Gurutzeta Guillera‐Arroita
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Recognitions
Gurutzeta Guillera‐Arroita has a total of 206 co-authors. Here are the top co-authors by number of shared publications:
- José Joaquín Lahoz‐Monfort
School of BioSciences The University of Melbourne Parkville Victoria Australia
26 shared publications - Jane Elith
School of Agriculture, Food, and Ecosystem Science, University of Melbourne Parkville Vic Australia
13 shared publications - Michael Andrew McCarthy
School of BioSciences University of Melbourne Parkville Victoria Australia
7 shared publications - Roozbeh Valavi
School of Ecosystem and Forest Sciences University of Melbourne Parkville Victoria Australia
6 shared publications - Brendan Anthony Wintle
University of Melbourne
5 shared publications - Damaris Zurell
Institute of Biochemistry and Biology, University of Potsdam, Potsdam, Germany
4 shared publications
Latest Publications
- Open Access
- 13 August 2026
- Published by Elsevier in Biological Conservation
- Vol. 322
Long-term detection data reveals widespread range contractions in Spanish herpetofauna
- 13 August 2026
- Published by Elsevier in Biological Conservation
- Vol. 322
Open AccessLong-term detection data reveals widespread range contractions in Spanish herpetofauna
- 6 February 2026
- Published by Springer Nature in Nature Reviews Biodiversity
- Vol. 2 (3) , 204-215
Biodiversity science and policy need more model intercomparisons
- 6 February 2026
- Published by Springer Nature in Nature Reviews Biodiversity
- Vol. 2 (3) , 204-215
Biodiversity science and policy need more model intercomparisons
- Open Access
- 21 November 2025
- Published by Elsevier in Forest Ecology and Management
- Vol. 601
Which bird species respond most to forest structural variation? Implications for biodiversity indicators in Mediterranean forests
- 21 November 2025
- Published by Elsevier in Forest Ecology and Management
- Vol. 601
Open AccessWhich bird species respond most to forest structural variation? Implications for biodiversity indicators in Mediterranean forests
- Open Access
- 8 October 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (41)
Predicting the way forward for the Global Biodiversity Framework
- 8 October 2025
- Published by National Academy of Sciences in Proceedings of the National Academy of Sciences
- Vol. 122 (41)
Open AccessPredicting the way forward for the Global Biodiversity Framework
- Open Access
Twenty years of dynamic occupancy models: a review of applications and look to the future
Since their introduction over 20 years ago, dynamic occupancy models (DOMs) have become a powerful and flexible framework for estimating species occupancy across space and time while accounting for imperfect detection. As their popularity has increased and extensions have further expanded their capabilities, DOMs have been applied to increasingly diverse datasets and research objectives in applied ecology. At the same time, technological advancements have resulted in massive increases in available data, offering both new opportunities and challenges for users of DOMs. Given these developments, it is timely to examine common practices in building these models to understand the breadth of modelling approaches, determine potential vulnerabilities, and identify priorities for future research. We reviewed a sample of articles that have fit DOMs in the past 20 years, examining the contexts of their application and the approaches taken to the model‐building process. We find that these models have been used to pursue diverse objectives, based on datasets with wide‐ranging spatial and temporal scales collected using a variety of survey methods. Our comparisons of modelling approaches indicate that many applications of DOMs considered relatively few covariates on key model parameters, as well as a tendency towards linear responses over more complex non‐linear or interactive forms. Model selection techniques were largely idiosyncratic with little consensus on the best approaches, and model evaluation was rare across reviewed applications. Based on these findings we highlight aspects of the modelling process that merit closer attention, such as the possible impacts of low complexity and missing drivers of heterogeneity on model performance, the uncertainties around robust and appropriate model selection techniques for different contexts, and the need for trusted and reliable tools for model assessment and evaluation.
