基于地理环境相似度的长江经济带入侵物种虚拟负样本生成方法

doi:10.17520/biods.2022094

生物多样性 ›› 2023, Vol. 31 ›› Issue (1): 22094. DOI: 10.17520/biods.2022094 cstr: 32101.14.biods.2022094

基于地理环境相似度的长江经济带入侵物种虚拟负样本生成方法

肖巍峰¹^,²^,³, 左绿荇¹, 杨文涛¹^,³^,^*(), 李朝奎³

1.湖南科技大学地球科学与空间信息工程学院, 湖南湘潭 411201
2.湖南省地质灾害监测预警与应急救援工程技术研究中心, 长沙 410004
3.湖南科技大学测绘遥感重点实验室, 湖南湘潭 411201

收稿日期:2022-03-01 接受日期:2022-06-01 出版日期:2023-01-20 发布日期:2022-06-23
通讯作者: 杨文涛
作者简介:*E-mail: yangwentao8868@126.com
基金资助:
湖南省自然科学基金创新研究群体项目(2020JJ1003);湖南省教育厅科研项目(20C0805)

Generating pseudo-absence samples of invasive species based on the similarity of geographical environment in the Yangtze River Economic Belt

Weifeng Xiao¹^,²^,³, Lüxing Zuo¹, Wentao Yang¹^,³^,^*(), Chaokui Li³

1. School of Earth Sciences and Spatial Information Engineering, Hunan University of Science and Technology, Xiangtan, Hunan 411201
2. Hunan Geological Disaster Monitoring, Early Warning and Emergency Rescue Engineering Technology Research Center, Changsha 410004
3. Hunan Provincial Key Laboratory of Geo-Information Engineering in Surveying, Mapping and Remote Sensing, Hunan University of Science and Technology, Xiangtan, Hunan 411201

Received:2022-03-01 Accepted:2022-06-01 Online:2023-01-20 Published:2022-06-23
Contact: Wentao Yang

1. 附录1 一年蓬样本位置信息.pdf(104KB)

摘要/Abstract

摘要：

入侵物种空间分布建模的核心数据源来源于物种多样性采样(物种出现点和未出现点), 然而, 大多数入侵物种标本库只记录物种出现点样本信息, 缺乏对未出现点(负样本)位置的记录。因此, 生成有效的入侵物种虚拟负样本是建立物种空间分布模型的关键。本文提出了一种基于地理环境相似度的虚拟负样本生成方法。首先利用主成分分析(PCA)方法对地理环境原始变量进行线性相关性建模, 基于提取的主成分, 采用K-means算法对入侵物种样本进行聚类分析并计算各样本的地理环境相似度。在此基础上, 通过建立基于主成分的入侵物种相似性度量与可信度计算框架来识别虚拟负样本。以长江经济带入侵物种一年蓬(Erigeron annuus)数据集为例, 分析了整个区域虚拟负样本的可信度。结果表明, 与空间随机采样和单类支持向量机采样相比, 用本研究提出的方法生成的样本数据建立的logistic回归和支持向量机预测结果更优, 验证了该方法的可行性与有效性。基于地理环境相似度的虚拟负样本抽样策略有助于解决由于随机采样而引起的误采样到潜在入侵点的难题, 同时负样本的可信度能有助于识别不同等级的入侵物种适应区。

关键词: 入侵物种, 地理环境, 可信度, 一年蓬, 长江经济带

Abstract

Aims: Obtaining diversity samples of invasive alien species is crucial for species spatial distribution models. This includes both invasive species presence and absence samples. However, most invasive species data sets lack explicit spatial information for absent species samples. Consequently, generating effective pseudo-absence samples of invasive species is a significant issue for constructing species spatial distribution models. This paper proposed an invasive species pseudo-absence sampling method based on the similarities of geographical environments.

