基于无人机影像数据的苹果产量模拟——以洛川县为例

西安科技大学 测绘科学与技术学院,陕西 西安 710054

遥感; GIS; 回归分析; 苹果估产

Simulation of the apple yield based on unmanned aerial vehicle image data——Taking Luochuan county as an example
GUO Bin,WU Ya-yan,ZHOU Jia-yao,WANG Zhou-zhu,SHI Qin-yu,TIAN Yang

(College of Geomatics,Xi'an University of Science and Technology,Xi'an 710054,China)

remote-sensing; GIS; regression analysis; estimate of apples'yield

DOI: 10.13800/j.cnki.xakjdxxb.2017.0322

备注

苹果是陕西省主要的经济作物之一,洛川县是陕西省主要的苹果生产区。利用无人机遥感迅速获取苹果长势数据,结合地理信息系统的空间分析与建模功能尝试性的预测苹果产量。文中采用多源数据,结合当地的统计年鉴包括苹果总产量、降水量、均温、日照等气象数据等,进行洛川县的苹果产量预测,并将预测结果与实际统计数据进行比较与分析。研究表明:遥感气象产量模型的准确度较高,模型R2为0.802,标准残差为11.26.针对苹果季节性生产的特点,利用无人机遥感实时动态的进行数据获取和分析,可以有效地对苹果产量进行预测。利用计量地理学的方法,对数据进行回归分析、方法可靠,可为农业管理部门提供决策依据。

Apples are one of the most important cash crops in the Shaanxi Province.Luochuan County is a main apple product district of Shaanxi Province.This paper practices reaping apples'growth through an unmanned aerial vehicle remote sensing technique combined with spatial analysis function of Geographic Information System(GIS)to tentatively estimate apples'output.Under the study process using multi-source data and combining the local statistical yearbook including apples'gross output,precipitation,temperature and sunshine etc.,we are able to predict the apples'output in Luochuan County,then compare the estimated yield result of predicted model with the actual statistics and analyze the data.The results show that the accuracy of the yield model of remote-sensing meteorology is higher than others',the multiple correlation coefficient of the apples'yield model of remote-sensing meteorology is 0.802 and its standardized residual is 11.26.Considering that apples provide a seasonal yield,it would be available for an efficient dynamic acquiring and analyzing of data to predict the outputby aerial vehicle's remote sensing technique.Using the Quantity Geography,we carry out the regression analysis.The method is reliable,which provides reference for decision-makers in agricultural industry.