青海湖北岸天然牧草产量预测模型研究  

Study on Predicting Models of Grass Yield in North Shore of Qinghai Lake

作　　者：朱生翠 李国婷 魏永林 马扶林 金显玲 曹迎敏 ZHU Shengcui;LI Guoting;WEI Yonglin;MA Fulin;JIN Xianling;CAO Yingmin(China Global Atmosphere Watch Baseline Observatory,Xining 810001;Greenhouse Gas and Carbon Neutral Key Laboratory of Qinghai Province,Xining 810001;Qinghai Meteorological Information Center,Xining 810001;Haibei Pastoral Meteorology Experimental Station of Qinghai Province,Haibei,Qinghai 810200)

机构地区：[1]中国大气本底基准观象台,西宁810001 [2]青海省温室气体及碳中和重点实验室,西宁810001 [3]青海省气象信息中心,西宁810001 [4]青海省海北牧业气象试验站,青海海北810200

出　　处：《中国农学通报》2023年第25期109-115,共7页Chinese Agricultural Science Bulletin

基　　金：2021年国家自然基金-地区基金“青藏高原东北部植物物候变化及区域分异”(4216050067);第二次青藏高原综合科学考察研究“青海省气象格点数据及产品地面验证”(2019QZKK020615)。

摘　　要：研究旨在实现牧草产量动态预测,及时掌握牧草产量变化,为高寒地区牧业生产效率及结构调整提供科学依据。以青海湖北岸为研究区域,利用2003—2020年生长季牧草产量观测资料、归一化植被指数(normalized difference vegetation index,NDVI)和气象条件因子,结合放牧与围封2种草地利用方式,建立适用于青海湖北岸地区不同草地类型(高寒草甸类、高寒草原类、温性草原类)的牧草产量气象估算模型。结果表明,3种不同草地类型中高寒草甸的预测效果最好。实测牧草产量与气象要素的回归效果优于NDVI与气象要素的回归效果,海晏县地面产量与气象要素回归相关系数均达0.8以上,通过了0.001的极显著性检验。验证和筛选出海晏5个、祁连4个、央隆2个、刚察2个预测精度较高的模型,具有良好的估测能力,可以满足这4个地区围栏内或围栏外的牧草产量预测应用需要。The objective is to realize the dynamic prediction of grass yield,grasp the change of grass yield in time,and provide scientific basis for animal husbandry production efficiency and structural adjustment in alpine region.Taking the north bank of Qinghai Lake as the research area,the grass yield prediction models for different grassland types(alpine meadow,alpine steppe and temperate steppe)were established by grass yield data,meteorological data and NDVI data from 2003 to 2020.The effect of fencing and grazing on the grass yield prediction models were analyzed.The results showed that alpine meadow had the best prediction effect among the three different grassland types.The regression effect between grass yield data and meteorological elements was better than that between NDVI and meteorological elements.The regression correlation coefficients between grass yield data and meteorological data in Haiyan were above 0.8,which passed the significant test of 0.001.Five models of Haiyan,four models of Qilian,two models of Yanglong and two models of Gangcha were screened with high prediction accuracy,which had good estimation ability and could meet the needs of grass yield prediction application in or outside the fence in these four areas.

关 键 词：青海湖北岸 草地 牧草产量 归一化植被指数 预测模型 

分 类 号：S812.1[农业科学—草业科学]