Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments

Multispectral imagery acquired via Unmanned Aircraft Systems (UAS) can provide an on-demand and cost-effective approach to crop yield estimation. Traditional methods relying solely on vegetation indices (VIs) for yield prediction face challenges such as saturation in dense canopies, like those of ma...

Full description

Saved in:
Bibliographic Details
Main Authors: Bala Ram Sapkota, Gurjinder S. Baath, K. Colton Flynn, Kabindra Adhikari, Chad Hajda, Douglas R. Smith
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Science of Remote Sensing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666017225000732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849398102982656000
author Bala Ram Sapkota
Gurjinder S. Baath
K. Colton Flynn
Kabindra Adhikari
Chad Hajda
Douglas R. Smith
author_facet Bala Ram Sapkota
Gurjinder S. Baath
K. Colton Flynn
Kabindra Adhikari
Chad Hajda
Douglas R. Smith
author_sort Bala Ram Sapkota
collection DOAJ
description Multispectral imagery acquired via Unmanned Aircraft Systems (UAS) can provide an on-demand and cost-effective approach to crop yield estimation. Traditional methods relying solely on vegetation indices (VIs) for yield prediction face challenges such as saturation in dense canopies, like those of maize (Zea Mays L.), and inconsistencies due to environmental variability. This study investigates the potential use of canopy spectral reflectance, directly applied in conjunction with machine learning (ML) to address these limitations and produce more consistent and reliable yield predictions. The performance of reflectance, VI and hybrid (utilizing both reflectance and VIs) based ML models was evaluated for maize yield predictions across various crop growth phases. The research utilizes multispectral imagery and maize yield data from diverse growing environments, comprising seven maize planting dates tested across three field locations over two years. Among five ML algorithms tested, the Extra Trees Regressor (ETR) showed superior performance at predicting maize yield across most maize growth phases. Reflectance-based models consistently outperformed VI-based models at mid-vegetative (R2 = 0.71 vs. 0.50), late vegetative (R2 = 0.85 vs. 0.80), flowering (R2 = 0.83 vs. 0.60), and mid-reproductive (R2 = 0.83 vs. 0.74) growth phases. Hybrid models combining spectral bands and VIs achieved the greatest prediction accuracy but required more extensive data pre-processing compared to models using reflectance or VIs alone. Our findings indicate that direct incorporation of canopy reflectance bands into ML models, bypassing the complexities associated with VIs, can lead to more consistent, timely and reliable maize yield predictions across varied growing environments.
format Article
id doaj-art-ff0ee414c6574b4d97f98d35ac4dbf0d
institution Kabale University
issn 2666-0172
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Science of Remote Sensing
spelling doaj-art-ff0ee414c6574b4d97f98d35ac4dbf0d2025-08-20T03:38:43ZengElsevierScience of Remote Sensing2666-01722025-12-011210026710.1016/j.srs.2025.100267Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environmentsBala Ram Sapkota0Gurjinder S. Baath1K. Colton Flynn2Kabindra Adhikari3Chad Hajda4Douglas R. Smith5Blackland Research & Extension Center, Texas A&M AgriLife Research, 720 E. Blackland Rd, Temple, TX, 76502, USA; Department of Soil and Crop Sciences, Texas A&M University, College Station, TX, 77843, USABlackland Research & Extension Center, Texas A&M AgriLife Research, 720 E. Blackland Rd, Temple, TX, 76502, USA; Corresponding author.USDA-ARS Grassland Soil and Water Research Laboratory, 808 E. Blackland Road, Temple, TX, 76502, USAUSDA-ARS Grassland Soil and Water Research Laboratory, 808 E. Blackland Road, Temple, TX, 76502, USAUSDA-ARS Grassland Soil and Water Research Laboratory, 808 E. Blackland Road, Temple, TX, 76502, USAUSDA-ARS Grassland Soil and Water Research Laboratory, 808 E. Blackland Road, Temple, TX, 76502, USAMultispectral imagery acquired via Unmanned Aircraft Systems (UAS) can provide an on-demand and cost-effective approach to crop yield estimation. Traditional methods relying solely on vegetation indices (VIs) for yield prediction face challenges such as saturation in dense canopies, like those of maize (Zea Mays L.), and inconsistencies due to environmental variability. This study investigates the potential use of canopy spectral reflectance, directly applied in conjunction with machine learning (ML) to address these limitations and produce more consistent and reliable yield predictions. The performance of reflectance, VI and hybrid (utilizing both reflectance and VIs) based ML models was evaluated for maize yield predictions across various crop growth phases. The research utilizes multispectral imagery and maize yield data from diverse growing environments, comprising seven maize planting dates tested across three field locations over two years. Among five ML algorithms tested, the Extra Trees Regressor (ETR) showed superior performance at predicting maize yield across most maize growth phases. Reflectance-based models consistently outperformed VI-based models at mid-vegetative (R2 = 0.71 vs. 0.50), late vegetative (R2 = 0.85 vs. 0.80), flowering (R2 = 0.83 vs. 0.60), and mid-reproductive (R2 = 0.83 vs. 0.74) growth phases. Hybrid models combining spectral bands and VIs achieved the greatest prediction accuracy but required more extensive data pre-processing compared to models using reflectance or VIs alone. Our findings indicate that direct incorporation of canopy reflectance bands into ML models, bypassing the complexities associated with VIs, can lead to more consistent, timely and reliable maize yield predictions across varied growing environments.http://www.sciencedirect.com/science/article/pii/S2666017225000732CornRemote sensingCanopy reflectanceVegetation indicesExtra trees regressor
spellingShingle Bala Ram Sapkota
Gurjinder S. Baath
K. Colton Flynn
Kabindra Adhikari
Chad Hajda
Douglas R. Smith
Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
Science of Remote Sensing
Corn
Remote sensing
Canopy reflectance
Vegetation indices
Extra trees regressor
title Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
title_full Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
title_fullStr Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
title_full_unstemmed Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
title_short Machine learning algorithms for maize yield prediction with multispectral imagery: Assessing robustness across varied growing environments
title_sort machine learning algorithms for maize yield prediction with multispectral imagery assessing robustness across varied growing environments
topic Corn
Remote sensing
Canopy reflectance
Vegetation indices
Extra trees regressor
url http://www.sciencedirect.com/science/article/pii/S2666017225000732
work_keys_str_mv AT balaramsapkota machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments
AT gurjindersbaath machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments
AT kcoltonflynn machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments
AT kabindraadhikari machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments
AT chadhajda machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments
AT douglasrsmith machinelearningalgorithmsformaizeyieldpredictionwithmultispectralimageryassessingrobustnessacrossvariedgrowingenvironments