Species distribution models of the Spotted Wing
            Drosophila
            (
            Drosophila suzukii
            , Diptera: Drosophilidae) in its native and invasive range reveal an ecological niche shift

La elaboración de modelos de nicho ecológico (MNE/Ecological Niche Models) y/o modelos de distribución de especies (MDE/Species Distribution Models) requieren de diferentes fuentes de información para poder hacer la inferencia de la distribución de las especies en un espacio geográfico y ecológico interactuante (Ríos-Muñoz & Espinosa-Martínez, 2019; Peterson et al., 2011). La información biológica está representada por los sitios geográficos donde las especies han sido registradas (datos de ocurrencia) y por lo tanto, bajo la perspectiva de los MNE/MDE, representan los sitios donde existen las condiciones ambientalmente viables (tanto físicas como ecológicas) para que las especies puedan mantenerse a largo plazo (Pulliam, 2000). Por esta razón, es necesario considerar diferentes aspectos referentes a la calidad de la información que representan los datos de ocurrencia de las especies y hacer énfasis en algunas consideraciones que deben tenerse con este tipo de datos. Esta es la segunda entrega de la serie de editoriales que están enfocadas a este proceso.

Download Full-text

NichePy: modular tools for estimating the similarity of ecological niche and species distribution models

Methods in Ecology and Evolution ◽

10.1111/j.2041-210x.2011.00184.x ◽

2012 ◽

Vol 3 (3) ◽

pp. 484-489 ◽

Cited By ~ 5

Author(s):

Bastian Bentlage ◽

Mariya Shcheglovitova

Keyword(s):

Species Distribution ◽

Ecological Niche ◽

Species Distribution Models ◽

Distribution Models

Download Full-text

Using species distribution models with climate change scenarios to aid ecological restoration decisionmaking for southern California shrublands

10.2737/psw-rp-270 ◽

2018 ◽

Author(s):

Erin C. Riordan ◽

Arlee M. Montalvo ◽

Jan L. Beyers

Keyword(s):

Climate Change ◽

Ecological Restoration ◽

Species Distribution ◽

Southern California ◽

Species Distribution Models ◽

Climate Change Scenarios ◽

Distribution Models

Download Full-text

A new record of Stylophorum diphyllum (Michx.) Nutt. in Canada: A case study of the value and limitations of building species distribution models for very rare plants

The Journal of the Torrey Botanical Society ◽

10.3159/torrey-d-18-00026.1 ◽

2019 ◽

Vol 146 (2) ◽

pp. 119 ◽

Cited By ~ 2

Author(s):

Jenny L. McCune

Keyword(s):

Species Distribution ◽

New Record ◽

Species Distribution Models ◽

Rare Plants ◽

Distribution Models

Download Full-text

A Robust Prediction Model for Species Distribution Using Bagging Ensembles with Deep Neural Networks

Remote Sensing ◽

10.3390/rs13081495 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1495

Author(s):

Jehyeok Rew ◽

Yongjang Cho ◽

Eenjun Hwang

Keyword(s):

Neural Networks ◽

Species Distribution ◽

Best Practice ◽

Deep Neural Networks ◽

Species Distribution Models ◽

Species Distribution Model ◽

Environmental Data ◽

Distribution Model ◽

Distribution Models ◽

Robust Prediction

Species distribution models have been used for various purposes, such as conserving species, discovering potential habitats, and obtaining evolutionary insights by predicting species occurrence. Many statistical and machine-learning-based approaches have been proposed to construct effective species distribution models, but with limited success due to spatial biases in presences and imbalanced presence-absences. We propose a novel species distribution model to address these problems based on bootstrap aggregating (bagging) ensembles of deep neural networks (DNNs). We first generate bootstraps considering presence-absence data on spatial balance to alleviate the bias problem. Then we construct DNNs using environmental data from presence and absence locations, and finally combine these into an ensemble model using three voting methods to improve prediction accuracy. Extensive experiments verified the proposed model’s effectiveness for species in South Korea using crowdsourced observations that have spatial biases. The proposed model achieved more accurate and robust prediction results than the current best practice models.

Download Full-text