Improving the estimation of the Boyce index using statistical smoothing methods for evaluating species distribution models with presence-only data

IF 5.4 1区环境科学与生态学 Q1 BIODIVERSITY CONSERVATION

Ecography Pub Date : 2024-10-16 DOI:10.1111/ecog.07218

Canran Liu, Graeme Newell, Matt White, Josephine Machunter

{"title":"Improving the estimation of the Boyce index using statistical smoothing methods for evaluating species distribution models with presence-only data","authors":"Canran Liu, Graeme Newell, Matt White, Josephine Machunter","doi":"10.1111/ecog.07218","DOIUrl":null,"url":null,"abstract":"Species distribution models (SDMs) underpin a wide range of decisions concerning biodiversity. Although SDMs can be built using presence-only data, rigorous evaluation of these models remains challenging. One evaluation method is the Boyce index (BI), which uses the relative frequencies between presence sites and background sites within a series of bins or moving windows spanning the entire range of predicted values from the SDM. Obtaining accurate estimates of the BI using these methods relies upon having a large number of presences, which is often not feasible, particularly for rare or restricted species that are often the focus of modelling. Wider application of the BI requires a method that can accurately and reliably estimate the BI using small numbers of presence records. In this study, we investigated the effectiveness of five statistical smoothing methods (i.e. thin plate regression splines, cubic regression splines, B-splines, P-splines and adaptive smoothers) and the mean of these five methods (denoted as ‘mean') to estimate the BI. We simulated 600 species with varying prevalence and built distribution models using random forest and Maxent methods. For training data, we used two levels for the number of presences (NPtrain: 20 and 500), along with 2 × NPtrain and 10000 random points (i.e. random background sites) for each modelling method. We used the number of presences at four levels (NPbi: 1000, 200, 50 and 10) to investigate its effect, together with 5000 random points to calculate the BI. Our results indicate that the BI estimates from the binning and moving window methods are severely affected by the decrease of NPbi, but all the estimates of the BI from smoothing-based methods were almost always unbiased for realistic situations. Hence, we recommend these methods for estimating the BI for evaluating SDMs when verified absence data are unavailable.","PeriodicalId":51026,"journal":{"name":"Ecography","volume":null,"pages":null},"PeriodicalIF":5.4000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ecography","FirstCategoryId":"93","ListUrlMain":"https://doi.org/10.1111/ecog.07218","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIODIVERSITY CONSERVATION","Score":null,"Total":0}

引用次数: 0

Abstract

Species distribution models (SDMs) underpin a wide range of decisions concerning biodiversity. Although SDMs can be built using presence-only data, rigorous evaluation of these models remains challenging. One evaluation method is the Boyce index (BI), which uses the relative frequencies between presence sites and background sites within a series of bins or moving windows spanning the entire range of predicted values from the SDM. Obtaining accurate estimates of the BI using these methods relies upon having a large number of presences, which is often not feasible, particularly for rare or restricted species that are often the focus of modelling. Wider application of the BI requires a method that can accurately and reliably estimate the BI using small numbers of presence records. In this study, we investigated the effectiveness of five statistical smoothing methods (i.e. thin plate regression splines, cubic regression splines, B-splines, P-splines and adaptive smoothers) and the mean of these five methods (denoted as ‘mean') to estimate the BI. We simulated 600 species with varying prevalence and built distribution models using random forest and Maxent methods. For training data, we used two levels for the number of presences (NP_train: 20 and 500), along with 2 × NP_train and 10000 random points (i.e. random background sites) for each modelling method. We used the number of presences at four levels (NP_bi: 1000, 200, 50 and 10) to investigate its effect, together with 5000 random points to calculate the BI. Our results indicate that the BI estimates from the binning and moving window methods are severely affected by the decrease of NP_bi, but all the estimates of the BI from smoothing-based methods were almost always unbiased for realistic situations. Hence, we recommend these methods for estimating the BI for evaluating SDMs when verified absence data are unavailable.

查看原文本刊更多论文

利用统计平滑方法改进博伊斯指数的估算，以评估仅存在数据的物种分布模型

物种分布模型（SDM）是有关生物多样性的各种决策的基础。尽管可以使用纯存在数据建立 SDM，但对这些模型进行严格评估仍具有挑战性。其中一种评估方法是博伊斯指数（BI），它使用的是存在地点与背景地点之间在一系列横跨 SDM 预测值整个范围的箱或移动窗口中的相对频率。使用这些方法获得 BI 的准确估计值依赖于大量的存在点，而这往往是不可行的，特别是对于通常是建模重点的稀有或限制性物种。要想更广泛地应用生物多样性指数，就需要一种能利用少量存在记录准确可靠地估算生物多样性指数的方法。在本研究中，我们调查了五种统计平滑方法（即薄板回归样条、立方回归样条、B 样条、P 样条和自适应平滑器）以及这五种方法的平均值（称为 "平均值"）在估算生物分布指数方面的有效性。我们模拟了 600 种不同流行率的物种，并使用随机森林和 Maxent 方法建立了分布模型。在训练数据方面，我们使用了两个级别的存在数量（NPtrain：20 和 500），同时每种建模方法还使用了 2 × NPtrain 和 10000 个随机点（即随机背景点）。我们使用了四种水平的存在数量（NPbi：1000、200、50 和 10）来研究其影响，同时使用 5000 个随机点来计算 BI。我们的结果表明，分选法和移动窗口法的 BI 估计值会受到 NPbi 下降的严重影响，但基于平滑法的所有 BI 估计值在现实情况下几乎总是无偏的。因此，我们推荐使用这些方法估算 BI，以便在无法获得经核实的缺席数据时评估 SDM。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Ecography 环境科学-生态学

CiteScore

11.60

自引率

3.40%

发文量

122

审稿时长

8-16 weeks

期刊介绍： ECOGRAPHY publishes exciting, novel, and important articles that significantly advance understanding of ecological or biodiversity patterns in space or time. Papers focusing on conservation or restoration are welcomed, provided they are anchored in ecological theory and convey a general message that goes beyond a single case study. We encourage papers that seek advancing the field through the development and testing of theory or methodology, or by proposing new tools for analysis or interpretation of ecological phenomena. Manuscripts are expected to address general principles in ecology, though they may do so using a specific model system if they adequately frame the problem relative to a generalized ecological question or problem. Purely descriptive papers are considered only if breaking new ground and/or describing patterns seldom explored. Studies focused on a single species or single location are generally discouraged unless they make a significant contribution to advancing general theory or understanding of biodiversity patterns and processes. Manuscripts merely confirming or marginally extending results of previous work are unlikely to be considered in Ecography. Papers are judged by virtue of their originality, appeal to general interest, and their contribution to new developments in studies of spatial and temporal ecological patterns. There are no biases with regard to taxon, biome, or biogeographical area.