On the selection of thresholds for predicting species occurrence with presence‐only data

Presence‐only data present challenges for selecting thresholds to transform species distribution modeling results into binary outputs. In this article, we compare two recently published threshold selection methods (maxSSS and maxF_pb) and examine the effectiveness of the threshold‐based prevalence estimation approach. Six virtual species with varying prevalence were simulated within a real landscape in southeastern Australia. Presence‐only models were built with DOMAIN, generalized linear model, Maxent, and Random Forest. Thresholds were selected with two methods maxSSS and maxF_pb with four presence‐only datasets with different ratios of the number of known presences to the number of random points (KP–RP_ratio). Sensitivity, specificity, true skill statistic, and F measure were used to evaluate the performance of the results. Species prevalence was estimated as the ratio of the number of predicted presences to the total number of points in the evaluation dataset. Thresholds selected with maxF_pb varied as the KP–RP_ratio of the threshold selection datasets changed. Datasets with the KP–RP_ratio around 1 generally produced better results than scores distant from 1. Results produced by We conclude that maxF_pb had specificity too low for very common species using Random Forest and Maxent models. In contrast, maxSSS produced consistent results whichever dataset was used. The estimation of prevalence was almost always biased, and the bias was very large for DOMAIN and Random Forest predictions. We conclude that maxF_pb is affected by the KP–RP_ratio of the threshold selection datasets, but maxSSS is almost unaffected by this ratio. Unbiased estimations of prevalence are difficult to be determined using the threshold‐based approach.     

Using a species distribution model to guide NSW surveys of the long‐footed potoroo (Potorous longipes)

Knowledge of threatened species’ distributions is essential for effective conservation decision‐making. Species distribution models (SDMs) are widely used to map species’ geographic ranges, identify new areas of suitable habitat and guide field surveys. In New South Wales (NSW), Australia, there are grave doubts about whether populations of the critically endangered long‐footed potoroo (Potorous longipes) remain extant, and identification of occupied sites is a high priority for its conservation. We used an SDM (Maxent) to identify regions in NSW that may have suitable habitat for the potoroo. The SDM was built with seven climate layers and had strong predictive performance (cross‐validated AUC = 0.94). We then combined this information on habitat suitability with vegetation and topography, to identify 58 survey sites across NSW. From April 2016 to May 2017, we undertook six field trips deploying six to eight cameras at each site for 52–63 days, resulting in 25 120 camera trap nights. A total of 215 759 images captured 43 native and feral animal species, but no long‐footed potoroos. Following the survey, newly available, independent presence and absence data were used to validate our model. A Kruskal–Wallis H test indicated that habitat suitability values were significantly higher at presence locations than absence locations (H = 58.66, d.f. = 1, P < 0.001). Finally, we refitted the Maxent model with the new data and identified additional regions that future surveys could explore. We conclude, however, that if the long‐footed potoroo remains extant in NSW, it is extremely rare.     

Nondetection sampling bias in marked presence‐only data

相似文献   

Presence‐only versus presence–absence data in species composition determinant analyses

Aim Studying relationships between species and their physical environment requires species distribution data, ideally based on presence–absence (P–A) data derived from surveys. Such data are limited in their spatial extent. Presence‐only (P‐O) data are considered inappropriate for such analyses. Our aim was to evaluate whether such data may be used when considering a multitude of species over a large spatial extent, in order to analyse the relationships between environmental factors and species composition. Location The study was conducted in virtual space. However, geographic origin of the data used is the contiguous USA. Methods We created distribution maps for 50 virtual species based on actual environmental conditions in the study. Sampling locations were based on true observations from the Global Biodiversity Information Facility. We produced P–A data by selecting ∼1000 random locations and recorded the presence/absence of all species. We produced two P‐O data sets. Full P‐O set was produced by sampling the species in locations of true occurrences of species. Partial P‐O was a subset of full P‐O data set matching the size of the P–A data set. For each data set, we recorded the environmental variables at the same locations. We used CCA to evaluate the amount of variance in species composition explained by each variable. We evaluated the bias in the data set by calculating the deviation of average values of the environmental variables in sampled locations compared to the entire area. Results P–A and P‐O data sets were similar in terms of the amount of variance explained by the different environmental variables. We found sizable environmental and spatial bias in the P‐O data set, compared to the entire study area. Main conclusions Our results suggest that although P‐O data from collections contain bias, the multitude of species, and thus the relatively large amount of information in the data, allow the use of P‐O data for analysing environmental determinants of species composition.     

