108 research outputs found
A review of evidence about use and performance of species distribution modelling ensembles like BIOMOD
No full textAim:
The idea of combining predictions from different models into an ensemble has gained considerable popularity in species distribution modelling, partly due to free and comprehensive software such as the R package BIOMOD. However, despite proliferation of ensemble models, we lack oversight of how and where they are used for modelling distributions, and how well they perform. Here, we present such an overview.Location:
Global.Methods:
Since BIOMOD is freely available and widely used by ensemble species distribution modellers, we focused on articles that apply BIOMOD, filtering the initial 852 papers identified in our structured literature search to a relevant final subset of 224 eligible peer-reviewed journal articles.Results:
BIOMOD-based ensembles are used across many taxa and locations, with terrestrial plants being the most represented group of species (n = 72) and Europe being the most represented continent (n = 106). These studies often focus on forecasting distributions in the future (n = 109), and commonly use presence-only species data (n = 139) and climatic environmental predictors (n = 219). An average of six models are used in ensembles, and approximately half of ensembles weight contributions of models by their cross-validation performance. However, discussion about choices made in the modelling process and unambiguous information on the performance of ensemble models versus individual models are limited. The use of independent data to validate model performance is particularly uncommon.Main conclusions:
We document the breadth of ensemble applications, but could not draw strong quantitative conclusions about the predictive performance of ensemble models, due to lack of unambiguous information reported. Understanding how and where ensembles are best used when modelling species distributions is important for enabling best choices for different applications. To enable this objective to be achieved, we provide recommendations for thorough reporting practices in a BIOMOD-based ensemble workflow.The authors were supported by a Discovery Project grant to José J. Lahoz-Monfort and Jane Elith (DP160101003), and a Discovery Early Career Research Award to Gurutzeta Guillera-Arroita (DE160100904), both from the Australian Research Council.Peer reviewe
Running head: Modelling presence-only records with MARS
No full textCitation. Elith, J., and J. R. Leathwick. In press. Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression splines. Diversity and Distributions. Title: Predicting species distributions from museum and herbarium records using multiresponse models fitted with multivariate adaptive regression spline
SDM_NCEAS
No full textThese are data described in this publication: Elith, J., Graham, C.H., Valavi, R., Abegg, M., Bruce, C., Ferrier, S., Ford, A., Guisan, A., Hijmans, R.J., Huettmann, F., Lohmann, L.G., Loiselle, B.A., Moritz, C., Overton, J.McC., Peterson, A.T., Phillips, S., Richardson, K., Williams, S., Wiser, S.K., Wohlgemuth, T., Zimmermann, N.E. (2020). Presence-only and presence-absence data for comparing species distribution modeling methods. Biodiversity Informatics 15:69-8
Testing whether ensemble modelling is advantageous for maximising predictive performance of species distribution models
No full textPredictive performance is important to many applications of species distribution models (SDMs). The SDM ‘ensemble’ approach, which combines predictions across different modelling methods, is believed to improve predictive performance, and is used in many recent SDM studies. Here, we aim to compare the predictive performance of ensemble species distribution models to that of individual models, using a large presence–absence dataset of eucalypt tree species. To test model performance, we divided our dataset into calibration and evaluation folds using two spatial blocking strategies (checkerboard‐pattern and latitudinal slicing). We calibrated and cross‐validated all models within the calibration folds, using both repeated random division of data (a common approach) and spatial blocking. Ensembles were built using the software package ‘biomod2’, with standard (‘untuned’) settings. Boosted regression tree (BRT) models were also fitted to the same data, tuned according to published procedures. We then used evaluation folds to compare ensembles against both their component untuned individual models, and against the BRTs. We used area under the receiver‐operating characteristic curve (AUC) and log‐likelihood for assessing model performance. In all our tests, ensemble models performed well, but not consistently better than their component untuned individual models or tuned BRTs across all tests. Moreover, choosing untuned individual models with best cross‐validation performance also yielded good external performance, with blocked cross‐validation proving better suited for this choice, in this study, than repeated random cross‐validation. The latitudinal slice test was only possible for four species; this showed some individual models, and particularly the tuned one, performing better than ensembles. This study shows no particular benefit to using ensembles over individual tuned models. It also suggests that further robust testing of performance is required for situations where models are used to predict to distant places or environments
Predicted Pleistocene–Holocene range shifts of the tiger (Panthera tigris)
No full textAim
In this article, we modelled the potential range shifts of tiger (Panthera tigris) populations over the Late Pleistocene and Holocene, to provide new insights into the evolutionary history and interconnectivity between populations of this endangered species.
