Eliciting and encoding expert knowledge on variable selection into classical or Bayesian species distribution models

The quality of species distribution models (SDMs) relies to a large degree on the quality of the input data, from bioclimatic indices to environmental and habitat descriptors (Austin, 2002). Recent reviews of SDM techniques, have sought to optimize predictive performance e.g. Elith et al., 2006. In general SDMs employ one of three approaches to variable selection. The simplest approach relies on the expert to select the variables, as in environmental niche models Nix, 1986 or a generalized linear model without variable selection (Miller and Franklin, 2002). A second approach explicitly incorporates variable selection into model fitting, which allows examination of particular combinations of variables. Examples include generalized linear or additive models with variable selection (Hastie et al. 2002); or classification trees with complexity or model based pruning (Breiman et al., 1984, Zeileis, 2008). A third approach uses model averaging, to summarize the overall contribution of a variable, without considering particular combinations. Examples include neural networks, boosted or bagged regression trees and Maximum Entropy as compared in Elith et al. 2006. Typically, users of SDMs will either consider a small number of variable sets, via the first approach, or else supply all of the candidate variables (often numbering more than a hundred) to the second or third approaches. Bayesian SDMs exist, with several methods for eliciting and encoding priors on model parameters (see review in Low Choy et al. 2010). However few methods have been published for informative variable selection; one example is Bayesian trees (O’Leary 2008). Here we report an elicitation protocol that helps makes explicit a priori expert judgements on the quality of candidate variables. This protocol can be flexibly applied to any of the three approaches to variable selection, described above, Bayesian or otherwise. We demonstrate how this information can be obtained then used to guide variable selection in classical or machine learning SDMs, or to define priors within Bayesian SDMs.

Behavioural context of multi-scale species distribution models assessed by radio-tracking

Incorporating ecological processes and animal behaviour into Species Distribution Models (SDMs) is difficult. In species with a central resting or breeding place, there can be conflict between the environmental requirements of the 'central place' and foraging habitat. We apply a multi-scale SDM to examine habitat trade-offs between the central place, roost sites, and foraging habitat in . Myotis nattereri. We validate these derived associations using habitat selection from behavioural observations of radio-tracked bats. A Generalised Linear Model (GLM) of roost occurrence using land cover variables with mixed spatial scales indicated roost occurrence was positively associated with woodland on a fine scale and pasture on a broad scale. Habitat selection of radio-tracked bats mirrored the SDM with bats selecting for woodland in the immediate vicinity of individual roosts but avoiding this habitat in foraging areas, whilst pasture was significantly positively selected for in foraging areas. Using habitat selection derived from radio-tracking enables a multi-scale SDM to be interpreted in a behavioural context. We suggest that the multi-scale SDM of . M. nattereri describes a trade-off between the central place and foraging habitat. Multi-scale methods provide a greater understanding of the ecological processes which determine where species occur and allow integration of behavioural processes into SDMs. The findings have implications when assessing the resource use of a species at a single point in time. Doing so could lead to misinterpretation of habitat requirements as these can change within a short time period depending on specific behaviour, particularly if detectability changes depending on behaviour. © 2011 Gesellschaft für ökologie.

Species distribution models reveal apparent competitive and facilitative effects of a dominant species on the distribution of tundra plants

Abiotic factors are considered strong drivers of species distribution and assemblages. Yet these spatial patterns are also influenced by biotic interactions. Accounting for competitors or facilitators may improve both the fit and the predictive power of species distribution models (SDMs). We investigated the influence of a dominant species, Empetrum nigrum ssp. hermaphroditum, on the distribution of 34 subordinate species in the tundra of northern Norway. We related SDM parameters of those subordinate species to their functional traits and their co-occurrence patterns with E. hermaphroditum across three spatial scales. By combining both approaches, we sought to understand whether these species may be limited by competitive interactions and/or benefit from habitat conditions created by the dominant species. The model fit and predictive power increased for most species when the frequency of occurrence of E. hermaphroditum was included in the SDMs as a predictor. The largest increase was found for species that 1) co-occur most of the time with E. hermaphroditum, both at large (i.e. 750 m) and small spatial scale (i.e. 2 m) or co-occur with E. hermaphroditum at large scale but not at small scale and 2) have particularly low or high leaf dry matter content (LDMC). Species that do not co-occur with E. hermaphroditum at the smallest scale are generally palatable herbaceous species with low LDMC, thus showing a weak ability to tolerate resource depletion that is directly or indirectly induced by E. hermaphroditum. Species with high LDMC, showing a better aptitude to face resource depletion and grazing, are often found in the proximity of E. hermaphroditum. Our results are consistent with previous findings that both competition and facilitation structure plant distribution and assemblages in the Arctic tundra. The functional and co-occurrence approaches used were complementary and provided a deeper understanding of the observed patterns by refinement of the pool of potential direct and indirect ecological effects of E. hermaphroditum on the distribution of subordinate species. Our correlative study would benefit being complemented by experimental approaches.

