Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Comment on "Pollination supply models from a local to global scale": convolutional neural networks can improve pollination supply models at a global scale

  • Allen-Perkins, Alfonso
  • Giménez-García, Ángel
  • Magrach, Ainhoa
  • Galeano, Javier
  • Tarquis, Ana María
  • Bartomeus, Ignasi
Tools to predict pollinator activity at regional scales generally rely on land cover maps, combined with human-inferred mechanistic rules and/or expert knowledge. Recently, showed that, using large pollinator datasets, different environmental variables, and machine learning models, those predictions can be enhanced but at the cost of losing model interpretability. Here, we complement this work by exploring the potential of using advanced machine learning techniques to directly infer wild-bee visitation rates across different biomes only from land cover maps and available pollinator data while maintaining a mechanistic interpretation. In particular, we assess the ability of convolutional neural networks (CNNs), which are deep learning models, to infer mechanistic rules able to predict pollinator habitat use. At a global scale, our CNNs achieved a rank correlation coefficient of 0.44 between predictions and observations of pollinator visitation rates, doubling that of the previous human-inferred mechanistic models presented in (0.17). Most interestingly, we show that the predictions depend on both landscape composition and configuration variables, with prediction rules being more complex than those of traditional mechanistic processes. We also demonstrate how CNNs can improve the predictions of our previous data-driven models that did not use land cover maps by creating a new model that combined the predictions of our CNN with those of our best regression model based on environmental variables, a Bayesian ridge regressor. This new ensemble model improved the overall rank correlation from 0.56 to 0.64., This research was funded by the Comunidad de Madrid through the Research Grants for Young Investigators call from Universidad Politécnica de Madrid (APOYO-JOVENES-21-9K9EVJ-36-3VPZPJ). Alfonso Allen-Perkins was also funded by the Spanish Ministry of Science and Innovation (MICINN) through the TASTE (PID2021-127607OB-I00) and ChaSisCOMA (PID2021-122711NB-C21) projects. Ainhoa Magrach acknowledges funding from a Ministry of Science and Innovation grant (PID2021-127900NB-I00), an Ikerbasque research professorship, and the Spanish Ministry of Science and Innovation and the European Social Fund through the Ramón y Cajal Program (RYC2021-032351-I365). Research is co-funded by the European Union (ERC Consolidator Grant, GorBEEa 101086771). This research is part of the project PID2021-127900NB-I00 funded by the Ministry of Science and Innovation and supported by María de Maeztu Unit of Excellence 2023–2027, ref. CEX2021-001201-M, funded by MCIN/AEI /10.13039/501100011033., With funding from the Spanish government through the ‘María de Maeztu Unit of Excelence’ accreditation (CEX2021-001201-M), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

Islas: Los ecosistemas más vulnerables a las invasiones biológicas, Islands: The ecosystems most vulnerable to biological invasions

  • Muñoz-Gallego, Raquel
  • Correia, Marta
  • Costa, Alba
  • Donoso, Isabel
  • Hervías-Parejo, Sandra
  • Mieles, Alejandro
  • Quitián, Marta
  • Vollstädt, Maximilian
  • Traveset, Anna
[ES] Islands are ecosystems particularly vulnerable to biological invasions due to their geographic isolation, high specialization and low pressure from natural predators and competition. In fact, invasive species have contributed to 86% of the extinctions of island endemic species. In this research, we review the ecological impacts of biological invasions on islands, both on the functional traits of native species and on different ecological functions and interactions. The introduction of species can affect the functional traits of species, either by increasing functional diversity by adding new traits into the ecosystem, or by reducing it by introducing redundant traits to those of native species. Ecological interactions, both mutualistic (pollination, seed dispersal, plant-microorganism) and antagonistic (herbivory, pathogenic parasitism, predation), can also be altered. The indirect impacts of invasive species, complex and difficult to quantify, can be crucial in island ecosystems, which are commonly affected by multiple invasive species that may interact with each other. Although non-native species can cause significant ecological disruptions, in some cases they can also functionally replace extinct native species. Addressing the knowledge gaps identified in this study will be essential to protect island ecosystems from biological invasions. Future research should adopt interdisciplinary and collaborative approaches that integrate contextual variation and the different levels of ecological organization. Promoting this type of research will be essential to design more effective conservation strategies aimed at preserving not only island biodiversity, but also the stability and functionality of these unique ecosystems., [EN] Islands are ecosystems particularly vulnerable to biological invasions due to their geographic isolation, high specialization and low pressure from natural predators and competition. In fact, invasive species have contributed to 86% of the extinctions of island endemic species. In this research, we review the ecological impacts of biological invasions on islands, both on the functional traits of native species and on different ecological functions and interactions. The introduction of species can affect the functional traits of species, either by increasing functional diversity by adding new traits into the ecosystem, or by reducing it by introducing redundant traits to those of native species. Ecological interactions, both mutualistic (pollination, seed dispersal, plant-microorganism) and antagonistic (herbivory, pathogenic parasitism, predation), can also be altered. The indirect impacts of invasive species, complex and difficult to quantify, can be crucial in island ecosystems, which are commonly affected by multiple invasive species that may interact with each other. Although non-native species can cause significant ecological disruptions, in some cases they can also functionally replace extinct native species. Addressing the knowledge gaps identified in this study will be essential to protect island ecosystems from biological invasions. Future research should adopt interdisciplinary and collaborative approaches that integrate contextual variation and the different levels of ecological organization. Promoting this type of research will be essential to design more effective conservation strategies aimed at preserving not only island biodiversity, but also the stability and functionality of these unique ecosystems., Este estudio se ha llevado a cabo en el marco de las actividades del Gobierno de España a través de la Unidad de Excelencia María de Maeztu 2023-2027 (MCIN/AEI/10.13039/501100011033) concedido al IMEDEA (CSIC-UIB) (ref. CEX2021-001198) y al BC3 (ref. CEX2021-001201-M). El trabajo se enmarca también dentro del proyecto IslandLife (Ref. 101054177) financiado por el Consejo Europeo de Investigación (ERC, Advanced Grant). I. Donoso fue financiada por una beca postdoctoral Ikerbasque. M. Vollstädt fue financiado por una beca postdoctoral Marie Curie (Horizon-TMA-MSCA-101149502)., With funding from the Spanish government through the "Maria de Maeztu Centre of Excellence" accreditation (CEX2021-001198)., With funding from the Spanish government through the "Maria de Maeztu Centre of Excellence" accreditation (CEX2021-001201-M)., Peer reviewed