基于物联网的土壤墒情监测系统与预测模型的研究

发布时间：2018-04-08 07:16

本文选题：土壤墒情　切入点：墒情监测系统　出处：《吉林农业大学》2017年硕士论文

【摘要】：我国领土幅员辽阔,人口众多。各地区有限的农业生产原料,人均占有的农业资源不充沛和分配不均等等现象。各种情况的存在,都表明农业是决定国民经济快速发展的主要因素之一。玉米是我国主要粮食作物,也是中国东北地区的主要作物。农作物在生长发育期间,由于降雨量较低以及水资源匮乏,导致土壤含水量较低,在农作物生长的一定时期内所需水量不足,影响了农作物的生长,它也对人们的生产生活产生了一定的影响。农业的一个发展方向就是建立一个符合中国农情的精准农业系统。为了加强对农业生产中旱情动态的掌握,减少旱灾所造成的损害,对结合大田作业的土壤墒情情况的监测体系的建立已成为一项重要工作。本课题研究大田作业中土壤墒情数据无线监测系统。墒情是作为农作物的种子出苗、生长及产出形成的重要条件之一,它一般是指土壤水分条件。对农田墒情,关注其实时变化情况,可为农业及时采用抗旱、灌溉或排水形式提供有有利的科学依据。本文通过对目前土壤墒情预报、监测等研究工作进行了总结,在项目区内,对大田中野外环境的土壤墒情监测系统做了初步设计,实时获取田间监测数据,并进行试验、分析处理,土壤水分预测模型进行了研究,主要结论如下:1.初步设计了实验区野外环境中土壤墒情监测系统,明确了整体技术路线,整理系统的软硬件系统的研究思路,选择适合的开发环境以及工具,构建一个相对比较完善的墒情监测系统。为土壤墒情土壤温度水分预测建模提供了数据基础,也为以后建立一个抗旱管理系统做了有利的铺垫。2.利用土壤墒情相关理论及其实时获取的实际监测数据,分析大田土壤墒情研究中的土壤、水分随时间等因素变化情况,为下一步模型研究提供理论基础。3.建立基于BP人工神经网络的同时输出不同深度土层体积含水率预报模型,并用实测土壤含水率数据对模型进行了检验,研究结果表明预报模型预报误差较小,运用模型来预报作物根系层不同深度的土壤含水率。该模型参数少,容易获得,形式相对简单,易于操作,更实时。
[Abstract]:Our country has a vast territory and a large population.Regional limited agricultural production raw materials, per capita possession of agricultural resources and uneven distribution and other phenomena.The existence of various situations, all show that agriculture is one of the main factors that determine the rapid development of national economy.Corn is the main food crop in China, and also the main crop in Northeast China.During the growth and development of crops, because of the low rainfall and lack of water resources, the soil water content is low, and the water demand is insufficient in a certain period of crop growth, which affects the growth of crops.It also has a certain impact on people's production and life.One of the development directions of agriculture is to establish a precision agriculture system in accordance with Chinese agricultural conditions.In order to strengthen the grasp of drought dynamics in agricultural production and reduce the damage caused by drought, it has become an important work to establish a monitoring system for soil moisture in combination with field operations.This paper studies the wireless monitoring system of soil moisture data in field operation.Soil moisture is one of the important conditions for seed emergence, growth and production of crops. It usually refers to soil moisture condition.Paying attention to the real time change of farmland moisture can provide favorable scientific basis for agriculture to adopt drought resistance irrigation or drainage in time.In this paper, the current research work on soil moisture forecast and monitoring is summarized. In the project area, the preliminary design of soil moisture monitoring system in field environment is made, and the field monitoring data are acquired in real time, and the experiment is carried out.Analysis and treatment, soil moisture prediction model was studied, the main conclusions are as follows: 1.The soil moisture monitoring system in the field environment of the experimental area is preliminarily designed, the overall technical route is clarified, the research ideas of the software and hardware systems of the system are sorted out, and the suitable development environment and tools are selected.Build a relatively perfect soil moisture monitoring system.It provides the data basis for soil moisture and soil temperature and moisture prediction modeling, and also provides a favorable cushion for the establishment of a drought resistance management system in the future.Based on the theory of soil moisture and the actual monitoring data obtained in real time, the variation of soil moisture with time in field soil moisture research is analyzed, which provides a theoretical basis for the next model study.Based on BP artificial neural network, the prediction model of volume water content of soil layer with different depth is produced simultaneously, and the model is tested with the measured soil moisture content data. The results show that the prediction error of the prediction model is small.The model was used to predict soil moisture at different depths of crop root layer.The model has few parameters, easy to obtain, relatively simple, easy to operate and more real-time.
【学位授予单位】：吉林农业大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：S152.7;TP274

【相似文献】