Species distribution models for crop pollination: a modelling framework applied to Great Britain

Insect pollination benefits over three quarters of the world's major crops. There is growing concern that observed declines in pollinators may impact on production and revenues from animal pollinated crops. Knowing the distribution of pollinators is therefore crucial for estimating their availability to pollinate crops; however, in general, we have an incomplete knowledge of where these pollinators occur. We propose a method to predict geographical patterns of pollination service to crops, novel in two elements: the use of pollinator records rather than expert knowledge to predict pollinator occurrence, and the inclusion of the managed pollinator supply. We integrated a maximum entropy species distribution model (SDM) with an existing pollination service model (PSM) to derive the availability of pollinators for crop pollination. We used nation-wide records of wild and managed pollinators (honey bees) as well as agricultural data from Great Britain. We first calibrated the SDM on a representative sample of bee and hoverfly crop pollinator species, evaluating the effects of different settings on model performance and on its capacity to identify the most important predictors. The importance of the different predictors was better resolved by SDM derived from simpler functions, with consistent results for bees and hoverflies. We then used the species distributions from the calibrated model to predict pollination service of wild and managed pollinators, using field beans as a test case. The PSM allowed us to spatially characterize the contribution of wild and managed pollinators and also identify areas potentially vulnerable to low pollination service provision, which can help direct local scale interventions. This approach can be extended to investigate geographical mismatches between crop pollination demand and the availability of pollinators, resulting from environmental change or policy scenarios.

Climate refugia: joint inference from fossil records, species distribution models and phylogeography

Climate refugia, locations where taxa survive periods of regionally adverse climate, are thought to be critical for maintaining biodiversity through the glacial–interglacial climate changes of the Quaternary. A critical research need is to better integrate and reconcile the three major lines of evidence used to infer the existence of past refugia – fossil records, species distribution models and phylogeographic surveys – in order to characterize the complex spatiotemporal trajectories of species and populations in and out of refugia. Here we review the complementary strengths, limitations and new advances for these three approaches. We provide case studies to illustrate their combined application, and point the way towards new opportunities for synthesizing these disparate lines of evidence. Case studies with European beech, Qinghai spruce and Douglas-fir illustrate how the combination of these three approaches successfully resolves complex species histories not attainable from any one approach. Promising new statistical techniques can capitalize on the strengths of each method and provide a robust quantitative reconstruction of species history. Studying past refugia can help identify contemporary refugia and clarify their conservation significance, in particular by elucidating the fine-scale processes and the particular geographic locations that buffer species against rapidly changing climate.

Three species distribution models for the marine diatom Fragilariopsis kerguelensis of the Southern Ocean, links to NetCDF files

Fragilariopsis kerguelensis, a dominant diatom species throughout the Antarctic Circumpolar Current, is coined to be one of the main drivers of the biological silicate pump. Here, we study the distribution of this important species and expected consequences of climate change upon it, using correlative species distribution modeling and publicly available presence-only data. As experience with SDM is scarce for marine phytoplankton, this also serves as a pilot study for this organism group. We used the maximum entropy method to calculate distribution models for the diatom F. kerguelensis based on yearly and monthly environmental data (sea surface temperature, salinity, nitrate and silicate concentrations). Observation data were harvested from GBIF and the Global Diatom Database, and for further analyses also from the Hustedt Diatom Collection (BRM). The models were projected on current yearly and seasonal environmental data to study current distribution and its seasonality. Furthermore, we projected the seasonal model on future environmental data obtained from climate models for the year 2100. Projected on current yearly averaged environmental data, all models showed similar distribution patterns for F. kerguelensis. The monthly model showed seasonality, for example, a shift of the southern distribution boundary toward the north in the winter. Projections on future scenarios resulted in a moderately to negligibly shrinking distribution area and a change in seasonality. We found a substantial bias in the publicly available observation datasets, which could be reduced by additional observation records we obtained from the Hustedt Diatom Collection. Present-day distribution patterns inferred from the models coincided well with background knowledge and previous reports about F. kerguelensis distribution, showing that maximum entropy-based distribution models are suitable to map distribution patterns for oceanic planktonic organisms. Our scenario projections indicate moderate effects of climate change upon the biogeography of F. kerguelensis.

