Use of Maximum Entropy Modeling in Wildlife Research

By Roger A. Baldwin. Entropy, 2009

784 citations recorded by the source corpus.

Maximum entropy (Maxent) modeling has great potential for identifying distributions and habitat selection of wildlife given its reliance on only presence locations. Recent studies indicate Maxent is relatively insensitive to spatial errors associated with location data, requires few locations to construct useful models, and performs better than other presence-only modeling approaches. Further advances are needed to better define model thresholds, to test model significance, and to address model selection. Additionally, development of modeling approaches is needed when using repeated sampling of known individuals to assess habitat selection. These advancements would strengthen the utility of Maxent for wildlife research and management.

Subfields: Ecological Modeling, Ecology, Nature and Landscape Conservation

View Paper: https://www.semanticscholar.org/paper/64adaeb65c6e88185f15ff0c3a9900773daef21e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ecological Modeling

1. Peter J. Galante
2. Robert Muscarella
3. S. Goodman
4. Babatunde Alade
5. S. Jansa
6. Francis Gilbert
7. Iben Ørsted
8. Michael Ørsted

In Ecology

1. S. Goodman
2. Peter J. Galante
3. Robert Muscarella
4. Iben Ørsted
5. Michael Ørsted
6. Francis Gilbert
7. Babatunde Alade
8. S. Jansa

In Nature and Landscape Conservation

1. Robert Muscarella
2. Peter J. Galante
3. Francis Gilbert
4. Iben Ørsted
5. Michael Ørsted
6. S. Goodman
7. Victoria Nolan
8. Emad Kaky

Citations in the corpus

• The challenge of modeling niches and distributions for data‐poor species: a comprehensive approach to model complexity (2018, methodology): “Regarding the first approach, some studies have advocated the use of information criteria, specifically Akaike’s information criterion in the selection of optimally complex ENMs (AICc, corrected for small sample size; Baldwin 2009, Warren and Seifert 2011).”
• Marketing Mix Modeling Using PLS-SEM, Bootstrapping the Model Coefficients (2021, methodology): “As a solution to time series bootstrapping, Vinod and López‐de‐Lacalle [13] proposed the application of the principle of maximum entropy (ME), explained in depth by [27].”
• A comparison between Ensemble and MaxEnt species distribution modelling approaches for conservation: A case study with Egyptian medicinal plants (2020, background): “1A), after discarding all species with fewer than 10 records because these would result in models with low accuracy (Baldwin, 2009; van Proosdij et al., 2015).”
• Where the bears roam in Majella National Park, Italy (2014, background): “The least contributing predictors were removed stepwise (Baldwin, 2009), until the most parsimonious number of predictors resulting in an AUC >0.”
• Mapping the Global Potential Geographical Distribution of Black Locust (Robinia Pseudoacacia L.) Using Herbarium Data and a Maximum Entropy Model (2014, background): “Upward trends for variables indicate a positive relationship; downward movements represent a negative relationship; and the magnitude of these movements indicates the strength of the relationship [51].”
• Species distribution models of the Spotted Wing Drosophila ( Drosophila suzukii , Diptera: Drosophilidae) in its native and invasive range reveal an ecological niche shift (2018, background): “This has two purposes; firstly, this hierarchical procedure removes one of a pair of collinear predictors transparently based on actual model performance rather than the customary a priori, subjective elimination (Baldwin, 2009; van Gils et al., 2012).”