Open AccessTwenty years of dynamic occupancy models: a review of applications and look to the future
Since their introduction over 20 years ago, dynamic occupancy models (DOMs) have become a powerful and flexible framework for estimating species occupancy across space and time while accounting for imperfect detection. As their popularity has increased and extensions have further expanded their capabilities, DOMs have been applied to increasingly diverse datasets and research objectives in applied ecology. At the same time, technological advancements have resulted in massive increases in available data, offering both new opportunities and challenges for users of DOMs. Given these developments, it is timely to examine common practices in building these models to understand the breadth of modelling approaches, determine potential vulnerabilities, and identify priorities for future research. We reviewed a sample of articles that have fit DOMs in the past 20 years, examining the contexts of their application and the approaches taken to the model‐building process. We find that these models have been used to pursue diverse objectives, based on datasets with wide‐ranging spatial and temporal scales collected using a variety of survey methods. Our comparisons of modelling approaches indicate that many applications of DOMs considered relatively few covariates on key model parameters, as well as a tendency towards linear responses over more complex non‐linear or interactive forms. Model selection techniques were largely idiosyncratic with little consensus on the best approaches, and model evaluation was rare across reviewed applications. Based on these findings we highlight aspects of the modelling process that merit closer attention, such as the possible impacts of low complexity and missing drivers of heterogeneity on model performance, the uncertainties around robust and appropriate model selection techniques for different contexts, and the need for trusted and reliable tools for model assessment and evaluation.
- Open Access
- 27 January 2023
- Published by Wiley in Global Ecology and Biogeography
- Vol. 32 (3) , 369-383
Flexible species distribution modelling methods perform well on spatially separated testing data
Aim: To assess whether flexible species distribution models that perform well at nearby testing locations still perform strongly when evaluated on spatially separated testing data.Location: Australian Wet Tropics (AWT), Ontario, Canada (CAN), north‐east New South Wales, Australia (NSW), New Zealand (NZ), five countries of South America (SA), and Switzerland (SWI).Time period: Most species data were collected between 1950 and 2000.Major taxa studied: Birds, mammals, plants and reptiles.Methods: We compared 10 species distribution modelling methods with varying flexibility in terms of the allowed complexity of their fitted functions [boosted regression trees (BRT), generalized additive model (GAM), multivariate adaptive regression splines (MARS), maximum entropy (MaxEnt), support vector machine (SVM), variants of generalized linear model (GLM) and random forest (RF), and an Ensemble model]. We used established practices for model selection to avoid overfitting, including parameter tuning in learning methods. Models were trained on presence–background data for 171 species and tested on presence–absence data. Training and testing data were separated using both random and spatial partitioning, the latter based on 75‐km blocks. We calculated the average performance and mean rank of the methods (focussing on the area under the receiver operating characteristic and precision‐recall gain curves, and correlation) and assessed the statistical significance of the differences between them.Results: The ranking of methods did not change when evaluated on spatially separated testing data. Methods with the strongest predictive performance were nonparametric methods known to be flexible. An ensemble formed by averaging predictions of five pre‐selected modelling methods was the best model in both random and spatial partitioning, followed by MaxEnt and a variant of random forest.Main conclusions: Whilst some modellers expect methods limited to simple smooth functions to predict better spatially separated data, we found no evidence of that using blocks of 75 km. We conclude that flexible models that are tuned well enough to avoid overfitting are effective at predicting to spatially distinct areas.
