943455375 @default.
- W4380450149 cites W1949176574 @default.
- W4380450149 cites W1964138333 @default.
- W4380450149 cites W1977601452 @default.
- W4380450149 cites W2003220902 @default.
- W4380450149 cites W2004444667 @default.
- W4380450149 cites W2008237095 @default.
- W4380450149 cites W2015929993 @default.
- W4380450149 cites W2023822819 @default.
- W4380450149 cites W2032456334 @default.
- W4380450149 cites W2033531754 @default.
- W4380450149 cites W2039079870 @default.
- W4380450149 cites W2045002121 @default.
- W4380450149 cites W2046079134 @default.
- W4380450149 cites W2058731966 @default.
- W4380450149 cites W2078043848 @default.
- W4380450149 cites W2084341220 @default.
- W4380450149 cites W2109230155 @default.
- W4380450149 cites W2119182375 @default.
- W4380450149 cites W2119444539 @default.
- W4380450149 cites W2120578286 @default.
- W4380450149 cites W2122264567 @default.
- W4380450149 cites W2125092464 @default.
- W4380450149 cites W2125936169 @default.
- W4380450149 cites W2125948619 @default.
- W4380450149 cites W2127499811 @default.
- W4380450149 cites W2138102892 @default.
- W4380450149 cites W2141283603 @default.
- W4380450149 cites W2142928551 @default.
- W4380450149 cites W2146102426 @default.
- W4380450149 cites W2146643231 @default.
- W4380450149 cites W2152437002 @default.
- W4380450149 cites W2161339576 @default.
- W4380450149 cites W2162307412 @default.
- W4380450149 cites W2165640245 @default.
- W4380450149 cites W2166972836 @default.
- W4380450149 cites W2168570223 @default.
- W4380450149 cites W2170706978 @default.
- W4380450149 cites W2179969133 @default.
- W4380450149 cites W2237821689 @default.
- W4380450149 cites W2280236176 @default.
- W4380450149 cites W2328275961 @default.
- W4380450149 cites W2580606745 @default.
- W4380450149 cites W2617349321 @default.
- W4380450149 cites W2782678399 @default.
- W4380450149 cites W2789669334 @default.
- W4380450149 cites W2797447231 @default.
- W4380450149 cites W2889222116 @default.
- W4380450149 cites W2901072521 @default.
- W4380450149 cites W2920765323 @default.
- W4380450149 cites W2932084606 @default.
- W4380450149 cites W2936748293 @default.
- W4380450149 cites W2947990342 @default.
- W4380450149 cites W2950373858 @default.
- W4380450149 cites W2952084747 @default.
- W4380450149 cites W2953259387 @default.
- W4380450149 cites W2958805699 @default.
- W4380450149 cites W2988920411 @default.
- W4380450149 cites W3005201051 @default.
- W4380450149 cites W3008695158 @default.
- W4380450149 cites W3015292474 @default.
- W4380450149 cites W3030061166 @default.
- W4380450149 cites W3114248982 @default.
- W4380450149 cites W3114732641 @default.
- W4380450149 cites W3128200846 @default.
- W4380450149 cites W3154040839 @default.
- W4380450149 cites W3163112933 @default.
- W4380450149 cites W3163915094 @default.
- W4380450149 cites W3181274160 @default.
- W4380450149 cites W3182093424 @default.
- W4380450149 cites W3196146750 @default.
- W4380450149 cites W3203900017 @default.
- W4380450149 cites W3208630603 @default.
- W4380450149 cites W4210413950 @default.
- W4380450149 cites W4213345184 @default.
- W4380450149 cites W4223649474 @default.
- W4380450149 cites W4281728047 @default.
- W4380450149 cites W4297458148 @default.
- W4380450149 cites W50599583 @default.
- W4380450149 doi "https://doi.org/10.1101/2023.06.12.544639" @default.
- W4380450149 hasPublicationYear "2023" @default.
- W4380450149 type Work @default.
- W4380450149 citedByCount "0" @default.
- W4380450149 crossrefType "posted-content" @default.
- W4380450149 hasAuthorship W4380450149A5077347417 @default.
- W4380450149 hasBestOaLocation W43804501491 @default.
- W4380450149 hasConcept C105795698 @default.
- W4380450149 hasConcept C119857082 @default.
- W4380450149 hasConcept C124101348 @default.
- W4380450149 hasConcept C144024400 @default.
- W4380450149 hasConcept C149923435 @default.
- W4380450149 hasConcept C154945302 @default.
- W4380450149 hasConcept C18903297 @default.