Show simple item record

Files in this item

Thumbnail

Item metadata

dc.contributor.authorKittlein, Marcelo
dc.contributor.authorMora, Matías S.
dc.contributor.authorMapelli, Fernando J.
dc.contributor.authorAustrich, Ailin
dc.contributor.authorGaggiotti, Oscar Eduardo
dc.date.accessioned2022-12-16T00:40:01Z
dc.date.available2022-12-16T00:40:01Z
dc.date.issued2021-12-16
dc.identifier.citationKittlein , M , Mora , M S , Mapelli , F J , Austrich , A & Gaggiotti , O E 2021 , ' Deep learning and satellite imagery predict genetic diversity and differentiation ' , Methods in Ecology and Evolution , vol. Early View . https://doi.org/10.1111/2041-210X.13775en
dc.identifier.issn2041-210X
dc.identifier.otherPURE: 276446842
dc.identifier.otherPURE UUID: 82cd915c-6730-4be8-a94c-aca5acf3b77d
dc.identifier.otherORCID: /0000-0003-1827-1493/work/105956717
dc.identifier.otherScopus: 85121373619
dc.identifier.otherWOS: 000730673500001
dc.identifier.urihttps://hdl.handle.net/10023/26615
dc.descriptionFunding: Financial support was provided by Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET, PIP 11220150100066 CO), UNMdP (Project EXA903457/18) and FONCYT (PICT 201-0427).en
dc.description.abstract1. During the last decade, convolutional neural networks (CNNs) have revolutionised the application of deep learning (DL) methods to classification tasks and object recognition. These procedures can capture the key features of image data that are not easily visible to the human eye and use them to classify and predict outcomes with exceptional precision. 2. Here, we show for the first time that CNNs provide highly accurate predictions for small-scale genetic differentiation and diversity in Ctenomys australis, a subterranean rodent from central Argentina. Using microsatellite genotypes and high-resolution satellite imagery, we trained a simple CNN to predict local FST and mean allele richness. To identify landscape features with high impact on predicted values, we applied species distribution models to obtain the distribution of suitable habitat. Subsequent use of a machine learning algorithm (random forest) allowed us to identify the attributes that contribute the most to predictions of population genetic metrics. 3. Predictions obtained from the CNN accounted for more than 98% of the variation observed both in FST and mean allele richness values. Random forest regression on landscape metrics indicated that features involving connectivity and consistent prevalence of suitable habitat promoted genetic diversity and reduced genetic differentiation in C. australis. 4. Validation with synthetic data via simulations of genetic differentiation based on the landscape structure of the study area and of a nearby area showed that DL models are able to capture complex relationships between actual data and synthetic data in the same landscape and between synthetic data generated under different landscapes. 5. Our approach represents an objective and powerful approach to landscape genetics because it can extract information from patterns that are not easily identified by humans. Spatial predictions from the CNN may assist in the identification of areas of interest for biodiversity conservation and management of populations.
dc.language.isoeng
dc.relation.ispartofMethods in Ecology and Evolutionen
dc.rightsCopyright © 2021 British Ecological Society. This work has been made available online in accordance with publisher policies or with permission. Permission for further reuse of this content should be sought from the publisher or the rights holder. This is the author created accepted manuscript following peer review and may differ slightly from the final published version. The final published version of this work is available at https://doi.org/10.1111/2041-210X.13775.en
dc.subjectBiodiversity predictionen
dc.subjectConvolutional neural networksen
dc.subjectCoastal dunesen
dc.subjectCtenomys australisen
dc.subjectDeep learningen
dc.subjectGenetic differentiationen
dc.subjectLandscape geneticsen
dc.subjectSubterranean rodentsen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectQH301 Biologyen
dc.subjectQH426 Geneticsen
dc.subjectDASen
dc.subject.lccQA75en
dc.subject.lccQH301en
dc.subject.lccQH426en
dc.titleDeep learning and satellite imagery predict genetic diversity and differentiationen
dc.typeJournal articleen
dc.description.versionPostprinten
dc.contributor.institutionUniversity of St Andrews. School of Biologyen
dc.contributor.institutionUniversity of St Andrews. Scottish Oceans Instituteen
dc.contributor.institutionUniversity of St Andrews. St Andrews Bioinformatics Uniten
dc.contributor.institutionUniversity of St Andrews. Marine Alliance for Science & Technology Scotlanden
dc.identifier.doihttps://doi.org/10.1111/2041-210X.13775
dc.description.statusPeer revieweden
dc.date.embargoedUntil2022-12-16


This item appears in the following Collection(s)

Show simple item record