Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance

Accurate knowledge of photosynthetic capacity is critical for understanding the carbon cycle under climate change. Despite the fact that deep neural network (DNN) models are increasingly applied across a wide range of fields, there are very few attempts to predict leaf photosynthetic capacity (indic...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Guangman Song, Quan Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	DNN <i>V</i>cmax <i>J</i>max bootstrap hyperspectral reflectance Science Q
Acceso en línea:	https://doaj.org/article/490686a6ae5d4413a20b37a7af168bb2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:490686a6ae5d4413a20b37a7af168bb2
record_format	dspace
spelling	oai:doaj.org-article:490686a6ae5d4413a20b37a7af168bb22021-11-11T18:58:12ZIncluding Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance10.3390/rs132144672072-4292https://doaj.org/article/490686a6ae5d4413a20b37a7af168bb22021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4467https://doaj.org/toc/2072-4292Accurate knowledge of photosynthetic capacity is critical for understanding the carbon cycle under climate change. Despite the fact that deep neural network (DNN) models are increasingly applied across a wide range of fields, there are very few attempts to predict leaf photosynthetic capacity (indicated by maximum carboxylation rate, <i>V</i>cmax, and maximum electron transport rate, <i>J</i>max) from reflected information. In this study, we have built a DNN model that uses leaf reflected spectra, alone or together with other leaf traits, for the reliable estimation of photosynthetic capacity, accounting for leaf types and growing periods in cool–temperate deciduous forests. Our results demonstrate that even though DNN models using only the reflectance spectra are capable of estimating both <i>V</i>cmax and <i>J</i>max acceptably, their performance could nevertheless be improved by including information about other leaf biophysical/biochemical traits. The results highlight the fact that leaf spectra and leaf biophysical/biochemical traits are closely linked with leaf photosynthetic capacity, providing a practical and feasible approach to tracing functional traits. However, the DNN models developed in this study should undergo more extensive validation and training before being applied in other regions, and further refinements in future studies using larger datasets from a wide range of ecosystems are also necessary.Guangman SongQuan WangMDPI AGarticleDNN<i>V</i>cmax<i>J</i>maxbootstraphyperspectral reflectanceScienceQENRemote Sensing, Vol 13, Iss 4467, p 4467 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	DNN <i>V</i>cmax <i>J</i>max bootstrap hyperspectral reflectance Science Q
spellingShingle	DNN <i>V</i>cmax <i>J</i>max bootstrap hyperspectral reflectance Science Q Guangman Song Quan Wang Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
description	Accurate knowledge of photosynthetic capacity is critical for understanding the carbon cycle under climate change. Despite the fact that deep neural network (DNN) models are increasingly applied across a wide range of fields, there are very few attempts to predict leaf photosynthetic capacity (indicated by maximum carboxylation rate, <i>V</i>cmax, and maximum electron transport rate, <i>J</i>max) from reflected information. In this study, we have built a DNN model that uses leaf reflected spectra, alone or together with other leaf traits, for the reliable estimation of photosynthetic capacity, accounting for leaf types and growing periods in cool–temperate deciduous forests. Our results demonstrate that even though DNN models using only the reflectance spectra are capable of estimating both <i>V</i>cmax and <i>J</i>max acceptably, their performance could nevertheless be improved by including information about other leaf biophysical/biochemical traits. The results highlight the fact that leaf spectra and leaf biophysical/biochemical traits are closely linked with leaf photosynthetic capacity, providing a practical and feasible approach to tracing functional traits. However, the DNN models developed in this study should undergo more extensive validation and training before being applied in other regions, and further refinements in future studies using larger datasets from a wide range of ecosystems are also necessary.
format	article
author	Guangman Song Quan Wang
author_facet	Guangman Song Quan Wang
author_sort	Guangman Song
title	Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
title_short	Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
title_full	Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
title_fullStr	Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
title_full_unstemmed	Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance
title_sort	including leaf traits improves a deep neural network model for predicting photosynthetic capacity from reflectance
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/490686a6ae5d4413a20b37a7af168bb2
work_keys_str_mv	AT guangmansong includingleaftraitsimprovesadeepneuralnetworkmodelforpredictingphotosyntheticcapacityfromreflectance AT quanwang includingleaftraitsimprovesadeepneuralnetworkmodelforpredictingphotosyntheticcapacityfromreflectance
_version_	1718431642816610304

Including Leaf Traits Improves a Deep Neural Network Model for Predicting Photosynthetic Capacity from Reflectance

Ejemplares similares