Location
Asia.
Methods
We used an ecological niche approach and applied a maximum entropy (Maxent) framework to model potential distributions of tigers. Bioclimatic conditions for the present day and mid-Holocene, and for the Last Glacial Maximum (LGM), were used to represent interglacial and glacial conditions of the Late Pleistocene, respectively.
Results
Our results show that the maximum potential tiger range during modern climates (without human impacts) would be continuous from the Indian subcontinent to north-east Siberia. During the LGM, distributions are predicted to have contracted to southern China, India and Southeast Asia and remained largely contiguous. A potential distribution gap between Peninsular Malaya and Sumatra could have effectively separated tigers on the Sunda Islands from those in continental Asia during interglacials.
Main conclusions
The continuous modelled distribution of tigers in mainland Asia supports the idea of mainly unimpeded gene flow between all populations throughout the Late Pleistocene and Holocene. Thus, our data support a pragmatic approach to tiger conservation management, especially of mainland populations, as it is likely that only recent anthropogenic changes caused separation of these populations. In contrast, Sunda tigers are likely to have separated and differentiated following the Last Glacial Maximum and thus warrant separate management
‐fold cross‐validation of species distribution models
No full text[EN]When applied to structured data, conventional random cross-validation techniques can lead to underestimation of prediction error, and may result in inappropriate model selection. We present the r package blockCV, a new toolbox for cross-validation of species distribution modelling. Although it has been developed with species distribution modelling in mind, it can be used for any spatial modelling. The package can generate spatially or environmentally separated folds. It includes tools to measure spatial autocorrelation ranges in candidate covariates, providing the user with insights into the spatial structure in these data. It also offers interactive graphical capabilities for creating spatial blocks and exploring data folds. Package blockCV enables modellers to more easily implement a range of evaluation approaches. It will help the modelling community learn more about the impacts of evaluation approaches on our understanding of predictive performance of species distribution models.[AR]هنگامی که روش اعتبارسنجی متقاطع بر روی دادههای دارای ساختار (مکانی٬ محیطی …) اعمال میشود٬ میتواند منجر به تخمین نادرست خطای پیشبینی و در نتیجه اشتباه در انتخاب مدلها شود.در اینجا کتابخانه blockCV در نرمافزار برنامهنویسی R را بعنوان یک ابزار جدید برای اعتبارسنجی متقاطع مدلهای توزیع گونهها ارائه میدهیم. گرچه این کتابخانه با ایدهی مدلسازی توزیع گونهها توسعه داده شده است اما میتواند برای انواع مدلسازیهای مکانی نیز مورد استفاده قرار گیرد.این کتابخانه توانایی ساخت زیرمجموعههای مجزای مکانی و محیطی از دادهها را دارد و همچنین شامل ابزاری برای اندازهگیری دامنه تاثیر خودهمبستگی مکانی در متغیرهای پیشبینیکننده میباشد که به کاربر دیدگاه بهتری از ساختار مکانی این دادهها را میدهد. این کتابخانه دارای ابزارهای گرافیکی برای بررسی و ساخت بلاکهای مکانی نیز میباشد.کتابخانه blockCV مدلسازان را قادر میسازد که دامنه وسیعتری از روشهای اعتبارسنجی را بکار گیرند و همچنین درباره تاثیرات روشهای مختلف اعتبارسنجی بر درک بهتر ما از قدرت پیشبینی مدلهای توزیع گونهها کمک میکند.R.V. is supported by an Australian Government Research Training Program Scholarship and a Rowden White Scholarship; G.G.-A. by an Australian Research Council (ARC) Discovery Early Career Researcher Award (DE160100904), and J.J.L.-M. and J.E. by ARC Discovery Project 160101003. J.E. appreciates the support of the ARC's Centre of Excellence for Environmental Decisions (CE11001000104). We also thank Babak Mirbagheri, Nick Golding, and reviewers and editors: Robert Anderson, David Roberts, an anonymous reviewer and Associate Editor, for their helpful suggestions and advice.Peer reviewe
Evaluating 318 continental-scale species distribution models over a 60-year prediction horizon: what factors influence the reliability of predictions?
