School of Agriculture, Food and Ecosystem Sciences - Research Publications
Permanent URI for this collection
Search Results
1 - 6 of 6
-
ItemIntegrating species metrics into biodiversity offsetting calculations to improve long-term persistence(WILEY, 2022-04)Abstract Several methods of measuring biodiversity in development‐offset trades exist. However, there is little consensus on which biodiversity metrics should be used for quantifying development impacts and assigning offsets. We simulated development impacts in a virtual landscape and offset these impacts using six biodiversity metrics: vegetation area, vegetation condition, habitat suitability, species abundance, metapopulation connectivity and rarity‐weighted richness. We tested long‐term impacts of metric choice during offsetting by combining simulated landscapes with population viability analyses. No net loss or net gains in habitat were achieved using all metrics except vegetation area and condition. Limited habitat and like‐for‐like requirements resulted in offsets exhausting available habitat in each vegetation class before offset requirements were met when using vegetation‐based metrics. We also found that impact avoidance was an important driver in how much compensation offsets could deliver. When impacts avoided high‐suitability habitats, all six metrics achieved no net loss or net gains for most species. However, when core habitats were developed, none of the metrics were able to consistently prevent population declines. Synthesis and application. When impacts on high‐quality habitat were avoided, and assuming the protection and restoration benefits can occur in practice, vegetation‐based metrics may produce offsets which deliver gains in species abundance equivalent to species‐specific metrics. However, species‐specific metrics outperformed vegetation‐based metrics when core habitats were lost. Applying avoidance measures as a first step to minimise biodiversity impacts during development will significantly improve offset outcomes for species and result in greater long‐term population benefits delivered through offsetting.
-
ItemModelling species presence-only data with random forests(WILEY, 2021-12)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.
-
ItemPredictive performance of presence-only species distribution models: a benchmark study with reproducible code(WILEY, 2022-02)Abstract Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence‐only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence‐only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well‐established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point‐process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision‐recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible.
-
ItemThe conservation impacts of ecological disturbance: Time-bound estimates of population loss and recovery for fauna affected by the 2019-2020 Australian megafires(WILEY, 2022-10-01)Aim: After environmental disasters, species with large population losses may need urgent protection to prevent extinction and support recovery. Following the 2019–2020 Australian megafires, we estimated population losses and recovery in fire-affected fauna, to inform conservation status assessments and management. Location: Temperate and subtropical Australia. Time period: 2019–2030 and beyond. Major taxa: Australian terrestrial and freshwater vertebrates; one invertebrate group. Methods: From > 1,050 fire-affected taxa, we selected 173 whose distributions substantially overlapped the fire extent. We estimated the proportion of each taxon’s distribution affected by fires, using fire severity and aquatic impact mapping, and new distribution mapping. Using expert elicitation informed by evidence of responses to previous wildfires, we estimated local population responses to fires of varying severity. We combined the spatial and elicitation data to estimate overall population loss and recovery trajectories, and thus indicate potential eligibility for listing as threatened, or uplisting, under Australian legislation. Results: We estimate that the 2019–2020 Australian megafires caused, or contributed to, population declines that make 70–82 taxa eligible for listing as threatened; and another 21–27 taxa eligible for uplisting. If so-listed, this represents a 22–26% increase in Australian statutory lists of threatened terrestrial and freshwater vertebrates and spiny crayfish, and uplisting for 8–10% of threatened taxa. Such changes would cause an abrupt worsening of underlying trajectories in vertebrates, as measured by Red List Indices. We predict that 54–88% of 173 assessed taxa will not recover to pre-fire population size within 10 years/three generations. Main conclusions: We suggest the 2019–2020 Australian megafires have worsened the conservation prospects for many species. Of the 91 taxa recommended for listing/uplisting consideration, 84 are now under formal review through national processes. Improving predictions about taxon vulnerability with empirical data on population responses, reducing the likelihood of future catastrophic events and mitigating their impacts on biodiversity, are critical.
-
ItemPRESENCE-ONLY AND PRESENCE-ABSENCE DATA FOR COMPARING SPECIES DISTRIBUTION MODELING METHODS(UNIV KANSAS, NATURAL HISTORY MUSEUM & BIODIVERSITY RESEARCH CTR, 2020)Species distribution models (SDMs) are widely used to predict and study distributions of species. Many different modeling methods and associated algorithms are used and continue to emerge. It is important to understand how different approaches perform, particularly when applied to species occurrence records that were not gathered in structured surveys (e.g. opportunistic records). This need motivated a large-scale, collaborative effort, published in 2006, that aimed to create objective comparisons of algorithm performance. As a benchmark, and to facilitate future comparisons of approaches, here we publish that dataset: point location records for 226 anonymized species from six regions of the world, with accompanying predictor variables in raster (grid) and point formats. A particularly interesting characteristic of this dataset is that independent presence-absence survey data are available for evaluation alongside the presence-only species occurrence data intended for modeling. The dataset is available on Open Science Framework and as an R package and can be used as a benchmark for modeling approaches and for testing new ways to evaluate the accuracy of SDMs.
-
ItemQuantifying the impact of vegetation-based metrics on species persistence when choosing offsets for habitat destruction(WILEY, 2021-04)Developers are often required by law to offset environmental impacts through targeted conservation actions. Most offset policies specify metrics for calculating offset requirements, usually by assessing vegetation condition. Despite widespread use, there is little evidence to support the effectiveness of vegetation-based metrics for ensuring biodiversity persistence. We compared long-term impacts of biodiversity offsetting based on area only; vegetation condition only; area × habitat suitability; and condition × habitat suitability in development and restoration simulations for the Hunter Region of New South Wales, Australia. We simulated development and subsequent offsetting through restoration within a virtual landscape, linking simulations to population viability models for 3 species. Habitat gains did not ensure species persistence. No net loss was achieved when performance of offsetting was assessed in terms of amount of habitat restored, but not when outcomes were assessed in terms of persistence. Maintenance of persistence occurred more often when impacts were avoided, giving further support to better enforce the avoidance stage of the mitigation hierarchy. When development affected areas of high habitat quality for species, persistence could not be guaranteed. Therefore, species must be more explicitly accounted for in offsets, rather than just vegetation or habitat alone. Declines due to a failure to account directly for species population dynamics and connectivity overshadowed the benefits delivered by producing large areas of high-quality habitat. Our modeling framework showed that the benefits delivered by offsets are species specific and that simple vegetation-based metrics can give misguided impressions on how well biodiversity offsets achieve no net loss.