Search

In building a robust knowledge base or validating existing models for use in ecological spatial modelling, having plentiful high‐quality data is paramount. Careful survey design helps attain that goal and, in part due to financial constraints, such design requires the balancing of hard monetary costs and the intangible benefit of improved ecological models.We propose a framework that quantifies a location's value to the modeller by accounting for both the probability of obtaining new samples and their expected contribution to the model. The approach is illustrated on a citizen science database of roadkills in Taiwan, modelled as a Poisson point process on a linear road network.Our method has revealed some valuable locations that were not self‐evident, for example, highlighting the possibility of sending volunteers to mountainous areas that despite being hard to reach, would provide valuable samples. We have also highlighted some ex situ sampling opportunities to avoid wasting resources by over‐sampling hard to access locations.Our technique is not restricted to presence‐only data, and in fact we present a general framework that can be applied to a wide range of settings by tuning its formulation. Our method is quite flexible and allows for more elaborate value functions, enabling managers to precisely quantify varied goals within the same framework. [ABSTRACT FROM AUTHOR]

This study evaluates the spatiotemporal generalization of statistical and machine learning models to simulate built‐up land expansion and compare it to ensemble approaches. Integrated with cellular automata, six individual models—artificial neural networks, support vector machines (SVM), random forest (RF), boosted regression trees, the generalized additive model, the lasso, and two ensemble approaches called ensemble median and ensemble weighted area under the curve—were implemented. Each model was calibrated based on data from 1975–1990, and their extrapolation power was evaluated for 1990–1996, 1996–2000, 2000–2011, and 2011–2017. Total operating characteristics revealed that the RF model achieved the highest calibration accuracy and the highest performance loss during the validation period. The lowest calibration accuracy was related to the SVM model, yet its performance during the validation period increased. In the third time interval (1996–2002), the highest accuracy was again related to the SVM model. A sharp drop in simulation accuracy was seen in all models during the fourth (2002–2011) and fifth intervals (2011–2017). None of the ensemble models appeared to be superior to the individual models. Further, the accuracy of built‐up land expansion models drops noticeably for long‐term simulations. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. Article impact statement: It is important to use offset metrics that account for the impacts of development on long‐term species persistence. [ABSTRACT FROM AUTHOR]

Copyright of Methods in Ecology & Evolution is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Large-scale disturbance events are forecast to increase in severity and frequency due to climate change. On-ground surveys are crucial for assessing the immediate impact of disturbances on biodiversity and for informing management responses. However, there are few examples where quantitative tools have guided post-disturbance survey design. In this study, we integrated species distribution modelling and spatial prioritisation to identify taxonomic and spatial gaps in surveys for 92 priority vertebrates 6 months after the 2019–20 wildfires in Australia. We predicted the pre-fire distribution of priority species, mapped locations of post-wildfire surveys that were already underway, and integrated this information with remotely-sensed fire severity maps in the tool, Zonation, to prioritise locations for new surveys across three fire severity classes (unburnt, low severity, high severity). Our results suggest that 6 months after the wildfires, surveys by government agencies had targeted 17 of 20 mammals (85%); 11 of 17 birds (65%); 10 of 17 frogs (59%); 10 of 23 reptiles (43%) and 5 of 17 fish (29%). We developed species distribution models for 63 of these species after collating 120,118 occurrence records from 6 data repositories. By predicting their distribution before the wildfires, we most efficiently identified gaps in survey effort while ensuring representation across species and fire severity classes. Our analysis provided an important 'stocktake' of the response effort to the 2019–20 wildfires in Australia and helped inform the allocation of government-funded wildfire recovery programs. Although we focus on wildfire, our approach could assess gaps in survey effort following any large-scale disturbance. • Post-fire survey effort was inconsistent across taxonomic groups. • There was little national coordination of post-fire surveys. • The representation of surveys could be drastically increased with small amounts of additional effort. • Many species and regions are yet to be surveyed after the 2019–20 megafires. [ABSTRACT FROM AUTHOR]