No full textAim:
Species distribution models (SDMs) are currently the most widely used tools in ecology for evaluating the suitability of environments for biodiversity in the face of future environmental change. In this study we seek to provide an assessment of the predictive performance of SDMs over time. How well do SDMs predict for future time periods and what factors influence predictive performance?Innovation:
We used a historical spatially explicit database of 1.8 million occurrence records for 318 tetrapod species from across continental Australia over the period 1950–2013. We fitted distribution models for each species to data from four multi-decadal time slices and used these to predict the species distributions up to 60 years after the data collection period for the fitted models. We evaluated predictions against observed data from the relevant time period. Predictions were made assuming either complete knowledge of changes in climatic and environmental conditions or assuming the environment and climate remained unchanged between the fitting and evaluation time periods. We used generalized linear mixed models to model variation in the predictive performance of SDMs over time in relation to a variety of factors, including the length of time between fitting and evaluation, species traits, taxonomic group and attributes of the dataset used to fit models.Main conclusions:
We found that most models provided useful predictions even when the period between model fitting and evaluation was 60 years (area under the receiver operator characteristic curve > 0.7 in 80% of the species evaluated). Variation in predictive performance over time was strongly related to the species range breadth (models for species with broad geographical ranges tended to perform worse than models for locally restricted species) and to the environmental coverage of occupancy data. Conversely, taxonomic group, habitat preferences and body size were not highly influential in describing the variation in predictive performance over time.Data custodians: Department of Land Resource Management of Northern Territory; Department of Environment and Primary Industries of Victoria; New South Wales office of Environment and Heritage; Department of Environment and Land Conservation of Western Australia, and the Department of Environment and Heritage protection of Queensland. G. Guillera-Arroita, M. McCarthy, M. Kearney, M. Bode, R. Fuller, G. Luck, G. Heard, A. Whitehead, R. Tingley, contributed discussion, ideas and data. This work was supported by the ARC Centre of Excellence for Environmental Decisions (CEED) and the National Environment Research Program Environmental Decisions Hub (NERP ED). B.W. and J.E. were supported by ARC Future Fellowships (FT100100819, FT0991640).Peer reviewe
Predicting the distribution of plants
No full textTypescript (photocopy)Thesis (PhD) -- University of Melbourne, Faculty of Science, 2002Includes bibliographical references (leaves 271-304)CD-ROM content not included in digitised versionThis thesis investigates methods for building spatially explicit, static models of distribution for individual plant species, with particular emphasis on issues that are important when the predictions are used in a land management and conservation framework. It focusses on modelling with presence-absence species data combined with environmental information.
Several methods are reviewed and five applied to existing government data from the Central Highlands region of Victoria, Australia. These data were not specifically collected for modelling. Within the spectrum of the types of data usually available for conservation planning in Australia, they represent one of the more complete sets of data. The models are developed with protocols that could be used in a management setting. The predictions are assessed in several ways, including a comparison with independent field observations. These indicate that:
� some species are well modelled, but there are no characteristics of species or their data sets which can be used as a guide to the likely success of modelling,
� the difference between modelling methods is generally small, although there is some evidence that predictions from the regression methods (generalized linear models and generalized additive models) performed better, and
� the model evaluation scale and data sets affect the outcome of the evaluation.
This modelling prompted examination of several issues. The first, variable selection, is important because there are often many more variables available for modelling than can be justified in a model. Selection algorithms commonly employed in regression modelling are hard to defend statistically and prone to error. It is recommended that variable sets are constructed, using expert knowledge, and that no selection algorithms are applied.
These recommendations are implemented in the second case study. In this, existing records for two rare woody shrubs of rocky outcrops near Eden, New South Wales, are supplemented with data collected by the author. For modelling, attention is given to developing environmental variables that capture ecologically relevant patterns in the landscape. The final logistic regression models are sensible summaries of the data, have good discrimination, and will act as a useful guide to future field work.
This thesis also examines issues associated with uncertainty in modelled maps of species distribution. Uncertainty can arise from many sources including measurement error, systematic error, natural variation, model uncertainty, subjective judgement and vagueness. The chapter on uncertainty focusses on examples of these, and proposes methods for classifying and quantifying the uncertainty. The emphasis is on developing a framework that will enable prediction uncertainty to be traced back to its various sources, quantified, and communicated to decision-makers.
The final topic is how to evaluate modelled predictions. Once the ecological concepts of the model are assessed, the evaluation problem has two main elements: the construction of evaluation data sets, and the selection of relevant test statistics. The chapter includes guidelines and recommendations for constructing and selecting these, and includes an assessment of their performance on simulated data. Consistent with the rest of the thesis, the emphasis is on recommending approaches that will inform the conservation planners
- …