Using individual tracking data to validate the predictions of species distribution models

The authors would like to thank the College of Life Sciences of Aberdeen University and Marine Scotland Science which funded CP's PhD project. Skate tagging experiments were undertaken as part of Scottish Government project SP004. We thank Ian Burrett for help in catching the fish and the other fishermen and anglers who returned tags. We thank José Manuel Gonzalez-Irusta for extracting and making available the environmental layers used as environmental covariates in the environmental suitability modelling procedure. We also thank Jason Matthiopoulos for insightful suggestions on habitat utilization metrics as well as Stephen C.F. Palmer, and three anonymous reviewers for useful suggestions to improve the clarity and quality of the manuscript.

Data to Decision in a Dynamic Ocean: Robust Species Distribution Models and Spatial Decision Frameworks

Human use of the oceans is increasingly in conflict with conservation of endangered species. Methods for managing the spatial and temporal placement of industries such as military, fishing, transportation and offshore energy, have historically been post hoc; i.e. the time and place of human activity is often already determined before assessment of environmental impacts. In this dissertation, I build robust species distribution models in two case study areas, US Atlantic (Best et al. 2012) and British Columbia (Best et al. 2015), predicting presence and abundance respectively, from scientific surveys. These models are then applied to novel decision frameworks for preemptively suggesting optimal placement of human activities in space and time to minimize ecological impacts: siting for offshore wind energy development, and routing ships to minimize risk of striking whales. Both decision frameworks relate the tradeoff between conservation risk and industry profit with synchronized variable and map views as online spatial decision support systems.

For siting offshore wind energy development (OWED) in the U.S. Atlantic (chapter 4), bird density maps are combined across species with weights of OWED sensitivity to collision and displacement and 10 km2 sites are compared against OWED profitability based on average annual wind speed at 90m hub heights and distance to transmission grid. A spatial decision support system enables toggling between the map and tradeoff plot views by site. A selected site can be inspected for sensitivity to a cetaceans throughout the year, so as to capture months of the year which minimize episodic impacts of pre-operational activities such as seismic airgun surveying and pile driving.

Routing ships to avoid whale strikes (chapter 5) can be similarly viewed as a tradeoff, but is a different problem spatially. A cumulative cost surface is generated from density surface maps and conservation status of cetaceans, before applying as a resistance surface to calculate least-cost routes between start and end locations, i.e. ports and entrance locations to study areas. Varying a multiplier to the cost surface enables calculation of multiple routes with different costs to conservation of cetaceans versus cost to transportation industry, measured as distance. Similar to the siting chapter, a spatial decisions support system enables toggling between the map and tradeoff plot view of proposed routes. The user can also input arbitrary start and end locations to calculate the tradeoff on the fly.

Essential to the input of these decision frameworks are distributions of the species. The two preceding chapters comprise species distribution models from two case study areas, U.S. Atlantic (chapter 2) and British Columbia (chapter 3), predicting presence and density, respectively. Although density is preferred to estimate potential biological removal, per Marine Mammal Protection Act requirements in the U.S., all the necessary parameters, especially distance and angle of observation, are less readily available across publicly mined datasets.

In the case of predicting cetacean presence in the U.S. Atlantic (chapter 2), I extracted datasets from the online OBIS-SEAMAP geo-database, and integrated scientific surveys conducted by ship (n=36) and aircraft (n=16), weighting a Generalized Additive Model by minutes surveyed within space-time grid cells to harmonize effort between the two survey platforms. For each of 16 cetacean species guilds, I predicted the probability of occurrence from static environmental variables (water depth, distance to shore, distance to continental shelf break) and time-varying conditions (monthly sea-surface temperature). To generate maps of presence vs. absence, Receiver Operator Characteristic (ROC) curves were used to define the optimal threshold that minimizes false positive and false negative error rates. I integrated model outputs, including tables (species in guilds, input surveys) and plots (fit of environmental variables, ROC curve), into an online spatial decision support system, allowing for easy navigation of models by taxon, region, season, and data provider.

