Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach

Protocols to evaluate turfgrass quality rely on visual ratings that, depending on the rater’s expertise, can be subjective and susceptible to positive and negative drifts. We developed seasonal (spring, summer and fall) as well as inter-seasonal machine learning predictive models of turfgrass qualit...

Full description

Saved in:
Bibliographic Details
Main Authors: Alexander Hernandez, Shaun Bushman, Paul Johnson, Matthew D. Robbins, Kaden Patten
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/14/11/2575
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850217996310544384
author Alexander Hernandez
Shaun Bushman
Paul Johnson
Matthew D. Robbins
Kaden Patten
author_facet Alexander Hernandez
Shaun Bushman
Paul Johnson
Matthew D. Robbins
Kaden Patten
author_sort Alexander Hernandez
collection DOAJ
description Protocols to evaluate turfgrass quality rely on visual ratings that, depending on the rater’s expertise, can be subjective and susceptible to positive and negative drifts. We developed seasonal (spring, summer and fall) as well as inter-seasonal machine learning predictive models of turfgrass quality using multispectral and thermal imagery collected using unmanned aerial vehicles for two years as a proof-of-concept. We chose ordinal regression to develop the models instead of conventional classification to account for the ranked nature of the turfgrass quality assessments. We implemented a fuzzy correction of the resulting confusion matrices to ameliorate the probable drift of the field-based visual ratings. The best seasonal predictions were rendered by the fall (multi-class AUC: 0.774, original kappa 0.139, corrected kappa: 0.707) model. However, the best overall predictions were obtained when observation across seasons and years were used for model fitting (multi-class AUC: 0.872, original kappa 0.365, corrected kappa: 0.872), clearly highlighting the need to integrate inter-seasonal variability to enhance models’ accuracies. Vegetation indices such as the NDVI, GNDVI, RVI, CGI and the thermal band can render as much information as a full array of predictors. Our protocol for modeling turfgrass quality can be followed to develop a library of predictive models that can be used in different settings where turfgrass quality ratings are needed.
format Article
id doaj-art-ccb8cccfc5364173ad861f34bfba24ed
institution OA Journals
issn 2073-4395
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-ccb8cccfc5364173ad861f34bfba24ed2025-08-20T02:07:56ZengMDPI AGAgronomy2073-43952024-11-011411257510.3390/agronomy14112575Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy ApproachAlexander Hernandez0Shaun Bushman1Paul Johnson2Matthew D. Robbins3Kaden Patten4Forage and Range Research Laboratory, Agricultural Research Service, United States Department of Agriculture, Logan, UT 84322, USAForage and Range Research Laboratory, Agricultural Research Service, United States Department of Agriculture, Logan, UT 84322, USAPlants, Soils and Climate Department, Utah State University, Logan, UT 84322, USAForage and Range Research Laboratory, Agricultural Research Service, United States Department of Agriculture, Logan, UT 84322, USAForage and Range Research Laboratory, Agricultural Research Service, United States Department of Agriculture, Logan, UT 84322, USAProtocols to evaluate turfgrass quality rely on visual ratings that, depending on the rater’s expertise, can be subjective and susceptible to positive and negative drifts. We developed seasonal (spring, summer and fall) as well as inter-seasonal machine learning predictive models of turfgrass quality using multispectral and thermal imagery collected using unmanned aerial vehicles for two years as a proof-of-concept. We chose ordinal regression to develop the models instead of conventional classification to account for the ranked nature of the turfgrass quality assessments. We implemented a fuzzy correction of the resulting confusion matrices to ameliorate the probable drift of the field-based visual ratings. The best seasonal predictions were rendered by the fall (multi-class AUC: 0.774, original kappa 0.139, corrected kappa: 0.707) model. However, the best overall predictions were obtained when observation across seasons and years were used for model fitting (multi-class AUC: 0.872, original kappa 0.365, corrected kappa: 0.872), clearly highlighting the need to integrate inter-seasonal variability to enhance models’ accuracies. Vegetation indices such as the NDVI, GNDVI, RVI, CGI and the thermal band can render as much information as a full array of predictors. Our protocol for modeling turfgrass quality can be followed to develop a library of predictive models that can be used in different settings where turfgrass quality ratings are needed.https://www.mdpi.com/2073-4395/14/11/2575turfgrass qualitymultispectral imageryunmanned aerial vehiclesordinal forestsfuzzy correctionsremote sensing
spellingShingle Alexander Hernandez
Shaun Bushman
Paul Johnson
Matthew D. Robbins
Kaden Patten
Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
Agronomy
turfgrass quality
multispectral imagery
unmanned aerial vehicles
ordinal forests
fuzzy corrections
remote sensing
title Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
title_full Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
title_fullStr Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
title_full_unstemmed Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
title_short Prediction of Turfgrass Quality Using Multispectral UAV Imagery and Ordinal Forests: Validation Using a Fuzzy Approach
title_sort prediction of turfgrass quality using multispectral uav imagery and ordinal forests validation using a fuzzy approach
topic turfgrass quality
multispectral imagery
unmanned aerial vehicles
ordinal forests
fuzzy corrections
remote sensing
url https://www.mdpi.com/2073-4395/14/11/2575
work_keys_str_mv AT alexanderhernandez predictionofturfgrassqualityusingmultispectraluavimageryandordinalforestsvalidationusingafuzzyapproach
AT shaunbushman predictionofturfgrassqualityusingmultispectraluavimageryandordinalforestsvalidationusingafuzzyapproach
AT pauljohnson predictionofturfgrassqualityusingmultispectraluavimageryandordinalforestsvalidationusingafuzzyapproach
AT matthewdrobbins predictionofturfgrassqualityusingmultispectraluavimageryandordinalforestsvalidationusingafuzzyapproach
AT kadenpatten predictionofturfgrassqualityusingmultispectraluavimageryandordinalforestsvalidationusingafuzzyapproach