This study employs spatial filtering of occurrence data with the aim of reducing overfitting to sampling bias in ecological niche models (ENMs). Sampling bias in geographic space leads to localities that may also be biased in environmental space. If so, the model can overfit to those biases. As a preliminary test addressing this issue, we used Maxent, bioclimatic variables, and occurrence localities of a broadly distributed Malagasy tenrec, Microgale cowani (Family Tenrecidae: Subfamily Oryzorictinae). We modeled the abiotically suitable area of this species using three distinct datasets: unfiltered, spatially filtered, and rarefied unfiltered localities. To quantify overfitting and model performance, we calculated evaluation AUC, the difference between calibration and evaluation AUC (= AUCdiff), and omission rates. Models made with the filtered dataset showed lower overfitting and better performance than the other two suites of models, having lower omission rates and AUCdiff, and a higher AUCevaluation. Additionally, the rarefied unfiltered dataset performed better than the unfiltered one for three evaluation metrics, likely because the larger datasets reinforced the biases. These results indicate that spatial filtering of occurrence localities may allow biogeographers to produce better models.
","abstract_html":"<p>This study employs spatial filtering of occurrence data with the aim of reducing overfitting to sampling bias in ecological niche models (ENMs). Sampling bias in geographic space leads to localities that may also be biased in environmental space. If so, the model can overfit to those biases. As a preliminary test addressing this issue, we used Maxent, bioclimatic variables, and occurrence localities of a broadly distributed Malagasy tenrec, Microgale cowani (Family Tenrecidae: Subfamily Oryzorictinae). We modeled the abiotically suitable area of this species using three distinct datasets: unfiltered, spatially filtered, and rarefied unfiltered localities. To quantify overfitting and model performance, we calculated evaluation AUC, the difference between calibration and evaluation AUC (= AUCdiff), and omission rates. Models made with the filtered dataset showed lower overfitting and better performance than the other two suites of models, having lower omission rates and AUCdiff, and a higher AUCevaluation. Additionally, the rarefied unfiltered dataset performed better than the unfiltered one for three evaluation metrics, likely because the larger datasets reinforced the biases. These results indicate that spatial filtering of occurrence localities may allow biogeographers to produce better models.</p>","abstract_has_math":false,"creators":["Boria, Robert"],"institution":null,"degree_name":"Master of Science (M.S.)","degree_level":"Thesis","degree_discipline":"Biology","degree_department":null,"school":null,"contributors":["Robert P. Anderson","Amy C. Berkov","Ana Carnaval"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-01T08:00:00Z","date_published":"2014-01-01T08:00:00Z","updated_at":"2026-07-24T01:56:59Z","subjects":["Modeling","Niche","Ecology","Biology"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://academicworks.cuny.edu/cc_etds_theses/537","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Robert P. Anderson","Amy C. Berkov","Ana Carnaval"]},{"key":"dc:creator","label":"Author","values":["Boria, Robert"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-07-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biology"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Modeling","Niche","Ecology","Biology"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://academicworks.cuny.edu/cc_etds_theses/537"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This study employs spatial filtering of occurrence data with the aim of reducing overfitting to sampling bias in ecological niche models (ENMs). Sampling bias in geographic space leads to localities that may also be biased in environmental space. If so, the model can overfit to those biases. As a preliminary test addressing this issue, we used Maxent, bioclimatic variables, and occurrence localities of a broadly distributed Malagasy tenrec, Microgale cowani (Family Tenrecidae: Subfamily Oryzorictinae). We modeled the abiotically suitable area of this species using three distinct datasets: unfiltered, spatially filtered, and rarefied unfiltered localities. To quantify overfitting and model performance, we calculated evaluation AUC, the difference between calibration and evaluation AUC (= AUCdiff), and omission rates. Models made with the filtered dataset showed lower overfitting and better performance than the other two suites of models, having lower omission rates and AUCdiff, and a higher AUCevaluation. Additionally, the rarefied unfiltered dataset performed better than the unfiltered one for three evaluation metrics, likely because the larger datasets reinforced the biases. These results indicate that spatial filtering of occurrence localities may allow biogeographers to produce better models.
"]},{"key":"dc:title","label":"Title","values":["Methodological advancements for improving performance and generating ensemble ecological niche models"]}]}],"canonical_facts":{"dc:contributor":["Robert P. Anderson","Amy C. Berkov","Ana Carnaval"],"dc:creator":["Boria, Robert"],"dc:date.available":["2016-07-01T07:00:00Z"],"dc:description.abstract":["This study employs spatial filtering of occurrence data with the aim of reducing overfitting to sampling bias in ecological niche models (ENMs). Sampling bias in geographic space leads to localities that may also be biased in environmental space. If so, the model can overfit to those biases. As a preliminary test addressing this issue, we used Maxent, bioclimatic variables, and occurrence localities of a broadly distributed Malagasy tenrec, Microgale cowani (Family Tenrecidae: Subfamily Oryzorictinae). We modeled the abiotically suitable area of this species using three distinct datasets: unfiltered, spatially filtered, and rarefied unfiltered localities. To quantify overfitting and model performance, we calculated evaluation AUC, the difference between calibration and evaluation AUC (= AUCdiff), and omission rates. Models made with the filtered dataset showed lower overfitting and better performance than the other two suites of models, having lower omission rates and AUCdiff, and a higher AUCevaluation. Additionally, the rarefied unfiltered dataset performed better than the unfiltered one for three evaluation metrics, likely because the larger datasets reinforced the biases. These results indicate that spatial filtering of occurrence localities may allow biogeographers to produce better models.
"],"dc:identifier":["https://academicworks.cuny.edu/cc_etds_theses/537"],"dc:subject":["Modeling","Niche","Ecology","Biology"],"dc:title":["Methodological advancements for improving performance and generating ensemble ecological niche models"],"thesis:degree_discipline":["Biology"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (M.S.)"]},"updated_at":"2026-07-24T01:56:59Z"}