Methods: First, the principal component analysis (PCA) was used to model the linear correlation of the original variables. Then the K-means algorithm was used to cluster the invasive species samples and calculate the geographic environment similarity of each of them based on the PCA components. Second, the pseudo-absence samples of invasive species were generated by establishing a framework for similarity measurement of PCA components and confidence level calculation of pseudo-absence samples. Finally, based on random sampling, one-class support vector machine (OCSVM) and the proposed approach, the logistic regression and support vector machine (SVM) were adopted to implement the accuracy evaluation by using the dataset regarding the invasive species Erigeron annuus in the Yangtze River Economic Belt.

Results Compared with random sampling and OCSVM, the proposed sampling approach had better prediction results from logistic regression and SVM, and the feasibility and effectiveness of the proposed approach were validated.

ConclusionsThe strategy for generating pseudo-absence samples based on the similarity of geographical environments solves the problem of erroneously sampling potential invasive species presence owing to random sampling, meanwhile, the confidence level of species absence samples can be used to obtain different levels of adaptive areas of invasive species.

Key words: invasive species, geographic environment, confidence level, Erigeron annuus, the Yangtze River Economic Belt

肖巍峰, 左绿荇, 杨文涛, 李朝奎 (2023) 基于地理环境相似度的长江经济带入侵物种虚拟负样本生成方法. 生物多样性, 31, 22094. DOI: 10.17520/biods.2022094.

Weifeng Xiao, Lüxing Zuo, Wentao Yang, Chaokui Li (2023) Generating pseudo-absence samples of invasive species based on the similarity of geographical environment in the Yangtze River Economic Belt. Biodiversity Science, 31, 22094. DOI: 10.17520/biods.2022094.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.biodiversity-science.net/CN/10.17520/biods.2022094

