基于随机森林和最大熵模型的云南省钉螺潜在地理分布预测  

Prediction of potential geographic distribution of Oncomelania hupensis in Yunnan Province using random forest and maximum entropy models

作　　者：张宗亚 杜春红[1] 张云[1] 王洪琼 宋静[1] 周济华[1] 王丽芳[1] 孙佳昱[1] 沈美芬[1] 陈春琼 江华[1] 颜嘉琦 冯锡光[1] 王文雅 钱沛君 薛靖波 李石柱 董毅[1] ZHANG Zongya;DU Chunhong;ZHANG Yun;WANG Hongqiong;SONG Jing;ZHOU Jihua;WANG Lifang;SUN Jiayu;SHEN Meifen;CHEN Chunqiong;JIANG Hua;YAN Jiaqi;FENG Xiguang;WANG Wenya;QIAN Peijun;XUE Jingbo;LI Shizhu;DONG Yi(Yunnan Institute of Endemic Diseases Control and Prevention,Yunnan Provincial Key Laboratory for Zoonosis Control and Prevention,Dali,Yunnan 671000,China;National Institute of Parasitic Diseases,Chinese Center for Disease Control and Prevention(Chinese Center for Tropical Diseases Research),National Health Commission Key Laboratory of Parasite and Vector Biology,Shanghai 200025,China)

机构地区：[1]云南省地方病防治所、云南省自然疫源性疾病防控技术重点实验室,云南大理671000 [2]中国疾病预防控制中心寄生虫病预防控制所(国家热带病研究中心)、国家卫生健康委员会寄生虫病原与媒介生物学重点实验室,上海200025

出　　处：《中国血吸虫病防治杂志》2024年第6期562-571,613,共11页Chinese Journal of Schistosomiasis Control

基　　金：国家重点研发计划(2021YFC2300800,2021YFC2300804);国家自然科学基金(32161143036,32311540013);云南省地方病防治所青年科技人才培养项目(YIEDC-T202104)。

摘　　要：目的采用随机森林(random forest,RF)模型与最大熵(maximum entropy,MaxEnt)模型预测云南省钉螺潜在分布区,为云南省钉螺监测和控制提供参考。方法收集2015—2016年云南省钉螺调查数据并转换为钉螺存在点数据;收集云南省22个环境变量数据,包括年蒸发量、年平均地温、年降水量、年平均气压、年平均相对湿度、年日照时数、年平均气温、年平均风速、≥0℃积温、≥10℃积温、干燥度、湿润指数等12个气候变量,归一化植被指数、地貌类型、土地利用类型、海拔高度、土壤类型、土壤质地-黏土含量、土壤质地-沙土含量、土壤质地-粉砂土含量等8个地理变量及国内生产总值、人口分布2个人口经济学变量。经Pearson相关性检验和方差膨胀因子(variance inflation factor,VIF)检验筛选后,基于R 4.2.1软件biomod2包构建RF、MaxEnt模型及其组合模型,预测2016年后云南省钉螺潜在分布区。采用交叉验证和独立数据验证法,计算受试者工作特征(receiver operator characteristic,ROC)曲线下面积(area under curve,AUC)、真实技巧统计值(true skill statistics,TSS)和Kappa统计量以评价模型预测性能;选择AUC>0.950且TSS>0.850的模型输出的环境变量贡献值进行归一化处理,获得环境变量重要性百分比以分析环境变量重要性。结果累计将148个钉螺存在点数据和15个环境变量纳入RF、MaxEnt模型进行训练,RF与MaxEnt模型预测性能均较佳,AUC均值>0.900、TSS和Kappa均值均>0.800,且两模型AUC(t=19.862,P<0.05)、TSS(t=10.140,P<0.05)和Kappa值(t=10.237,P<0.05)差异均有统计学意义;组合模型AUC、TSS和Kappa值分别为0.996、0.954和0.920。独立数据验证发现,RF模型和组合模型建模结果的AUC、TSS和Kappa值均为1,在未知数据建模中表现良好;MaxEnt模型则表现较弱,24%(24/100)的建模结果TSS、Kappa值为0。累计有79个RF模型建模结果和38个MaxEnt模型建模结果及组合模型建模结Objective To predict the potential geographic distribution of Oncomelania hupensis in Yunnan Province using random forest(RF)and maximum entropy(MaxEnt)models,so as to provide insights into O.hupensis surveillance and control in Yunnan Province.Methods The O.hupensis snail survey data in Yunnan Province from 2015 to 2016 were collected and converted into O.hupensis snail distribution site data.Data of 22 environmental variables in Yunnan Province were collected,including twelve climate variables(annual potential evapotranspiration,annual mean ground surface temperature,annual precipitation,annual mean air pressure,annual mean relative humidity,annual sunshine duration,annual mean air temperature,annual mean wind speed,≥0℃annual accumulated temperature,≥10℃annual accumulated temperature,aridity and index of moisture),eight geographical variables(normalized difference vegetation index,landform type,land use type,altitude,soil type,soil textureclay content,soil texture⁃sand content and soil texture⁃silt content)and two population and economic variables(gross domestic product and population).Variables were screened with Pearson correlation test and variance inflation factor(VIF)test.The RF and MaxEnt models and the ensemble model were created using the biomod2 package of the software R 4.2.1,and the potential distribution of O.hupensis snails after 2016 was predicted in Yunnan Province.The predictive effects of models were evaluated through cross⁃validation and independent tests,and the area under the receiver operating characteristic curve(AUC),true skill statistics(TSS)and Kappa statistics were used for model evaluation.In addition,the importance of environmental variables was analyzed,the contribution of environmental variables output by the models with AUC values of>0.950 and TSS values of>0.850 were selected for normalization processing,and the importance percentage of environmental variables was obtained to analyze the importance of environmental variables.Results Data of 148 O.hupensis snail dist

关 键 词：湖北钉螺 随机森林模型 最大熵模型 地理分布 预测性能 云南省 

分 类 号：R383.24[医药卫生—医学寄生虫学]