For predicting cetacean density within the inner waters of British Columbia (chapter 3), I calculated density from systematic, line-transect marine mammal surveys over multiple years and seasons (summer 2004, 2005, 2008, and spring/autumn 2007) conducted by Raincoast Conservation Foundation. Abundance estimates were calculated using two different methods: Conventional Distance Sampling (CDS) and Density Surface Modelling (DSM). CDS generates a single density estimate for each stratum, whereas DSM explicitly models spatial variation and offers potential for greater precision by incorporating environmental predictors. Although DSM yields a more relevant product for the purposes of marine spatial planning, CDS has proven to be useful in cases where there are fewer observations available for seasonal and inter-annual comparison, particularly for the scarcely observed elephant seal. Abundance estimates are provided on a stratum-specific basis. Steller sea lions and harbour seals are further differentiated by ‘hauled out’ and ‘in water’. This analysis updates previous estimates (Williams & Thomas 2007) by including additional years of effort, providing greater spatial precision with the DSM method over CDS, novel reporting for spring and autumn seasons (rather than summer alone), and providing new abundance estimates for Steller sea lion and northern elephant seal. In addition to providing a baseline of marine mammal abundance and distribution, against which future changes can be compared, this information offers the opportunity to assess the risks posed to marine mammals by existing and emerging threats, such as fisheries bycatch, ship strikes, and increased oil spill and ocean noise issues associated with increases of container ship and oil tanker traffic in British Columbia’s continental shelf waters.

Starting with marine animal observations at specific coordinates and times, I combine these data with environmental data, often satellite derived, to produce seascape predictions generalizable in space and time. These habitat-based models enable prediction of encounter rates and, in the case of density surface models, abundance that can then be applied to management scenarios. Specific human activities, OWED and shipping, are then compared within a tradeoff decision support framework, enabling interchangeable map and tradeoff plot views. These products make complex processes transparent for gaming conservation, industry and stakeholders towards optimal marine spatial management, fundamental to the tenets of marine spatial planning, ecosystem-based management and dynamic ocean management.

Discrimination capacity in species distribution models depends on the representativeness of the environmental domain

Aim When faced with dichotomous events, such as the presence or absence of a species, discrimination capacity (the ability to separate the instances of presence from the instances of absence) is usually the only characteristic that is assessed in the evaluation of the performance of predictive models. Although neglected, calibration or reliability (how well the estimated probability of presence represents the observed proportion of presences) is another aspect of the performance of predictive models that provides important information. In this study, we explore how changes in the distribution of the probability of presence make discrimination capacity a context-dependent characteristic of models. For the first time,we explain the implications that ignoring the context dependence of discrimination can have in the interpretation of species distribution models.

New measures for assessing model equilibrium and prediction mismatch in species distribution models

Models based on species distributions are widely used and serve important purposes in ecology, biogeography and conservation. Their continuous predictions of environmental suitability are commonly converted into a binary classification of predicted (or potential) presences and absences, whose accuracy is then evaluated through a number of measures that have been the subject of recent reviews. We propose four additional measures that analyse observation-prediction mismatch from a different angle – namely, from the perspective of the predicted rather than the observed area – and add to the existing toolset of model evaluation methods. We explain how these measures can complete the view provided by the existing measures, allowing further insights into distribution model predictions. We also describe how they can be particularly useful when using models to forecast the spread of diseases or of invasive species and to predict modifications in species’ distributions under climate and land-use change

Spatial scale effects of sampling on the interpolation of species distribution models in the southwestern Amazon.