https://www.biodiversity-science.net/CN/Y2023/V31/I1/22094

图/表 8

参考文献 26

[1]	Chen H (2010) A GIS-based Multi-Scale Approach to Ecogeographical Invasive Species Modeling. PhD dissertation, Wuhan University, Wuhan. (in Chinese with English abstract)
	[陈浩 (2010) 基于GIS的多尺度生态地理物种入侵预测建模. 博士学位论文, 武汉大学, 武汉.]
[2]	Chen JJ, Wang J (2018) Progress in prevention and control of invasive species in China. Journal of Biosafety, 27(1), 16-19. (in Chinese with English abstract)
	[陈洁君, 王晶 (2018) 我国外来入侵生物防控科技进展. 生物安全学报, 27(1), 16-19.]
[3]	Dong HZ, Wang LH, Tang W, Yang Q, She YN (2021) Research on PCA-PSO-SVM ozone prediction considering spatial temporal features. China Environmental Science, 41, 596-605. (in Chinese with English abstract)
	[董红召, 王乐恒, 唐伟, 杨强, 佘翊妮 (2021) 融合时空特征的PCA-PSO-SVM臭氧(O₃)预测方法研究. 中国环境科学, 41, 596-605.]
[4]	Duan RY, Kong XQ, Huang MY, Wu GL, Wang ZG (2015) SDMvspecies: A software for creating virtual species for species distribution modelling. Ecography, 38, 108-110. DOI URL
[5]	Guisan A, Tingley R, Baumgartner JB, Naujokaitis-Lewis I, Sutcliffe PR, Tulloch AIT, Regan TJ, Brotons L, Mcdonald-Madden E, Mantyka-Pringle C, Martin TG, Rhodes JR, Maggini R, Setterfield SA, Elith J, Schwartz MW, Wintle BA, Broennimann O, Austin M, Ferrier S, Kearney MR, Possingham HP, Buckley YM (2013) Predicting species distributions for conservation decisions. Ecology Letters, 16, 1424-1435. DOI PMID
[6]	Guo H, Wang T, Louie PKK (2004) Source apportionment of ambient non-methane hydrocarbons in Hong Kong: Application of a principal component analysis/absolute principal component scores (PCA/APCS) receptor model. Environmental Pollution, 129, 489-498. PMID
[7]	Hu KX (2021) Interpretation of high frequency words in Biosafety Law of the People’s Republic of China. Port Health Control, 26(1), 29-31, 49. (in Chinese with English abstract)
	[胡孔新 (2021) 《中华人民共和国生物安全法》高频关键词解读. 口岸卫生与控制, 26(1), 29-31, 49.]
[8]	Iturbide M, Bedia J, Herrera S, Hierro O, Pinto M, Gutierrez JM (2015) A framework for species distribution modelling with improved pseudo-absence generation. Ecological Modelling, 312, 166-174. DOI URL
[9]	Jiménez-Valverde A, Lobo JM (2007) Threshold criteria for conversion of probability of species presence to either-or presence-absence. Acta Oecologica, 31, 361-369. DOI URL
[10]	Liu JY, Xu G, Yin LZ, Xu X, Armitage DW, Dong T (2020) Invasive plants exert disproportionately negative allelopathic effects on the growth and physiology of the earthworm Eisenia fetida. Science of the Total Environment, 747, 141534.
[11]	Liu TT, Zhang HJ, Wang XL, Wu L (2010) Influence of alien invasive species Erigeron annuus on biodiversity in region of Wuling Mountain. Acta Scientiarum Naturalium Universitatis Pekinensis, 46, 365-370. (in Chinese with English abstract)
	[刘婷婷, 张洪军, 王晓磊, 吴琳 (2010) 外来植物一年蓬对雾灵山生物多样性的影响. 北京大学学报(自然科学版), 46, 365-370.]
[12]	Liu XT, Yuan Q, Ni J (2019) Research advances in modelling plant species distribution in China. Chinese Journal of Plant Ecology, 43, 273-283. (in Chinese with English abstract) DOI URL
	[刘晓彤, 袁泉, 倪健 (2019) 中国植物分布模拟研究现状. 植物生态学报, 43, 273-283.] DOI
[13]	Ma QQ, Liu T, Dong HG, Wang HY, Zhao WX, Wang RL, Liu Y, Chen L (2020) Potential geographical distribution of Ambrosia trifida in Xinjiang under climate change. Acta Prataculturae Sinica, 29(12), 73-85. (in Chinese with English abstract)