- 27 January 2023
- Published by Wiley in Global Ecology and Biogeography
- Vol. 32 (3) , 369-383
Open AccessFlexible species distribution modelling methods perform well on spatially separated testing data
Aim: To assess whether flexible species distribution models that perform well at nearby testing locations still perform strongly when evaluated on spatially separated testing data.Location: Australian Wet Tropics (AWT), Ontario, Canada (CAN), north‐east New South Wales, Australia (NSW), New Zealand (NZ), five countries of South America (SA), and Switzerland (SWI).Time period: Most species data were collected between 1950 and 2000.Major taxa studied: Birds, mammals, plants and reptiles.Methods: We compared 10 species distribution modelling methods with varying flexibility in terms of the allowed complexity of their fitted functions [boosted regression trees (BRT), generalized additive model (GAM), multivariate adaptive regression splines (MARS), maximum entropy (MaxEnt), support vector machine (SVM), variants of generalized linear model (GLM) and random forest (RF), and an Ensemble model]. We used established practices for model selection to avoid overfitting, including parameter tuning in learning methods. Models were trained on presence–background data for 171 species and tested on presence–absence data. Training and testing data were separated using both random and spatial partitioning, the latter based on 75‐km blocks. We calculated the average performance and mean rank of the methods (focussing on the area under the receiver operating characteristic and precision‐recall gain curves, and correlation) and assessed the statistical significance of the differences between them.Results: The ranking of methods did not change when evaluated on spatially separated testing data. Methods with the strongest predictive performance were nonparametric methods known to be flexible. An ensemble formed by averaging predictions of five pre‐selected modelling methods was the best model in both random and spatial partitioning, followed by MaxEnt and a variant of random forest.Main conclusions: Whilst some modellers expect methods limited to simple smooth functions to predict better spatially separated data, we found no evidence of that using blocks of 75 km. We conclude that flexible models that are tuned well enough to avoid overfitting are effective at predicting to spatially distinct areas.
- Open Access
The predictive performance of process‐explicit range change models remains largely untested
Ecological models used to forecast range change (range change models; RCM) have recently diversified to account for a greater number of ecological and observational processes in pursuit of more accurate and realistic predictions. Theory suggests that process‐explicit RCMs should generate more robust forecasts, particularly under novel environmental conditions. RCMs accounting for processes are generally more complex and data hungry, and so, require extra effort to build. Thus, it is necessary to understand when the effort of building a more realistic model is likely to generate more reliable forecasts. Here, we review the literature to explore whether process‐explicit models have been tested through benchmarking their temporal predictive performance (i.e. their predictive performance when transferred in time) and model transferability (i.e. their ability to keep their predictive performance when transferred to generate predictions into a different time) against simpler models, and highlight the gaps between the rapid development of process‐explicit RCMs and the testing of their potential improvements. We found that, out of five ecological processes (dispersal, demography, physiology, evolution, species interactions) and two observational processes (sampling bias, imperfect detection) that may influence reliability of forecasts, only the effects of dispersal, demography and imperfect detection have been benchmarked using temporally‐independent datasets. Only nine out of twenty‐nine process‐explicit model types have been tested to assess whether accounting for processes improves temporal predictive performance. We found no benchmarks assessing model transferability. We discuss potential reasons for the lack of empirical validation of process‐explicit models. Considering these findings, we propose an expanded research agenda to properly test the performance of process‐explicit RCMs, and highlight some opportunities to fill the gaps by suggesting models to be benchmarked using existing historical datasets.
Open AccessThe predictive performance of process‐explicit range change models remains largely untested
Ecological models used to forecast range change (range change models; RCM) have recently diversified to account for a greater number of ecological and observational processes in pursuit of more accurate and realistic predictions. Theory suggests that process‐explicit RCMs should generate more robust forecasts, particularly under novel environmental conditions. RCMs accounting for processes are generally more complex and data hungry, and so, require extra effort to build. Thus, it is necessary to understand when the effort of building a more realistic model is likely to generate more reliable forecasts. Here, we review the literature to explore whether process‐explicit models have been tested through benchmarking their temporal predictive performance (i.e. their predictive performance when transferred in time) and model transferability (i.e. their ability to keep their predictive performance when transferred to generate predictions into a different time) against simpler models, and highlight the gaps between the rapid development of process‐explicit RCMs and the testing of their potential improvements. We found that, out of five ecological processes (dispersal, demography, physiology, evolution, species interactions) and two observational processes (sampling bias, imperfect detection) that may influence reliability of forecasts, only the effects of dispersal, demography and imperfect detection have been benchmarked using temporally‐independent datasets. Only nine out of twenty‐nine process‐explicit model types have been tested to assess whether accounting for processes improves temporal predictive performance. We found no benchmarks assessing model transferability. We discuss potential reasons for the lack of empirical validation of process‐explicit models. Considering these findings, we propose an expanded research agenda to properly test the performance of process‐explicit RCMs, and highlight some opportunities to fill the gaps by suggesting models to be benchmarked using existing historical datasets.
