基于无人机遥感的苹果产量估测模型研究

打开文本图片集

中图分类号：S126 文献标志码：A 文章编号：1008-0864（2025）09-0110-10

ResearchonAppleYieldEstimationModelBasedonUnmanned Aerial Vehicle Remote Sensing

ZHANG Zhenfei 1，2 ，YANAn1，GUO Jing2*，ZHAO Yuhang1，YUAN Yilin 1 ，LIU Peng1 QUZuohao’，YUANChuan1 （1.Xinjiang Agricultural University，Urumqi 83Oo52，China；2.InstituteofLandscapeand Greening Research， Xinjiang Academy ofForestry，Urumqi 830092，China）

Abstract：Therapidandaccurate estimationofapple tree yield basedon UAVremote sensing technologyisof great significance for precise orchard management and market planning.Using a DJI Phantom 4 RTK quadcopter drone equippedwithamultispectralcamera，multispectral imagesofappletres duringthefloweringperiod，fruitsetting period，fruit expansion period，andmaturityperiod wereobtained.Theimageswerestitched using DJI Terra software，and13 vegetation indices and4 phenotypic features including treeheight，east-west canopy width，northsouth canopy width and averagecanopy width were extracted.Subsequently，different apple yield estimation models were constructed for diferent growth stages and variable combinations using random forest（RF），back propagation neural network（BPNN）and support vector regression （SVR）.The results showed that，compared to considering singlevariables，combining phenotypic featureswith vegetation indicesyielded beter yield estimationresults. Among the 4 growth stages，the frui expansion period was more suitable for apple yield estimation.Among the 3 regression algorithms，SVRachieved the best yield estimation performance.The optimal yield estimation model was theP+VI-SVR 53 model based on phenotypic features and vegetation indices during the fruit expansion period，with a coefficient of determination （ R2 ）of 0.802 O，mean absolute error （MAE）of 15.024 2，and root mean square error （RMSE）of 18.510 7.Using vegetationindices andphenotypic features，apple yield could be estimated，and

combining phenotypic features with vegetation indicescould improve theaccuracy of appleyield estimation.SVR performed better for apple yield estimation during the fruit expansion period.

Keywords：UAV remote sensing;apple yield;inversion; machine learning

中国是世界苹果生产大国，，全国苹果种植区域已扩大到25个省（自治区、直辖市）。（剩余18601字）