	[马倩倩, 刘彤, 董合干, 王寒月, 赵文轩, 王瑞丽, 刘延, 陈乐 (2020) 气候变化下三裂叶豚草在新疆的潜在地理分布. 草业学报, 29(12), 73-85.]
[14]	Ma SM, Zhang ML, Zhang HX, Meng HH, Chen X (2010) Predicting potential geographical distributions and patterns of the relic plant Gymnocarpos przewalskii using maximum entropy and genetic algorithm for rule-set prediction. Chinese Journal of Plant Ecology, 34, 1327-1335. (in Chinese with English abstract)
	[马松梅, 张明理, 张宏祥, 孟宏虎, 陈曦 (2010) 利用最大熵模型和规则集遗传算法模型预测孑遗植物裸果木的潜在地理分布及格局. 植物生态学报, 34, 1327-1335.] DOI
[15]	Merow C, Smith MJ, Silander JA (2013) A practical guide to MaxEnt for modeling species’ distributions: What it does, and why inputs and settings matter. Ecography, 36, 1058-1069. DOI URL
[16]	Meynard CN, Kaplan DM (2013) Using virtual species to study species distributions and model performance. Journal of Biogeography, 40, 1-8. DOI URL
[17]	Miao YM, Zhu AX, Yang L, Bai SB, Liu JZ (2016) A method for quantifying the reliability of landslide pseudo absence samples based on geographic environmental similarity. Progress in Geography, 35, 860-869. (in Chinese with English abstract)
	[缪亚敏, 朱阿兴, 杨琳, 白世彪, 刘军志 (2016) 一种基于地理环境相似度的滑坡负样本可信度度量方法. 地理科学进展, 35, 860-869.] DOI
[18]	Olaiya A (2016) Transforming our world: The 2030 agenda for sustainable development. Civil Engineering, 24, 26-30.
[19]	Pouteau R, Meyer JY, Stoll B (2011) A SVM-based model for predicting distribution of the invasive tree Miconia calvescens in tropical rainforests. Ecological Modelling, 222, 2631-2641. DOI URL
[20]	Schӧlkopf B, Williamson R, Smola A, Shawe-Taylor J, Platt J (2000) Support vector method for novelty detection. In: Advances in Neural Information Processing Systems (eds Solla SA, Leen TK, Müller KR), pp. 582-588. MIT Press, Cambridge.
[21]	Yang WT, Deng M, Xu F, Wang H (2018) Prediction of hourly PM2.5 using a space-time support vector regression model. Atmospheric Environment, 181, 12-19 DOI URL
[22]	Yang WT, He HX, Wei DS, Chen H (2022) Generating pseudo-absence samples of invasive species based on outlier detection in the geographical characteristic space. Journal of Geographical Systems, 24, 261-279. DOI URL
[23]	Zhang YB, Liu YL, Zhang XL, Qin H, Wang GY, Wang W (2020) Impacts of climate change on the suitable habitats and spatial migration of Xanthoceras sorbifolia. China Environmental Science, 40, 4957-4606. (in Chinese with English abstract)
	[张殷波, 刘彦岚, 张晓龙, 秦浩, 王光玉, 王伟 (2020) 气候变化对文冠果适宜生境及空间迁移的影响. 中国环境科学, 40, 4957-4606.]
[24]	Zhao CY, Liu XY, Li FF, Zhu JF, Guo CD, Li JS (2022) The distribution pattern and determinant factors of the main invasive alien plants in national nature reserves in China. Acta Ecologica Sinica, 42, 2532-2541. (in Chinese with English abstract)
	[赵彩云, 柳晓燕, 李飞飞, 朱金方, 郭朝丹, 李俊生 (2022) 我国国家自然保护区主要外来入侵植物分布格局及成因. 生态学报, 42, 2532-2541.]
[25]	Zhu GP, Liu GQ, Bu WJ, Gao YB (2013) Ecological niche modeling and its application in biodiversity conservation. Biodiversity Science, 21, 90-98. (in Chinese with English abstract) DOI URL
	[朱耿平, 刘国卿, 卜文俊, 高玉葆 (2013) 生态位模型的基本原理及其在生物多样性保护中的应用. 生物多样性, 21, 90-98.] DOI
[26]	Zhu GP, Qiao HJ (2016) Effect of the MaxEnt model’s complexity on the prediction of species potential distributions. Biodiversity Science, 24, 1189-1196. (in Chinese with English abstract) DOI URL
	[朱耿平, 乔慧捷 (2016) Maxent模型复杂度对物种潜在分布区预测的影响. 生物多样性, 24, 1189-1196.] DOI