- Top Cited PapersOpen Access
Modelling species presence‐only data with random forests
The random forest (RF) algorithm is an ensemble of classification or regression trees and is widely used, including for species distribution modelling (SDM). Many researchers use implementations of RF in the R programming language with default parameters to analyse species presence‐only data together with ‘background' samples. However, there is good evidence that RF with default parameters does not perform well for such ‘presence‐background' modelling. This is often attributed to the disparity between the number of presence and background samples, also known as 'class imbalance', and several solutions have been proposed. Here, we first set the context: the background sample should be large enough to represent all environments in the region. We then aim to understand the drivers of poor performance of RF when models are fitted to presence‐only species data alongside background samples. We show that 'class overlap' (where both classes occur in the same environment) is an important driver of poor performance, alongside class imbalance. Class overlap can even degrade performance for presence–absence data. We explain, test and evaluate suggested solutions. Using simulated and real presence‐background data, we compare performance of default RF with other weighting and sampling approaches. Our results demonstrate clear evidence of improvement in the performance of RFs when techniques that explicitly manage imbalance are used. We show that these either limit or enforce tree depth. Without compromising the environmental representativeness of the sampled background, we identify approaches to fitting RF that ameliorate the effects of imbalance and overlap and allow excellent predictive performance. Understanding the problems of RF in presence‐background modelling allows new insights into how best to fit models, and should guide future efforts to best deal with such data.
Top Cited PapersOpen AccessModelling species presence‐only data with random forests
The random forest (RF) algorithm is an ensemble of classification or regression trees and is widely used, including for species distribution modelling (SDM). Many researchers use implementations of RF in the R programming language with default parameters to analyse species presence‐only data together with ‘background' samples. However, there is good evidence that RF with default parameters does not perform well for such ‘presence‐background' modelling. This is often attributed to the disparity between the number of presence and background samples, also known as 'class imbalance', and several solutions have been proposed. Here, we first set the context: the background sample should be large enough to represent all environments in the region. We then aim to understand the drivers of poor performance of RF when models are fitted to presence‐only species data alongside background samples. We show that 'class overlap' (where both classes occur in the same environment) is an important driver of poor performance, alongside class imbalance. Class overlap can even degrade performance for presence–absence data. We explain, test and evaluate suggested solutions. Using simulated and real presence‐background data, we compare performance of default RF with other weighting and sampling approaches. Our results demonstrate clear evidence of improvement in the performance of RFs when techniques that explicitly manage imbalance are used. We show that these either limit or enforce tree depth. Without compromising the environmental representativeness of the sampled background, we identify approaches to fitting RF that ameliorate the effects of imbalance and overlap and allow excellent predictive performance. Understanding the problems of RF in presence‐background modelling allows new insights into how best to fit models, and should guide future efforts to best deal with such data.
- Top Cited PapersOpen Access
- 6 October 2021
- Published by Wiley in Ecological Monographs
- Vol. 92 (1) , e1486
Predictive performance of presence‐only species distribution models: a benchmark study with reproducible code
- 6 October 2021
- Published by Wiley in Ecological Monographs
- Vol. 92 (1) , e1486
Top Cited PapersOpen AccessPredictive performance of presence‐only species distribution models: a benchmark study with reproducible code