基于WOFOST模型的柑橘智能种植服务平台构建与应用  

Construction and application of citrus intelligent planting service platform based on WOFOST model

作　　者：程杨[1] 唐谦 马强[1] 刁源[1] 周广文[1] 武峥[1] 游双艳 唐维超[1] 杨会静[1] 罗清平[1] CHENG Yang;TANG Qian;MA Qiang;DIAO Yuan;ZHOU Guangwen;WU Zheng;YOU Shuangyan;TANGWeichao;YANG Huijing;LUO Qingping(Chongqing Academy of Agricultural Sciences,Chongqing 401329,China;Chongqing Industry Polytechnic College,Chongqing 404000,China)

机构地区：[1]重庆市农业科学院,重庆401329 [2]重庆工业职业技术学院,重庆404000

出　　处：《果树学报》2021年第12期2209-2222,共14页Journal of Fruit Science

基　　金：重庆市技术创新与应用发展专项面上项目(cstc2019jscx-msxmX0361);重庆市农业科学院市级农发资金项目(NKY-2020AB013)。

摘　　要：【目的】提升重庆市柑橘种植智能化管理水平,探索构建基于WOFOST模型的柑橘智能种植服务平台(CIPSP),用于辅助橘农进行柑橘智能种植和经营管理决策。【方法】以柑橘新品种沃柑为试验材料,以物理服务器等5部分系统级软件为技术支撑,以WOFOST模型为基础构建CIPSP系统模型知识库,应用LH-OAT方法对模型中模型参数进行敏感性分析并确定CIPSP系统模型参数,设计自适应算法引擎对CIPSP系统模型参数进行精度预测和校正。根据需要设计CIPSP系统结构和智能种植功能,并在重庆市长寿区龙河镇河堰村选取3处不同生长年限(2~3 a、3~4 a、5 a以上)沃柑试验田场景的15个测算点,对系统产量预测模拟、土壤墒情/土质及气象实时监测、智能虫情测报等部分功能进行验证应用。【结果】通过分别设计相关参数,构建基于柑橘生长周期WOFOST建模思路的CIPSP系统模型知识库;对CIPSP系统分析后快速确定敏感性较高模型参数I;在实时观测数据基础上对作物生长进行模拟预测比对,引入自适应算法进行了模型修正。将CIPSP系统设计成感知层、边缘层、基础设施层、平台层和操作层等5层相互独立的结构,实现CIPSP系统对柑橘种植过程中产量预测模拟、土壤墒情/土质及气象实时监测、智能虫情测报等功能。初步验证表明,WOFOST模型能较好地模拟预测树龄不大于3 a的沃柑植株产量,但随着树龄增长,实测值与预测值偏差逐渐变大;通过实时监测数据信息与作物生长模型相结合,实现对采集分析土壤墒情/土质及气象实时环境数据(土壤肥力、光照度、降雨量等)监测分析应用;应用智能虫情监测系统与遥感技术及高光谱无人机相结合,实现现场/远程对基于机器深度学习的常见病虫害发生进行检测、判别、预警、防控等功能。【结论】构建了基于WOFOST模型的CIPSP系统,并成功应用于沃柑试验田产�【Objective】Chongqing is one of the dominant regions of citrus planting and one of the three late-maturing citrus producing areas in China.By the end of 2018,the citrus planting area in Chongqing was about 231700 hm2,the output was over 3.2 million tons,and the total output value was nearly 30 billion yuan.However,the citrus planting management mode in Chongqing is still traditional and extensive.WOFOST model is a common crop growth model,which is often used to predict crop yield and analyse the impact of different crop varieties,climate change,growth period changes and irrigation conditions on crop yield.It can provide theoretical basis for standardized,accurate and intelligent crop production management.In order to improve the intelligent management level of the whole process of citrus planting in Chongqing,this paper explores the construction of the citrus intelligent planting service platform(CIPSP)based on the WOFOST(World Food Studies)model,which is used to assist orange growers to make intelligent planting and management decisions,so as to improve the comprehensive economic benefits of citrus planting.【Methods】In this paper,a new citrus variety Orah Mandarin(Temple Tengor×Dancy Tangerine)served as the experimental material,and the CIPSP system based on WOFOST model was designed and validated with five parts of system level software,including physical server and virtual server operating system,virtualization software,open platform,large database and cloud platform management software.By referring to the methods introduced by Wan Qiuping,Dou Lifang,Bai Qinfeng and Zhou long,the CIPSP system model knowledge base derived from WOFOST modeling idea was constructed;referring to Zhu Jiaqi’s method,the sensitivity analysis of the model parameters was carried out by using the LH-OAT method to determine the CIPSP system model parameters;referring to the Jiang Haiyan’s method,an adaptive algorithm engine was designed to predict and correct the model parameters of CIPSP system.According to the needs of citr

关 键 词：柑橘 智能种植 WOFOST模型 CIPSP系统 技术创新 

分 类 号：S666[农业科学—果树学]