Using Maxent to model the historic distributions of stonefly species in Illinois streams: The effects of regularization and threshold selections

Cao, Yong; DeWalt, R. Edward; Robinson, Jason L.; Tweddale, Tari; Hinz, Leon C.; Pessino, Massimo

doi:10.1016/j.ecolmodel.2013.03.012

Cited by 114 publications

(77 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sensitivity and specificity were critically affected by the choice of thresholds, and TSS was affected by the species distribution rate (Cao et al. ). Although the applicability of the AUC for the assessment of presence/absence predictions has been questioned (Lobo et al.…”

Section: Discussionmentioning

confidence: 99%

The distribution of Athetis lepigone and prediction of its potential distribution based on GARP and MaxEnt

Wang

Li³

et al. 2016

J Applied Entomology

View full text Add to dashboard Cite

Athetis lepigone (Möschler) is a new agronomic pest which has caused serious damages to summer maize in China. In order to effectively monitor it, it is necessary to carry‐out a worldwide investigation on its potential geographical distribution. In this study, we give two ecological niche models, Genetic Algorithm for Rule‐set Production and Maximum Entropy (MaxEnt), to predict the potential geographical distribution of A. lepigone. The results indicate that the suitable areas for A. lepigone are mainly in China (Beijing, Tianjin, central and southern Hebei, northern Jiangsu, Shandong, most of Henan, northern Anhui, central and southern Shanxi, central and southern Shaanxi, small parts of north‐west in Hubei, eastern Gansu, parts of Ningxia, western of Xinjiang and Dandong, and Liaoning) and other Asian countries (South Korea, North Korea and Japan). Parts of Europe (south‐western Russia, Ukraine, Moldova, Romania, Hungary, Bulgaria, Slovenia, and Croatia, Bosnia and Herzegovina, Serbia, parts of Austria, western Poland, the Czech Republic, Germany, northern Italy, Denmark, western Lithuania, Latvia, Estonia, southern Finland and Sweden) are also highly suitable for A. lepigone. In addition, in the states of the USA including Michigan, New York, Chicago, Missouri, Ohio, Illinois and Indiana are also favourable for its occurrence although till now no reports about of this species has been recorded. A jackknife test in MaxEnt showed that the mean temperature of the driest quarter was the most important environmental variable affecting the distribution of this pest.

show abstract

Section: Discussionmentioning

confidence: 99%

The distribution of Athetis lepigone and prediction of its potential distribution based on GARP and MaxEnt

Wang

Li³

et al. 2016

J Applied Entomology

View full text Add to dashboard Cite

show abstract

“…Concerns about model complexity and overfitting have received increased attention in the niche modelling literature, with applications of information theory to machine learning models being Table 1 Significance testing on mixed models. explored as an alternative to cross-validation approaches for model evaluation (Anderson & Gonzalez, 2011;Rodda et al, 2011;Warren & Seifert, 2011;Cao et al, 2013;Warren et al, 2014). Area rankings capture the percentage change in suitable area within a minimum convex polygon of currently occupied cells in California.…”

Section: Discussionmentioning

confidence: 99%

Multiple sources of uncertainty affect metrics for ranking conservation risk under climate change

Wright

Hijmans

Schwartz

et al. 2014

Diversity and Distributions

View full text Add to dashboard Cite

Aim Ecological niche modelling is one of the main tools that allows for the incorporation of climate change effects into conservation planning. For example, ecological niche model predictions can be used to rank species by degree of predicted future habitat loss. While many studies have considered how different modelling decisions contribute to uncertainty in niche model outputs, here we evaluate how metrics used to rank species by conservation risk respond to the choice of global climate models, greenhouse gas emission scenarios, suitable versus unsuitable threshold values, and the degree of model complexity.Location California, USA.Methods We built ecological niche models for 153 species of reptiles and amphibians. Reduced complexity models were compared to default complexity models using AICc to select climate variables and tune Maxent' s built-in regularization parameter. We predicted the distribution of climatically suitable habitat under future (2041-2060) climate conditions according to 11 global climate models, four representative concentration pathways, and three threshold values. Two metrics to rank species by predicted future loss of climatically suitable habitat were calculated for each set of modelling decisions. To determine the effects of modelling decisions on rankings, we used mixed models. ResultsOur results indicate that while individual modelling decisions had relatively small effects on species ranks alone, in combination, they lead to very different conservation assessments.Main conclusions We recommend that a wide range of modelling decisions be explored and that variation in ranks across runs be reported as a first step in identifying the uncertainty in rank metrics used for assessing conservation risk under changing, but uncertain climate predictions.

show abstract

“…Due to these results, we generated all the models with the default settings of MaxEnt (β = 1). Similar studies in which the β = 1 was chosen as the better regularization parameter include Cao et al (2013) and Mason et al (2014).…”

Section: Geographic Model Fittingmentioning

confidence: 99%

Geographic and Potential Distribution of a Poorly Known South American Bat,Histiotus macrotus(Chiroptera: Vespertilionidae)

Giménez

Giannini

Schiaffini

et al. 2015

Acta Chiropterologica

View full text Add to dashboard Cite

Using Maxent to model the historic distributions of stonefly species in Illinois streams: The effects of regularization and threshold selections

Cited by 114 publications

References 63 publications

The distribution of Athetis lepigone and prediction of its potential distribution based on GARP and MaxEnt

The distribution of Athetis lepigone and prediction of its potential distribution based on GARP and MaxEnt

Multiple sources of uncertainty affect metrics for ranking conservation risk under climate change

Geographic and Potential Distribution of a Poorly Known South American Bat,Histiotus macrotus(Chiroptera: Vespertilionidae)

Contact Info

Product

Resources

About