摘要
准确估算作物系数(K_(c))对于计算作物蒸发蒸腾量(ET_(c)),实现精确有效的用水管理至关重要。为了及时掌握K_(c)的连续动态变化,进一步估算作物需水量来指导作物灌溉,采用超绿算法和最大类间方差法进行图像分割来提取生菜冠层覆盖度(PGC),并提出了基于贝叶斯优化XGBoost(Bayesian-XGBoost)的生菜K_(c)估算模型,为指导作物科学合理灌溉提供新途径。结果表明,全生育期内PGC呈先快速增长后趋于稳定的生长趋势,变化范围为10.38%~81.00%,日均增幅为1.56%,可有效反映K_(c)的变化趋势。以PGC作为输入所构建的Bayesian-XGBoost生菜K_(c)估算模型在迭代400次时达到最优估算效果,生菜幼苗期、莲座期、结球期的K_(c)分别为1.12、1.29和2.26,与实测值相比平均误差为2.13%。此外,进一步利用Penman-Monteith公式(PM公式)结合K_(c)估算模型实现了对生菜ET_(c)的实时计算,得到了秋茬种植期的生菜日均ET_(c)为2.38 mm/d。基于Bayesian-XGBoost的生菜K_(c)估算模型能够较好估算生菜K_(c)和作物需水量。
Accurate estimation of crop coefficient(K_(c))is crucial for calculating crop evapotranspiration(ET_(c)),and achieving accurate and effective water management.In order to grasp the continuous dynamic change of K_(c) in time and further estimate the crop water requirement to guide crop irrigation,in this paper,the super-green algorithm and maximum interclass variance method was adopted for image segmentation to extract the lettuce canopy coverage(PGC),and a lettuce K_(c) estimation model based on Bayesian optimization XGBoost(Bayesian-XGBoost)was proposed.It provided a new way to guide scientific and rational irrigation for crops.The experimental results showed that:PGC showed a rapid growth trend at first and then tended to be stable during the whole growth period,with a range of 10.38%-81.00%and an average daily increase rate of PGC of 1.56%,which could effectively reflect the change trend of K_(c).The Bayesian XGBoost lettuce K_(c) estimation model constructed with PGC as input achieved the optimal estimation effect when iterating for 400 times.K_(c) of lettuce at seedling stage,rosette stage,and heading stage was 1.12,1.29,and 2.26,respectively,with an average error of 2.13%compared with the measured true value.In addition,penman-monteith formula(PM)was further used with K_(c) estimation model to realize the real-time calculation of lettuce ET_(c).The average daily ET_(c) of lettuce in the autumn cropping period was 2.38 mm/d.The lettuce K_(c) estimation model based on Bayesian XGBoost could better estimate lettuce K_(c) and crop water requirement.
作者
高海荣
张钟莉莉
岳焕芳
张馨
郭瑞
李志伟
GAO Hairong;ZHANG Zhonglili;YUE Huanfang;ZHANG Xin;GUO Rui;LI Zhiwei(College of Agricultural Engineering,Shanxi Agricultural University,Taigu 030801,China;Intelligent Equipment Technology Research Center,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China;Key Laboratory of Software and Hardware Quality Testing for Agricultural Information Products,Ministry of Agriculture and Rural Affairs,Beijing 100097,China;Beijing Agricultural Technology Extension Station,Beijing 100029,China;Information Technology Research Center,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China)
出处
《山西农业科学》
2022年第10期1482-1488,共7页
Journal of Shanxi Agricultural Sciences
基金
河北省重点研发计划(21327410D)
北京市农林科学院创新能力建设项目(KJCX20210402,KJCX20200430)。
关键词
盆栽生菜
作物系数
图像处理
贝叶斯优化
机器学习
作物蒸发蒸腾量
potted lettuce
crop coefficient
image processing
Bayesian optimization
machine learning
crop evapotranspi‐ration
