When Good Fit Goes Bad: Identifying and Minimising Overfitting in Ecological Niche Models

To synthesise current understanding of overfitting as a pervasive and often underdiagnosed problem in correlative ecological niche models (ENMs), and to assess its consequences for model interpretation, generalisation and transferability under contemporary data and methodological practices.

• Publication year

  2026

• Venue

  Journal of Biogeography

• Publication date

  2026-02-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1111/jbi.70165
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An earth observation and explainable machine learning approach for determining the drivers of invasive species — a water hyacinth case study

  2025cited by this paper
• An improved SMOTE algorithm for enhanced imbalanced data classification by expanding sample generation space

  2025cited by this paper
• Cross-realm transferability of species distribution models–Species characteristics and prevalence matter more than modelling methods applied

  2025cited by this paper
• Spatially nested species distribution models (N‐SDM): An effective tool to overcome niche truncation for more robust inference and projections

  2025cited by this paper
• Foundation for unbiased cross-validation of spatio-temporal models for species distribution modeling

  2025influential reference
• GNN ‐ SDM : A Graph Neural Network‐Based Framework Integrating Complex Landscape Patterns Into Species Distribution Modelling

  2025cited by this paper
• Machine learning applied to global scale species distribution models

  2025cited by this paper
• Cross‐validation matters in species distribution models: a case study with goatfish species

  2024cited by this paper
• Predicting the expansion of invasive species: how much data do we need?

  2024cited by this paper
• Optimising occurrence data in species distribution models: sample size, positional uncertainty, and sampling bias matter

  2024cited by this paper
• High-resolution species distribution modelling reveals spatio-temporal variability of habitat suitability in a declining grassland bird

  2024cited by this paper
• Top ten hazards to avoid when modeling species distributions: a didactic guide of assumptions, problems, and recommendations

  2024cited by this paper
• The influence of the number and distribution of background points in presence-background species distribution models

  2024cited by this paper
• Effective strategies for correcting spatial sampling bias in species distribution models without independent test data

  2024influential reference
• tidysdm: leveraging the flexibility of tidymodels for Species Distribution Modelling in R

  2024cited by this paper
• Challenges in data-driven geospatial modeling for environmental research and practice

  2024cited by this paper
• Spatially explicit metrics improve the evaluation of species distribution models facing sampling biases

  2024cited by this paper
• Achieving higher standards in species distribution modeling by leveraging the diversity of available software

  2024cited by this paper
• Deconstructing the geography of human impacts on species’ natural distribution

  2024cited by this paper
• Detailed multivariate comparisons of environments with mobility oriented parity

  2024cited by this paper
• A comparison of machine learning and statistical species distribution models: Quantifying overfitting supports model interpretation

  2023influential reference
• Microclimate species distribution models estimate lower levels of climate-related habitat loss for salamanders

  2023cited by this paper
• An ensemble approach to species distribution modelling reconciles systematic differences in estimates of habitat utilization and range area

  2023cited by this paper
• How far can I extrapolate my species distribution model? Exploring shape, a novel method

  2023cited by this paper
• Integrating disparate survey data in species distribution models demonstrate the need for robust model evaluation

  2023cited by this paper
• spatialMaxent: Adapting species distribution modeling to spatial data

  2023cited by this paper
• A theoretical framework for upscaling species distribution models

  2023cited by this paper
• A quixotic view of spatial bias in modelling the distribution of species and their diversity

  2023cited by this paper
• Uncertainty of spatial averages and totals of natural resource maps

  2023cited by this paper
• Flexible species distribution modelling methods perform well on spatially separated testing data

  2023cited by this paper
• Effects of input data sources on species distribution model predictions across species with different distributional ranges

  2022cited by this paper
• Comparison between optimized MaxEnt and random forest modeling in predicting potential distribution: A case study with Quasipaa boulengeri in China.

  2022cited by this paper
• To be or not to be: the role of absences in niche modelling for highly mobile species in dynamic marine environments

  2022cited by this paper
• Aligning artificial intelligence with climate change mitigation

  2022cited by this paper
• Predictive models aren't for causal inference.

  2022cited by this paper
• flexsdm: An r package for supporting a comprehensive and flexible species distribution modelling workflow

  2022cited by this paper
• Deep Species Distribution Modeling From Sentinel-2 Image Time-Series: A Global Scale Analysis on the Orchid Family

  2022cited by this paper
• Convolutional neural networks improve species distribution modelling by capturing the spatial structure of the environment

  2021cited by this paper
• Potential distributions of invasive vertebrates in the Iberian Peninsula under projected changes in climate extreme events

  2021cited by this paper
• Spatial cross-validation is not the right way to evaluate map accuracy

  2021influential reference
• Target‐group backgrounds prove effective at correcting sampling bias in Maxent models

  2021cited by this paper
• Want to model a species niche? A step-by-step guideline on correlative ecological niche modelling

  2021cited by this paper
• ENMeval 2.0: Redesigned for customizable and reproducible modeling of species’ niches and distributions

  2021cited by this paper
• An interpretable machine learning method for supporting ecosystem management: Application to species distribution models of freshwater macroinvertebrates.

