A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials
Remote and non-destructive estimation of leaf area index (LAI) has been a challenge in the last few decades as the direct and indirect methods available are laborious and time-consuming. The recent emergence of high-throughput plant phenotyping platforms has increased the need to develop new phenoty...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Agronomy |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4395/10/2/175 |
id |
doaj-f4bb3e222c9144c08a6592501e370024 |
---|---|
record_format |
Article |
spelling |
doaj-f4bb3e222c9144c08a6592501e3700242021-04-02T08:40:39ZengMDPI AGAgronomy2073-43952020-01-0110217510.3390/agronomy10020175agronomy10020175A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding TrialsOrly Enrique Apolo-Apolo0Manuel Pérez-Ruiz1Jorge Martínez-Guanter2Gregorio Egea3Area of Agroforestry Engineering, Technical School of Agricultural Engineering (ETSIA), Universidad de Sevilla. Ctra. Utrera km 1, 41013 Sevilla, SpainArea of Agroforestry Engineering, Technical School of Agricultural Engineering (ETSIA), Universidad de Sevilla. Ctra. Utrera km 1, 41013 Sevilla, SpainArea of Agroforestry Engineering, Technical School of Agricultural Engineering (ETSIA), Universidad de Sevilla. Ctra. Utrera km 1, 41013 Sevilla, SpainArea of Agroforestry Engineering, Technical School of Agricultural Engineering (ETSIA), Universidad de Sevilla. Ctra. Utrera km 1, 41013 Sevilla, SpainRemote and non-destructive estimation of leaf area index (LAI) has been a challenge in the last few decades as the direct and indirect methods available are laborious and time-consuming. The recent emergence of high-throughput plant phenotyping platforms has increased the need to develop new phenotyping tools for better decision-making by breeders. In this paper, a novel model based on artificial intelligence algorithms and nadir-view red green blue (RGB) images taken from a terrestrial high throughput phenotyping platform is presented. The model mixes numerical data collected in a wheat breeding field and visual features extracted from the images to make rapid and accurate LAI estimations. Model-based LAI estimations were validated against LAI measurements determined non-destructively using an allometric relationship obtained in this study. The model performance was also compared with LAI estimates obtained by other classical indirect methods based on bottom-up hemispherical images and gaps fraction theory. Model-based LAI estimations were highly correlated with ground-truth LAI. The model performance was slightly better than that of the hemispherical image-based method, which tended to underestimate LAI. These results show the great potential of the developed model for near real-time LAI estimation, which can be further improved in the future by increasing the dataset used to train the model.https://www.mdpi.com/2073-4395/10/2/175plant phenotypingleaf areaindex estimationartificial intelligencewheatbreedingcrop monitoring |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Orly Enrique Apolo-Apolo Manuel Pérez-Ruiz Jorge Martínez-Guanter Gregorio Egea |
spellingShingle |
Orly Enrique Apolo-Apolo Manuel Pérez-Ruiz Jorge Martínez-Guanter Gregorio Egea A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials Agronomy plant phenotyping leaf area index estimation artificial intelligence wheat breeding crop monitoring |
author_facet |
Orly Enrique Apolo-Apolo Manuel Pérez-Ruiz Jorge Martínez-Guanter Gregorio Egea |
author_sort |
Orly Enrique Apolo-Apolo |
title |
A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials |
title_short |
A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials |
title_full |
A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials |
title_fullStr |
A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials |
title_full_unstemmed |
A Mixed Data-Based Deep Neural Network to Estimate Leaf Area Index in Wheat Breeding Trials |
title_sort |
mixed data-based deep neural network to estimate leaf area index in wheat breeding trials |
publisher |
MDPI AG |
series |
Agronomy |
issn |
2073-4395 |
publishDate |
2020-01-01 |
description |
Remote and non-destructive estimation of leaf area index (LAI) has been a challenge in the last few decades as the direct and indirect methods available are laborious and time-consuming. The recent emergence of high-throughput plant phenotyping platforms has increased the need to develop new phenotyping tools for better decision-making by breeders. In this paper, a novel model based on artificial intelligence algorithms and nadir-view red green blue (RGB) images taken from a terrestrial high throughput phenotyping platform is presented. The model mixes numerical data collected in a wheat breeding field and visual features extracted from the images to make rapid and accurate LAI estimations. Model-based LAI estimations were validated against LAI measurements determined non-destructively using an allometric relationship obtained in this study. The model performance was also compared with LAI estimates obtained by other classical indirect methods based on bottom-up hemispherical images and gaps fraction theory. Model-based LAI estimations were highly correlated with ground-truth LAI. The model performance was slightly better than that of the hemispherical image-based method, which tended to underestimate LAI. These results show the great potential of the developed model for near real-time LAI estimation, which can be further improved in the future by increasing the dataset used to train the model. |
topic |
plant phenotyping leaf area index estimation artificial intelligence wheat breeding crop monitoring |
url |
https://www.mdpi.com/2073-4395/10/2/175 |
work_keys_str_mv |
AT orlyenriqueapoloapolo amixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT manuelperezruiz amixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT jorgemartinezguanter amixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT gregorioegea amixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT orlyenriqueapoloapolo mixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT manuelperezruiz mixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT jorgemartinezguanter mixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials AT gregorioegea mixeddatabaseddeepneuralnetworktoestimateleafareaindexinwheatbreedingtrials |
_version_ |
1724170302371397632 |