Knowledge of the geographical distribution of timber tree species in the Amazon is still scarce. This is especially true at the local level, thereby limiting natural resource management actions. Forest inventories are key sources of information on the occurrence of such species. However, areas with approved forest management plans are mostly located near access roads and the main industrial centers. The present study aimed to assess the spatial scale effects of forest inventories used as sources of occurrence data in the interpolation of potential species distribution models. The occurrence data of a group of six forest tree species were divided into four geographical areas during the modeling process. Several sampling schemes were then tested applying the maximum entropy algorithm, using the following predictor variables: elevation, slope, exposure, normalized difference vegetation index (NDVI) and height above the nearest drainage (HAND). The results revealed that using occurrence data from only one geographical area with unique environmental characteristics increased both model overfitting to input data and omission error rates. The use of a diagonal systematic sampling scheme and lower threshold values led to improved model performance. Forest inventories may be used to predict areas with a high probability of species occurrence, provided they are located in forest management plan regions representative of the environmental range of the model projection area.

Distribution models for mountain plant species: The value of elevation

The climatic conditions of mountain habitats are greatly influenced by topography. Large differences in microclimate occur with small changes in elevation, and this complex interaction is an important determinant of mountain plant distributions. In spite of this, elevation is not often considered as a relevant predictor in species distribution models (SDMs) for mountain plants. Here, we evaluated the importance of including elevation as a predictor in SDMs for mountain plant species. We generated two sets of SDMs for each of 73 plant species that occur in the Pacific Northwest of North America; one set of models included elevation as a predictor variable and the other set did not. AUC scores indicated that omitting elevation as a predictor resulted in a negligible reduction of model performance. However, further analysis revealed that the omission of elevation resulted in large over-predictions of species' niche breadths-this effect was most pronounced for species that occupy the highest elevations. In addition, the inclusion of elevation as a predictor constrained the effects of other predictors that superficially affected the outcome of the models generated without elevation. Our results demonstrate that the inclusion of elevation as a predictor variable improves the quality of SDMs for high-elevation plant species. Because of the negligible AUC score penalty for over-predicting niche breadth, our results support the notion that AUC scores alone should not be used as a measure of model quality. More generally, our results illustrate the importance of selecting biologically relevant predictor variables when constructing SDMs.

Uncertain species distribution: From interpolation to extrapolation

Species distribution models (SDMs) are considered to exemplify Pattern rather than Process based models of a species' response to its environment. Hence when used to map species distribution, the purpose of SDMs can be viewed as interpolation, since species response is measured at a few sites in the study region, and the aim is to interpolate species response at intermediate sites. Increasingly, however, SDMs are also being used to also extrapolate species-environment relationships beyond the limits of the study region as represented by the training data. Regardless of whether SDMs are to be used for interpolation or extrapolation, the debate over how to implement SDMs focusses on evaluating the quality of the SDM, both ecologically and mathematically. This paper proposes a framework that includes useful tools previously employed to address uncertainty in habitat modelling. Together with existing frameworks for addressing uncertainty more generally when modelling, we then outline how these existing tools help inform development of a broader framework for addressing uncertainty, specifically when building habitat models. As discussed earlier we focus on extrapolation rather than interpolation, where the emphasis on predictive performance is diluted by the concerns for robustness and ecological relevance. We are cognisant of the dangers of excessively propagating uncertainty. Thus, although the framework provides a smorgasbord of approaches, it is intended that the exact menu selected for a particular application, is small in size and targets the most important sources of uncertainty. We conclude with some guidance on a strategic approach to identifying these important sources of uncertainty. Whilst various aspects of uncertainty in SDMs have previously been addressed, either as the main aim of a study or as a necessary element of constructing SDMs, this is the first paper to provide a more holistic view.

Incorporating uncertainty in predictive species distribution modelling

Motivated by the need to solve ecological problems (climate change, habitat fragmentation and biological invasions), there has been increasing interest in species distribution models (SDMs). Predictions from these models inform conservation policy, invasive species management and disease-control measures. However, predictions are subject to uncertainty, the degree and source of which is often unrecognized. Here, we review the SDM literature in the context of uncertainty, focusing on three main classes of SDM: niche-based models, demographic models and process-based models. We identify sources of uncertainty for each class and discuss how uncertainty can be minimized or included in the modelling process to give realistic measures of confidence around predictions. Because this has typically not been performed, we conclude that uncertainty in SDMs has often been underestimated and a false precision assigned to predictions of geographical distribution. We identify areas where development of new statistical tools will improve predictions from distribution models, notably the development of hierarchical models that link different types of distribution model and their attendant uncertainties across spatial scales. Finally, we discuss the need to develop more defensible methods for assessing predictive performance, quantifying model goodness-of-fit and for assessing the significance of model covariates.