Wrong,but useful: regional species distribution models may not be improved by range‐wide data under biased sampling

Species distribution modeling (SDM) is an essential method in ecology and conservation. SDMs are often calibrated within one country's borders, typically along a limited environmental gradient with biased and incomplete data, making the quality of these models questionable. In this study, we evaluated how adequate are national presence‐only data for calibrating regional SDMs. We trained SDMs for Egyptian bat species at two different scales: only within Egypt and at a species‐specific global extent. We used two modeling algorithms: Maxent and elastic net, both under the point‐process modeling framework. For each modeling algorithm, we measured the congruence of the predictions of global and regional models for Egypt, assuming that the lower the congruence, the lower the appropriateness of the Egyptian dataset to describe the species' niche. We inspected the effect of incorporating predictions from global models as additional predictor (“prior”) to regional models, and quantified the improvement in terms of AUC and the congruence between regional models run with and without priors. Moreover, we analyzed predictive performance improvements after correction for sampling bias at both scales. On average, predictions from global and regional models in Egypt only weakly concur. Collectively, the use of priors did not lead to much improvement: similar AUC and high congruence between regional models calibrated with and without priors. Correction for sampling bias led to higher model performance, whatever prior used, making the use of priors less pronounced. Under biased and incomplete sampling, the use of global bats data did not improve regional model performance. Without enough bias‐free regional data, we cannot objectively identify the actual improvement of regional models after incorporating information from the global niche. However, we still believe in great potential for global model predictions to guide future surveys and improve regional sampling in data‐poor regions.     

物种潜在分布地预测系统PSDS的设计与实现

本研究设计并实现了一个基于地理信息系统(GIS)的仅用物种已知分布点数据预测物种潜在分布地的PSDS系统.在这一系统中,通过层次聚类算法对物种已知分布点数据进行处理,减少了异常值对预测结果的影响,从而解决了环境包络模型预测结果过于乐观的问题,在物种已知分布数据较少时也能取得较好的结果.该系统实现了数据加载与导出、图层浏览与显示、生态因子分析与分布地预测、结果展示等功能,操作方便,简单易用.本文以白冠长尾雉(Syrmaticus reevesii)为例,根据4个省的少量已知分布点数据对其在国内的潜在分布地进行了预测,获得了较理想的结果,可为该物种的保护提供科学依据.     

Testing the utility of species distribution modelling using Random Forests for a species in decline

Habitat suitability estimates derived from species distribution models (SDMs) are increasingly used to guide management of threatened species. Poorly estimating species’ ranges can lead to underestimation of threatened status, undervaluing of remaining habitat and misdirection of conservation funding. We aimed to evaluate the utility of a SDM, similar to the models used to inform government regulation of habitat in our study region, in estimating the contemporary distribution of a threatened and declining species. We developed a presence‐only SDM for the endangered New Holland Mouse (Pseudomys novaehollandiae) across Victoria, Australia. We conducted extensive camera trap surveys across model‐predicted and expert‐selected areas to generate an independent data set for use in evaluating the model, determining confidence in absence data from non‐detection sites with occupancy and detectability modelling. We assessed the predictive capacity of the model at thresholds based on (1) sum of sensitivity and specificity (SSS), and (2) the lowest presence threshold (LPT; i.e. the lowest non‐zero model‐predicted habitat suitability value at which we detected the species). We detected P. novaehollandiae at 40 of 472 surveyed sites, with strong support for the species’ probable absence from non‐detection sites. Based on our post hoc optimised SSS threshold of the SDM, 25% of our detection sites were falsely predicted as non‐suitable habitat and 75% of sites predicted as suitable habitat did not contain the species at the time of our survey. One occupied site had a model‐predicted suitability value of zero, and at the LPT, 88% of sites predicted as suitable habitat did not contain the species at the time of our survey. Our findings demonstrate that application of generic SDMs in both regulatory and investment contexts should be tempered by considering their limitations and currency. Further, we recommend engaging species experts in the extrapolation and application of SDM outputs.     

