The modeling was carried out using Maxent (Maximum Entropy) software version 3.4.1, which uses an optimization procedure comparing species presence (from occurrence records) with environment characteristics, based on the maximum entropy principle [121]. This machine-learning algorithm, designed to be performed with presence-only record data, has recently gained direct use in various field applications for species distribution modeling, with hundreds of peer-reviewed articles published each year [114]. As the literature recommends, we avoided relying only on the default automatic configuration of Maxent, given increasing debate regarding its use as a black-box, which may not always generate the best results [126, 135]. For each modeled species, we tested a combination of different features (linear, quadratic, product, threshold, and hinge), regularizations multiplier, and used cross-validation to select the optimal settings (S3 file). The Akaike information criterion (AICc) was used to select the optimal combination (the one with minimal AICc value) using NicheA software version 3.0 [93, 125]. Given the lack of occurrence records in some areas, the lack of detailed information on each species distribution range, and the non-availability of absence data, we created a bias file used to fine‐tune background and occurrence point selection in Maxent. For this, we restricted background sampling to a maximum radial distance of no more than 5 km from observation points, using SDMtoolbox [29]. We ran 20 replicates in Maxent for each model and used the mean values to summarize the model predictions results.

Note: The content above has been extracted from a research article, so it may not display correctly.



Q&A
Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.



We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.