  2021cited by this paper
• Testing whether ensemble modelling is advantageous for maximising predictive performance of species distribution models

  2020cited by this paper
• A standard protocol for reporting species distribution models

  2020cited by this paper
• A translucent box: interpretable machine learning in ecology

  2020cited by this paper
• Comparing multi- and single-scale species distribution and abundance models built with the boosted regression tree algorithm

  2020cited by this paper
• Sampling biases shape our view of the natural world

  2020cited by this paper
• Explainable artificial intelligence enhances the ecological interpretability of black‐box species distribution models

  2020cited by this paper
• Balancing transferability and complexity of species distribution models for rare species conservation

  2020cited by this paper
• Common mistakes in ecological niche models

  2020cited by this paper
• A comparison between Ensemble and MaxEnt species distribution modelling approaches for conservation: A case study with Egyptian medicinal plants

  2020cited by this paper
• Deep learning and process understanding for data-driven Earth system science

  2019cited by this paper
• Standards for distribution models in biodiversity assessments

  2019cited by this paper
• Ensemble modeling of the potential distribution of the whale shark in the Atlantic Ocean

  2019cited by this paper
• The MIAmaxent R package: Variable transformation and model selection for species distribution models

  2019cited by this paper
• The spread of the red-billed leiothrix (Leiothrix lutea) in Europe: The conquest by an overlooked invader?

  2019cited by this paper
• embarcadero: Species distribution modelling with Bayesian additive regression trees in R

  2019cited by this paper
• Species' range model metadata standards: RMMS

  2019cited by this paper
• Species distribution models can be highly sensitive to algorithm configuration

  2019cited by this paper
• Bunching up the background betters bias in species distribution models

  2019cited by this paper
• Broad-scale species distribution models applied to data-poor areas

  2019cited by this paper
• iml: An R package for Interpretable Machine Learning

  2018cited by this paper
• blockCV: an R package for generating spatially or environmentally separated folds for k-fold cross-validation of species distribution models

  2018influential reference
• Applications for deep learning in ecology

  2018cited by this paper
• Background sampling and transferability of species distribution model ensembles under climate change

  2018cited by this paper
• An evaluation of transferability of ecological niche models

  2018cited by this paper
• Major challenges for correlational ecological niche model projections to future climate conditions

  2018cited by this paper
• Improved species‐occurrence predictions in data‐poor regions: using large‐scale data and bias correction with down‐weighted Poisson regression and Maxent

  2018cited by this paper
• Effects of grain size and niche breadth on species distribution modeling

  2018influential reference
• Outstanding Challenges in the Transferability of Ecological Models.

  2018cited by this paper
• Hypervolume concepts in niche‐ and trait‐based ecology

  2018cited by this paper
• Opening the black box: an open-source release of Maxent

  2017cited by this paper
• Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure

  2017cited by this paper
• Estimating the prediction performance of spatial models via spatial k-fold cross validation

  2017influential reference
• pdp: An R Package for Constructing Partial Dependence Plots

  2017cited by this paper
• A practical overview of transferability in species distribution modeling

  2017cited by this paper
• Shifts in habitat suitability and the conservation status of the Endangered Andean cat Leopardus jacobita under climate change scenarios

  2017cited by this paper
• WorldClim 2: new 1‐km spatial resolution climate surfaces for global land areas

  2017cited by this paper
• XGBoost: A Scalable Tree Boosting System

  2016cited by this paper
• Principal component analysis: a review and recent developments

  2016cited by this paper
• Drones for butterfly conservation: larval habitat assessment with an unmanned aerial vehicle

  2016cited by this paper
• Sixteen years of change in the global terrestrial human footprint and implications for biodiversity conservation

  2016cited by this paper
• sdm: a reproducible and extensible R platform for species distribution modelling

  2016influential reference
• Climatologies at high resolution for the earth’s land surface areas

  2016cited by this paper
• Deep Learning

  2016cited by this paper
• Statistics For Spatial Data

  2016cited by this paper
• Minimum required number of specimen records to develop accurate species distribution models

  2016cited by this paper
• Consensus Forecasting of Species Distributions: The Effects of Niche Model Performance and Niche Properties

  2015cited by this paper
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

  2015cited by this paper
• fuzzySim: applying fuzzy logic to binary similarity indices in ecology

  2015cited by this paper
• spThin: an R package for spatial thinning of species occurrence records for use in ecological niche models

  2015cited by this paper
• Characteristics of the top-cited papers in species distribution predictive models

  2015cited by this paper
• Environmental filters reduce the effects of sampling bias and improve predictions of ecological niche models

  2014cited by this paper
• Incorporating model complexity and spatial sampling bias into ecological niche models of climate change risks faced by 90 California vertebrate species of concern

  2014cited by this paper
• Here be dragons: a tool for quantifying novelty due to covariate range and correlation change when projecting species distribution models

  2014cited by this paper
• bioclim: the first species distribution modelling package, its early applications and relevance to most current MaxEnt studies

  2014cited by this paper
• Imperfect detection impacts the performance of species distribution models

  2014cited by this paper
• Bias correction in species distribution models: pooling survey and collection data for multiple species

  2014cited by this paper

• No citing papers are available for this paper.