气候变量 Climatic variables	均方误差 Mean squared error (MSE)	标准误差 Standard error (SE)	相对误差 Relative error (RE) (%)
年平均温度 Mean annual temperature (X₁)	1.052	1.083	5.674
暖季平均温度 Mean temperature in warm season (X₂)	1.204	1.258	3.570
冷季平均温度 Mean temperature in cold season (X₃)	0.991	0.976	2.144
最干月平均温度 Mean temperature in the driest month (X₄)	6.982	6.664	6.868
最湿月平均温度 Mean temperature in the wettest month (X₅)	2.918	2.933	9.251
暖季平均相对湿度 Relative humidity in warm season (X₆)	0.026	0.027	2.437
冷季平均相对湿度 Relative humidity in cold season (X₇)	0.033	0.032	3.864
最干月相对湿度 Relative humidity in the driest month (X₈)	0.032	0.029	3.928
最湿月相对湿度 Relative humidity in the wettest month (X₉)	0.025	0.025	5.361

气候变量 Climatic variables	均方误差 Mean squared error (MSE)	标准误差 Standard error (SE)	相对误差 Relative error (RE) (%)
年平均温度 Mean annual temperature (X₁)	1.052	1.083	5.674
暖季平均温度 Mean temperature in warm season (X₂)	1.204	1.258	3.570
冷季平均温度 Mean temperature in cold season (X₃)	0.991	0.976	2.144
最干月平均温度 Mean temperature in the driest month (X₄)	6.982	6.664	6.868
最湿月平均温度 Mean temperature in the wettest month (X₅)	2.918	2.933	9.251
暖季平均相对湿度 Relative humidity in warm season (X₆)	0.026	0.027	2.437
冷季平均相对湿度 Relative humidity in cold season (X₇)	0.033	0.032	3.864
最干月相对湿度 Relative humidity in the driest month (X₈)	0.032	0.029	3.928
最湿月相对湿度 Relative humidity in the wettest month (X₉)	0.025	0.025	5.361

采样方法 Sampling method	Logistic回归 Logistic regression			支持向量机 Support vector machine (SVM)
采样方法 Sampling method	Kappa	AUC	总体准确率 Accuracy	Kappa	AUC	总体准确率 Accuracy
空间随机采样 Random sampling	0.487	0.692	67.6%	0.514	0.723	69.3%
单类支持向量机 One-class SVM (OCSVM)	0.642	0.867	84.5%	0.678	0.879	86.7%
本文方法 This paper	0.784	0.911	88.1%	0.801	0.936	89.8%

采样方法 Sampling method	Logistic回归 Logistic regression			支持向量机 Support vector machine (SVM)
采样方法 Sampling method	Kappa	AUC	总体准确率 Accuracy	Kappa	AUC	总体准确率 Accuracy
空间随机采样 Random sampling	0.487	0.692	67.6%	0.514	0.723	69.3%
单类支持向量机 One-class SVM (OCSVM)	0.642	0.867	84.5%	0.678	0.879	86.7%
本文方法 This paper	0.784	0.911	88.1%	0.801	0.936	89.8%

基于地理环境相似度的长江经济带入侵物种虚拟负样本生成方法

Generating pseudo-absence samples of invasive species based on the similarity of geographical environment in the Yangtze River Economic Belt

RichHTML

PDF (PC)

补充材料

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 26

相关文章 9

编辑推荐

Metrics

本文评价

[1]	耿宜佳, 田瑜, 李俊生, 李子圆, 潘玉雪. 《生物多样性公约》框架下外来入侵物种管控的全球进展、挑战和展望[J]. 生物多样性, 2024, 32(11): 24275-.
[2]	陈敏豪, 张超, 王嘉栋, 湛振杰, 陈君帜, 栾晓峰. 北美水貂和欧亚水獭在东北地区的分布与生态位重叠[J]. 生物多样性, 2023, 31(1): 22289-.
[3]	李萌, 尉婷婷, 史博洋, 郝希阳, 徐海根, 孙红英. 环境DNA技术在淡水底栖大型无脊椎动物多样性监测中的应用[J]. 生物多样性, 2019, 27(5): 480-490.
[4]	王乐, 时晨, 田金炎, 宋晓楠, 贾明明, 李小娟, 刘晓萌, 钟若飞, 殷大萌, 杨杉杉, 郭先仙. 基于多源遥感的红树林监测[J]. 生物多样性, 2018, 26(8): 838-849.
[5]	肖兰, 张琳婷, 杨盛昌, 郑志翰, 姜德刚. 厦门近岸海域无居民海岛植物区系和物种组成相似性[J]. 生物多样性, 2018, 26(11): 1212-1222.
[6]	许玥, 李鹏, 刘晔, 张婉君, 秦思雨, 沈泽昊. 怒江河谷入侵植物与乡土植物丰富度的分布格局与影响因子[J]. 生物多样性, 2016, 24(4): 389-398.
[7]	刘金燕, 张桂芬, 万方浩, 王进军. 烟粉虱种内及种间竞争取代机制[J]. 生物多样性, 2008, 16(3): 214-224.
[8]	戴强, 戴建洪, 李成, 刘志君, 王跃招. 仙姑弹琴蛙蝌蚪对陌生捕食者克氏原螯虾的反捕反应[J]. 生物多样性, 2004, 12(5): 481-487.
[9]	陈良燕, 徐海根. 澳大利亚外来入侵物种管理策略及对我国的借鉴意义[J]. 生物多样性, 2001, 09(4): 466-471.