Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning

Alfalfa is a valuable and intensively produced forage crop in the United States, and the timely estimation of its yield can inform precision management decisions. However, traditional yield assessment approaches are laborious and time-consuming, and thus hinder the acquisition of timely information...

Full description

Bibliographic Details
Main Authors:	Luwei Feng, Zhou Zhang, Yuchi Ma, Qingyun Du, Parker Williams, Jessica Drewry, Brian Luck
Format:	Article
Language:	English
Published:	MDPI AG 2020-06-01
Series:	Remote Sensing
Subjects:	alfalfa yield prediction hyperspectral unmanned aerial vehicle (UAV) ensemble learning vegetation index
Online Access:	https://www.mdpi.com/2072-4292/12/12/2028

id	doaj-a2027643cec24f5bb976f0551c87c40e
record_format	Article
spelling	doaj-a2027643cec24f5bb976f0551c87c40e2020-11-25T03:37:02ZengMDPI AGRemote Sensing2072-42922020-06-01122028202810.3390/rs12122028Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble LearningLuwei Feng0Zhou Zhang1Yuchi Ma2Qingyun Du3Parker Williams4Jessica Drewry5Brian Luck6Biological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USABiological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USABiological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USASchool of Resources and Environmental Science, Wuhan University, Wuhan 430079, ChinaBiological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USABiological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USABiological Systems Engineering, University of Wisconsin–Madison, Madison, WI 53706, USAAlfalfa is a valuable and intensively produced forage crop in the United States, and the timely estimation of its yield can inform precision management decisions. However, traditional yield assessment approaches are laborious and time-consuming, and thus hinder the acquisition of timely information at the field scale. Recently, unmanned aerial vehicles (UAVs) have gained significant attention in precision agriculture due to their efficiency in data acquisition. In addition, compared with other imaging modalities, hyperspectral data can offer higher spectral fidelity for constructing narrow-band vegetation indices which are of great importance in yield modeling. In this study, we performed an in-season alfalfa yield prediction using UAV-based hyperspectral images. Specifically, we firstly extracted a large number of hyperspectral indices from the original data and performed a feature selection to reduce the data dimensionality. Then, an ensemble machine learning model was developed by combining three widely used base learners including random forest (RF), support vector regression (SVR) and K-nearest neighbors (KNN). The model performance was evaluated on experimental fields in Wisconsin. Our results showed that the ensemble model outperformed all the base learners and a coefficient of determination (R<sup>2</sup>) of 0.874 was achieved when using the selected features. In addition, we also evaluated the model adaptability on different machinery compaction treatments, and the results further demonstrate the efficacy of the proposed ensemble model.https://www.mdpi.com/2072-4292/12/12/2028alfalfayield predictionhyperspectralunmanned aerial vehicle (UAV)ensemble learningvegetation index
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Luwei Feng Zhou Zhang Yuchi Ma Qingyun Du Parker Williams Jessica Drewry Brian Luck
spellingShingle	Luwei Feng Zhou Zhang Yuchi Ma Qingyun Du Parker Williams Jessica Drewry Brian Luck Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning Remote Sensing alfalfa yield prediction hyperspectral unmanned aerial vehicle (UAV) ensemble learning vegetation index
author_facet	Luwei Feng Zhou Zhang Yuchi Ma Qingyun Du Parker Williams Jessica Drewry Brian Luck
author_sort	Luwei Feng
title	Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning
title_short	Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning
title_full	Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning
title_fullStr	Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning
title_full_unstemmed	Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning
title_sort	alfalfa yield prediction using uav-based hyperspectral imagery and ensemble learning
publisher	MDPI AG
series	Remote Sensing
issn	2072-4292
publishDate	2020-06-01
description	Alfalfa is a valuable and intensively produced forage crop in the United States, and the timely estimation of its yield can inform precision management decisions. However, traditional yield assessment approaches are laborious and time-consuming, and thus hinder the acquisition of timely information at the field scale. Recently, unmanned aerial vehicles (UAVs) have gained significant attention in precision agriculture due to their efficiency in data acquisition. In addition, compared with other imaging modalities, hyperspectral data can offer higher spectral fidelity for constructing narrow-band vegetation indices which are of great importance in yield modeling. In this study, we performed an in-season alfalfa yield prediction using UAV-based hyperspectral images. Specifically, we firstly extracted a large number of hyperspectral indices from the original data and performed a feature selection to reduce the data dimensionality. Then, an ensemble machine learning model was developed by combining three widely used base learners including random forest (RF), support vector regression (SVR) and K-nearest neighbors (KNN). The model performance was evaluated on experimental fields in Wisconsin. Our results showed that the ensemble model outperformed all the base learners and a coefficient of determination (R<sup>2</sup>) of 0.874 was achieved when using the selected features. In addition, we also evaluated the model adaptability on different machinery compaction treatments, and the results further demonstrate the efficacy of the proposed ensemble model.
topic	alfalfa yield prediction hyperspectral unmanned aerial vehicle (UAV) ensemble learning vegetation index
url	https://www.mdpi.com/2072-4292/12/12/2028
work_keys_str_mv	AT luweifeng alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT zhouzhang alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT yuchima alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT qingyundu alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT parkerwilliams alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT jessicadrewry alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning AT brianluck alfalfayieldpredictionusinguavbasedhyperspectralimageryandensemblelearning
_version_	1724547467135942656

Alfalfa Yield Prediction Using UAV-Based Hyperspectral Imagery and Ensemble Learning

Similar Items