Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape

Accurate and timely prediction of oilseed rape yield is crucial in precision agriculture and field remote sensing. We explored the feasibility and potential for predicting oilseed rape yield through the utilization of a UAV-based platform equipped with RGB and multispectral cameras. Genetic algorith...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongyan Zhu, Shikai Liang, Chengzhi Lin, Yong He, Jun-Li Xu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Drones
Subjects:
Online Access:https://www.mdpi.com/2504-446X/8/11/642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846153745949261824
author Hongyan Zhu
Shikai Liang
Chengzhi Lin
Yong He
Jun-Li Xu
author_facet Hongyan Zhu
Shikai Liang
Chengzhi Lin
Yong He
Jun-Li Xu
author_sort Hongyan Zhu
collection DOAJ
description Accurate and timely prediction of oilseed rape yield is crucial in precision agriculture and field remote sensing. We explored the feasibility and potential for predicting oilseed rape yield through the utilization of a UAV-based platform equipped with RGB and multispectral cameras. Genetic algorithm–partial least square was employed and evaluated for effective wavelength (EW) or vegetation index (VI) selection. Additionally, different machine learning algorithms, i.e., multiple linear regression (MLR), partial least squares regression (PLSR), least squares support vector machine (LS-SVM), back propagation neural network (BPNN), extreme learning machine (ELM), and radial basis function neural network (RBFNN), were developed and compared. With multi-source data fusion by combining vegetation indices (color and narrow-band VIs), robust prediction models of yield in oilseed rape were built. The performance of prediction models using the combination of VIs (RBFNN: <i>R<sub>pre</sub></i> = 0.8143, RMSEP = 171.9 kg/hm<sup>2</sup>) from multiple sensors manifested better results than those using only narrow-band VIs (BPNN: <i>R<sub>pre</sub></i> = 0.7655, RMSEP = 188.3 kg/hm<sup>2</sup>) from a multispectral camera. The best models for yield prediction were found by applying BPNN (<i>R<sub>pre</sub></i> = 0.8114, RMSEP = 172.6 kg/hm<sup>2</sup>) built from optimal EWs and ELM (<i>R<sub>pre</sub></i> = 0.8118, RMSEP = 170.9 kg/hm<sup>2</sup>) using optimal VIs. Taken together, the findings conclusively illustrate the potential of UAV-based RGB and multispectral images for the timely and non-invasive prediction of oilseed rape yield. This study also highlights that a lightweight UAV equipped with dual-image-frame snapshot cameras holds promise as a valuable tool for high-throughput plant phenotyping and advanced breeding programs within the realm of precision agriculture.
format Article
id doaj-art-af270725a1094ad6a3dd19c1eaca7913
institution Kabale University
issn 2504-446X
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Drones
spelling doaj-art-af270725a1094ad6a3dd19c1eaca79132024-11-26T18:00:40ZengMDPI AGDrones2504-446X2024-11-0181164210.3390/drones8110642Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed RapeHongyan Zhu0Shikai Liang1Chengzhi Lin2Yong He3Jun-Li Xu4Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, ChinaGuangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, ChinaGuangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips, School of Electronic and Information Engineering, Guangxi Normal University, Guilin 541004, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaSchool of Biosystems and Food Engineering, University College Dublin (UCD), Belfield, 4 Dublin, IrelandAccurate and timely prediction of oilseed rape yield is crucial in precision agriculture and field remote sensing. We explored the feasibility and potential for predicting oilseed rape yield through the utilization of a UAV-based platform equipped with RGB and multispectral cameras. Genetic algorithm–partial least square was employed and evaluated for effective wavelength (EW) or vegetation index (VI) selection. Additionally, different machine learning algorithms, i.e., multiple linear regression (MLR), partial least squares regression (PLSR), least squares support vector machine (LS-SVM), back propagation neural network (BPNN), extreme learning machine (ELM), and radial basis function neural network (RBFNN), were developed and compared. With multi-source data fusion by combining vegetation indices (color and narrow-band VIs), robust prediction models of yield in oilseed rape were built. The performance of prediction models using the combination of VIs (RBFNN: <i>R<sub>pre</sub></i> = 0.8143, RMSEP = 171.9 kg/hm<sup>2</sup>) from multiple sensors manifested better results than those using only narrow-band VIs (BPNN: <i>R<sub>pre</sub></i> = 0.7655, RMSEP = 188.3 kg/hm<sup>2</sup>) from a multispectral camera. The best models for yield prediction were found by applying BPNN (<i>R<sub>pre</sub></i> = 0.8114, RMSEP = 172.6 kg/hm<sup>2</sup>) built from optimal EWs and ELM (<i>R<sub>pre</sub></i> = 0.8118, RMSEP = 170.9 kg/hm<sup>2</sup>) using optimal VIs. Taken together, the findings conclusively illustrate the potential of UAV-based RGB and multispectral images for the timely and non-invasive prediction of oilseed rape yield. This study also highlights that a lightweight UAV equipped with dual-image-frame snapshot cameras holds promise as a valuable tool for high-throughput plant phenotyping and advanced breeding programs within the realm of precision agriculture.https://www.mdpi.com/2504-446X/8/11/642data fusionmachine learning algorithmsoilseed raperemote sensingunmanned aerial vehicle (UAV)yield prediction
spellingShingle Hongyan Zhu
Shikai Liang
Chengzhi Lin
Yong He
Jun-Li Xu
Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
Drones
data fusion
machine learning algorithms
oilseed rape
remote sensing
unmanned aerial vehicle (UAV)
yield prediction
title Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
title_full Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
title_fullStr Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
title_full_unstemmed Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
title_short Using Multi-Sensor Data Fusion Techniques and Machine Learning Algorithms for Improving UAV-Based Yield Prediction of Oilseed Rape
title_sort using multi sensor data fusion techniques and machine learning algorithms for improving uav based yield prediction of oilseed rape
topic data fusion
machine learning algorithms
oilseed rape
remote sensing
unmanned aerial vehicle (UAV)
yield prediction
url https://www.mdpi.com/2504-446X/8/11/642
work_keys_str_mv AT hongyanzhu usingmultisensordatafusiontechniquesandmachinelearningalgorithmsforimprovinguavbasedyieldpredictionofoilseedrape
AT shikailiang usingmultisensordatafusiontechniquesandmachinelearningalgorithmsforimprovinguavbasedyieldpredictionofoilseedrape
AT chengzhilin usingmultisensordatafusiontechniquesandmachinelearningalgorithmsforimprovinguavbasedyieldpredictionofoilseedrape
AT yonghe usingmultisensordatafusiontechniquesandmachinelearningalgorithmsforimprovinguavbasedyieldpredictionofoilseedrape
AT junlixu usingmultisensordatafusiontechniquesandmachinelearningalgorithmsforimprovinguavbasedyieldpredictionofoilseedrape