A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics

Canola (Brassica napus L.) yield prediction using a combined application of small unmanned aerial system (sUAS) and vegetation indices (VIs) have gained significant attention. In recent years, major studies have demonstrated the potential of developing new VIs for predicting canola yield. However, s...

Full description

Saved in:
Bibliographic Details
Main Authors: Nitin Rai, Harsh Pathak, Maria Villamil Mahecha, Dennis R. Buckmaster, Yanbo Huang, Paul Overby, Xin Sun
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375524003022
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850107096211652608
author Nitin Rai
Harsh Pathak
Maria Villamil Mahecha
Dennis R. Buckmaster
Yanbo Huang
Paul Overby
Xin Sun
author_facet Nitin Rai
Harsh Pathak
Maria Villamil Mahecha
Dennis R. Buckmaster
Yanbo Huang
Paul Overby
Xin Sun
author_sort Nitin Rai
collection DOAJ
description Canola (Brassica napus L.) yield prediction using a combined application of small unmanned aerial system (sUAS) and vegetation indices (VIs) have gained significant attention. In recent years, major studies have demonstrated the potential of developing new VIs for predicting canola yield. However, such indices may perform optimally on the specific farms for which they have been designed and may fail to generalize to a new agronomic scenario. Therefore, this study aims to conduct a comprehensive analysis on the application of existing VIs that could be used to predict potential canola yield on a commercial farm, thereby eliminating the need to develop new indices from scratch. In this research study, over twenty-seven VIs were extracted from two sUAS imagery captured during peak flowering and seed development stages of canola. The extracted features were fed to four conventional machine learning (ML) classifiers with appropriate hyperparameter tuning approaches. Additionally, to perform a comparative test with neural network-based deep learning (DL) architectures, a convolutional neural network-1-dimensional (CNN-1D_Canola) model was developed to train data points and predict canola yield. These models were trained on the yield maps interpolated using three approaches, based on the ground truth yield data points obtained from a harvester. Results suggest that peak flowering is the best stage to predict canola yield. Additionally, a combination of kriging-based yield maps with three best features, canola ratio index (CRI), canola index (CI), and structure intensive vegetation index (SIPI) indices, trained using support vector machine (R2=0.68), multi-layer perceptron (R2=0.7), and CNN_1D_Canola (R2=0.66) have the potential to predict canola yield based on spectral image-based features. This study highlights the potential of predicting canola yield for a commercial farm using a combined application of sUAS imagery and VIs. The promising performance of all the models coupled with a comprehensive hyperparameter tuning approaches suggests its applicability in predicting canola yield in real field conditions.
format Article
id doaj-art-65d1114af2eb4d3dbd7701a2a7fd985e
institution OA Journals
issn 2772-3755
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-65d1114af2eb4d3dbd7701a2a7fd985e2025-08-20T02:38:39ZengElsevierSmart Agricultural Technology2772-37552024-12-01910069810.1016/j.atech.2024.100698A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analyticsNitin Rai0Harsh Pathak1Maria Villamil Mahecha2Dennis R. Buckmaster3Yanbo Huang4Paul Overby5Xin Sun6Department of Agricultural and Biosystems Engineering, North Dakota State University, Fargo, ND 58102, United StatesDepartment of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, United StatesDepartment of Agricultural and Biosystems Engineering, North Dakota State University, Fargo, ND 58102, United StatesDepartment of Agricultural and Biological Engineering, Purdue University, West Lafayette, IN 47907, United StatesUSDA ARS, Crop Production Systems Research Unit, 141 Experiment Station Road, PO Box 350, Stoneville, MS 38776, United StatesLee Farms, Wolford, ND, 58385, United StatesDepartment of Agricultural and Biosystems Engineering, North Dakota State University, Fargo, ND 58102, United States; Corresponding author.Canola (Brassica napus L.) yield prediction using a combined application of small unmanned aerial system (sUAS) and vegetation indices (VIs) have gained significant attention. In recent years, major studies have demonstrated the potential of developing new VIs for predicting canola yield. However, such indices may perform optimally on the specific farms for which they have been designed and may fail to generalize to a new agronomic scenario. Therefore, this study aims to conduct a comprehensive analysis on the application of existing VIs that could be used to predict potential canola yield on a commercial farm, thereby eliminating the need to develop new indices from scratch. In this research study, over twenty-seven VIs were extracted from two sUAS imagery captured during peak flowering and seed development stages of canola. The extracted features were fed to four conventional machine learning (ML) classifiers with appropriate hyperparameter tuning approaches. Additionally, to perform a comparative test with neural network-based deep learning (DL) architectures, a convolutional neural network-1-dimensional (CNN-1D_Canola) model was developed to train data points and predict canola yield. These models were trained on the yield maps interpolated using three approaches, based on the ground truth yield data points obtained from a harvester. Results suggest that peak flowering is the best stage to predict canola yield. Additionally, a combination of kriging-based yield maps with three best features, canola ratio index (CRI), canola index (CI), and structure intensive vegetation index (SIPI) indices, trained using support vector machine (R2=0.68), multi-layer perceptron (R2=0.7), and CNN_1D_Canola (R2=0.66) have the potential to predict canola yield based on spectral image-based features. This study highlights the potential of predicting canola yield for a commercial farm using a combined application of sUAS imagery and VIs. The promising performance of all the models coupled with a comprehensive hyperparameter tuning approaches suggests its applicability in predicting canola yield in real field conditions.http://www.sciencedirect.com/science/article/pii/S2772375524003022CanolaData analyticsHyperparameter tuningMachine learningNeural-networkRemote sensing
spellingShingle Nitin Rai
Harsh Pathak
Maria Villamil Mahecha
Dennis R. Buckmaster
Yanbo Huang
Paul Overby
Xin Sun
A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
Smart Agricultural Technology
Canola
Data analytics
Hyperparameter tuning
Machine learning
Neural-network
Remote sensing
title A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
title_full A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
title_fullStr A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
title_full_unstemmed A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
title_short A case study on canola (Brassica napus L.) potential yield prediction using remote sensing imagery and advanced data analytics
title_sort case study on canola brassica napus l potential yield prediction using remote sensing imagery and advanced data analytics
topic Canola
Data analytics
Hyperparameter tuning
Machine learning
Neural-network
Remote sensing
url http://www.sciencedirect.com/science/article/pii/S2772375524003022
work_keys_str_mv AT nitinrai acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT harshpathak acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT mariavillamilmahecha acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT dennisrbuckmaster acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT yanbohuang acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT pauloverby acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT xinsun acasestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT nitinrai casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT harshpathak casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT mariavillamilmahecha casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT dennisrbuckmaster casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT yanbohuang casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT pauloverby casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics
AT xinsun casestudyoncanolabrassicanapuslpotentialyieldpredictionusingremotesensingimageryandadvanceddataanalytics