摘要
基于机器学习算法的天气指数保险是农业保险创新研究的有益尝试。农作物产量受气象灾害影响严重,构建能准确反映产量损失与气象灾害关系的数据分析模型,对农作物天气指数保险的定价十分重要。本文以甘肃庆阳苹果为研究对象,基于1996-2020年庆阳市5个县(区)苹果生长期(4-10月)逐日降水量、逐日气温数据以及苹果产量数据,构建低温冻害指数、干旱指数和连阴雨指数,利用XGBoost算法建立与苹果气象减产率的回归模型,结合核函数密度估计法厘定庆阳市苹果天气指数保险纯费率。结果表明:(1)庆阳市各县(区)苹果气象减产率受气象灾害影响波动明显,7种苹果灾害天气指数与苹果气象减产率存在非线性关系;(2)基于XGBoost算法建立1996-2020年宁县、庆城县、正宁县、环县和西峰区苹果气象减产率-天气指数回归模型,其拟合精准度高于多元逐步回归模型,决定系数R2分别高出0.157、0.125、0.190、0.115和0.117,均方根误差RMSE分别降低0.045、0.026、0.335、0.126和0.039个百分点;(3)宁县、庆城县、正宁县、环县和西峰区的苹果天气指数保险的气象减产率赔付触发值分别为11.88%、3.37%、4.33%、9.21%和17.70%,苹果天气指数保险纯费率分别为4.00%、3.64%、4.91%、1.94%和4.98%。
Weather index insurance based on machine learning algorithms represents a significant innovation in agricultural insurance research.Since crop yields are primarily influenced by weather-related disasters,developing a robust data analysis model that accurately captures the relationship between yield losses and adverse weather conditions is crucial for pricing crop weather index insurance.This paper focuses on Qingyang apples in Gansu province,utilizing daily precipitation and temperature data during the growing season(April-October)and apple yield data from five counties(or districts)in Qingyang city spanning 1996–2020.Indices of low-temperature freezing,drought and continuous cloudy rainfall were constructed,and a regression model linking these indices to the meteorological yield reduction rate of apples was established using the XGBoost algorithm.The kernel density estimation method was applied to determine the pure rate of weather index insurance for apples in Qingyang.The findings of the study were as follows:(1)meteorological disasters caused significant fluctuations in the apple cimate yield reduction rates across counties(or districts)in Qingyang city.A nonlinear relationship was observed between the cimate yield reduction rate and seven types of apple disaster weather indices.(2)Regression models for the climate yield reduction rate-weather indices in Ning county,Qingcheng county,Zhengning county,Huan county,and Xifeng district(1996–2020)were constructed using the XGBoost algorithm.These models demonstrated superior fitting accuracy compared to multivariate stepwise regression models,with coefficients of determination(R²)improving by 0.157,0.125,0.190,0.115 and 0.117,uhile root mean square errors(RMSE)decreasing by 0.045,0.026,0.335,0.126,and 0.039 percentage points,respectively.(3)The climate yield reduction rate payout triggers for apple weather index insurance were 11.88%,3.37%,4.33%,9.21%,and 17.70%in Ning county,Qingcheng county,Zhengning county,Huan county,and Xifeng district,respectively.The corresponding pure insurance rates were 4.00%,3.64%,4.91%,1.94%and 4.98%.
作者
李金蓉
肖鸿民
LI Jin-rong;XIAO Hong-min(Northwest Normal University,College of Mathematics and Statistics,Lanzhou 730070,China)
出处
《中国农业气象》
2025年第5期715-724,共10页
Chinese Journal of Agrometeorology
基金
国家自然科学基金项目(12061066)。
作者简介
通讯作者:肖鸿民,教授,主要研究方向为保险精算、金融统计及风险管理,E-mail:xiaohm@nwnu.edu.cn;第一作者:李金蓉,E-mail:ljrnwnu@163.com。
