人工红松松籽和松仁的产量模型  

Modelling the production of pine seeds and nuts in Pinus koraiensis plantation

作　　者：李玉萌 贾炜玮[1] 郭昊天 LI Yumeng;JIA Weiwei;GUO Haotian(College of Forest,Northeast Forestry University/Key Laboratory of Sustainable Management of Forest Ecosystem,Ministry of Education,Harbin 150040,China)

机构地区：[1]东北林业大学林学院/森林生态系统可持续经营教育部重点实验室,哈尔滨150040

出　　处：《应用生态学报》2025年第1期95-103,共9页Chinese Journal of Applied Ecology

基　　金：国家自然科学基金区域创新发展联合基金重点项目(U21A20244);黑龙江省林口林业局有限责任公司全国森林经营试点及碳汇试点科技支撑项目(HFW240100013)资助。

摘　　要：以黑龙江省林口林业局红松人工林木的松塔为研究对象,获取果实和林木因子实测数据,将红松松塔根据鲜重分为3个等级,对松塔、松籽、松仁性状进行相关性分析,构建松籽重量、松仁数量、松仁重量的基础模型,在基础模型中引入松塔等级和样地随机效应,通过比较赤池信息准则(AIC)和贝叶斯信息准则(BIC)等评价指标选取最优混合效应模型。结果表明:红松的松籽重量和松仁重量与空瘪数、松塔下直径呈极显著负相关,与其他性状呈极显著正相关。引入松塔等级和样地随机效应构建的混合效应模型均比基础模型拟合效果好,其中,在最优基础模型中引入样地效应的混合效应模型均比引入松塔等级效应的混合效应模型拟合效果更优。引入样地效应的松籽重量、松仁数量、松仁重量最优混合效应模型的R~2相比于最优基础模型分别提高了20.8%、29.5%、32.8%。松籽重量、松仁数量、松仁重量最优混合效应模型精度F_P分别为98.3%、97.9%、97.8%,结果均大于最优基础模型的预估精度,说明混合效应模型能够对红松的结实量进行较好的预测。We collected data on fruit and tree factors in Pinus koraiensis plantations in the Linkou Forestry Bureau of Heilongjiang Province.Pine cones were divided into three grades based on fresh weight.We analyzed the correla⁃tions between pine cones,pine seeds,and pine nuts,and constructed the foundational models for pine seed weight,pine nut quantity,and pine nut weight.Then,we introduced the effects of cone grade and random effects of sampling sites into the foundational models,and selected the optimal mixed⁃effects model by comparing the Akaike Information Criterion(AIC)and the Bayesian Information Criterion(BIC).The results showed that the weights of pine seeds and nuts were significantly negatively correlated with the number of empty seeds and the diameter at the base of pine cones,and were significantly positively correlated with other traits.The mixed⁃effects models that intro⁃duced cone grade and random effects of sampling sites had better fitness than the foundational models.Among them,the mixed⁃effects model that included the site effect in the optimal foundational model showed better fitness than the model that included the cone grade effect.Compared to the optimal foundational models,the R2 values of the optimal mixed⁃effects models for pine seed weight,pine nut quantity,and pine nut weight with the inclusion of the site effects was improved by 20.8%,29.5%,and 32.8%,respectively.The optimal mixed⁃effects models for pine seed weight,pine nut quantity,and pine nut weight had prediction accuracies(FP)of 98.3%,97.9%,and 97.8%,respectively.All those values surpassed the predictive accuracy of the optimal foundational model.Our re⁃sults indicated that the mixed⁃effects models could better predict seed yield of P.koraiensis.

关 键 词：红松 松籽重量 松仁数量 松仁重量 线性混合模型 

分 类 号：S791.247[农业科学—林木遗传育种]