A statistical explanation of MaxEnt for ecologists

MaxEnt is a program for modelling species distributions from presence‐only species records. This paper is written for ecologists and describes the MaxEnt model from a statistical perspective, making explicit links between the structure of the model, decisions required in producing a modelled distribution, and knowledge about the species and the data that might affect those decisions. To begin we discuss the characteristics of presence‐only data, highlighting implications for modelling distributions. We particularly focus on the problems of sample bias and lack of information on species prevalence. The keystone of the paper is a new statistical explanation of MaxEnt which shows that the model minimizes the relative entropy between two probability densities (one estimated from the presence data and one, from the landscape) defined in covariate space. For many users, this viewpoint is likely to be a more accessible way to understand the model than previous ones that rely on machine learning concepts. We then step through a detailed explanation of MaxEnt describing key components (e.g. covariates and features, and definition of the landscape extent), the mechanics of model fitting (e.g. feature selection, constraints and regularization) and outputs. Using case studies for a Banksia species native to south‐west Australia and a riverine fish, we fit models and interpret them, exploring why certain choices affect the result and what this means. The fish example illustrates use of the model with vector data for linear river segments rather than raster (gridded) data. Appropriate treatments for survey bias, unprojected data, locally restricted species, and predicting to environments outside the range of the training data are demonstrated, and new capabilities discussed. Online appendices include additional details of the model and the mathematical links between previous explanations and this one, example code and data, and further information on the case studies.     

Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling

Aim The area under the receiver operating characteristic (ROC) curve (AUC) is a widely used statistic for assessing the discriminatory capacity of species distribution models. Here, I used simulated data to examine the interdependence of the AUC and classical discrimination measures (sensitivity and specificity) derived for the application of a threshold. I shall further exemplify with simulated data the implications of using the AUC to evaluate potential versus realized distribution models. Innovation After applying the threshold that makes sensitivity and specificity equal, a strong relationship between the AUC and these two measures was found. This result is corroborated with real data. On the other hand, the AUC penalizes the models that estimate potential distributions (the regions where the species could survive and reproduce due to the existence of suitable environmental conditions), and favours those that estimate realized distributions (the regions where the species actually lives). Main conclusions Firstly, the independence of the AUC from the threshold selection may be irrelevant in practice. This result also emphasizes the fact that the AUC assumes nothing about the relative costs of errors of omission and commission. However, in most real situations this premise may not be optimal. Measures derived from a contingency table for different cost ratio scenarios, together with the ROC curve, may be more informative than reporting just a single AUC value. Secondly, the AUC is only truly informative when there are true instances of absence available and the objective is the estimation of the realized distribution. When the potential distribution is the goal of the research, the AUC is not an appropriate performance measure because the weight of commission errors is much lower than that of omission errors.     

Spatially autocorrelated sampling falsely inflates measures of accuracy for presence‐only niche models

Aim Environmental niche models that utilize presence‐only data have been increasingly employed to model species distributions and test ecological and evolutionary predictions. The ideal method for evaluating the accuracy of a niche model is to train a model with one dataset and then test model predictions against an independent dataset. However, a truly independent dataset is often not available, and instead random subsets of the total data are used for ‘training’ and ‘testing’ purposes. The goal of this study was to determine how spatially autocorrelated sampling affects measures of niche model accuracy when using subsets of a larger dataset for accuracy evaluation. Location The distribution of Centaurea maculosa (spotted knapweed; Asteraceae) was modelled in six states in the western United States: California, Oregon, Washington, Idaho, Wyoming and Montana. Methods Two types of niche modelling algorithms – the genetic algorithm for rule‐set prediction (GARP) and maximum entropy modelling (as implemented with Maxent) – were used to model the potential distribution of C. maculosa across the region. The effect of spatially autocorrelated sampling was examined by applying a spatial filter to the presence‐only data (to reduce autocorrelation) and then comparing predictions made using the spatial filter with those using a random subset of the data, equal in sample size to the filtered data. Results The accuracy of predictions from both algorithms was sensitive to the spatial autocorrelation of sampling effort in the occurrence data. Spatial filtering led to lower values of the area under the receiver operating characteristic curve plot but higher similarity statistic (I) values when compared with predictions from models built with random subsets of the total data, meaning that spatial autocorrelation of sampling effort between training and test data led to inflated measures of accuracy. Main conclusions The findings indicate that care should be taken when interpreting the results from presence‐only niche models when training and test data have been randomly partitioned but occurrence data were non‐randomly sampled (in a spatially autocorrelated manner). The higher accuracies obtained without the spatial filter are a result of spatial autocorrelation of sampling effort between training and test data inflating measures of prediction accuracy. If independently surveyed data for testing predictions are unavailable, then it may be necessary to explicitly account for the spatial autocorrelation of sampling effort between randomly partitioned training and test subsets when evaluating niche model predictions.