Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms

Surveying canopy attributes while conducting fieldwork in the rain forest is time-consuming. Low-cost imagery such as digital cover photography is a potential source of information to speed up the process of vegetation assessments and reduce costs during expeditions. This study presents an image-bas...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Duarte-Carvajalino JM, Paramo-Alvarez M, Ramos-Calderón PF, González-Orozco CE
Formato:	article
Lenguaje:	EN
Publicado:	Italian Society of Silviculture and Forest Ecology (SISEF) 2021
Materias:	Canopy Attributes Cover Photography Colombia Machine Learning Deep Learning Forestry SD1-669.5
Acceso en línea:	https://doaj.org/article/bb2a6d182d34425684baa90c30fe765f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bb2a6d182d34425684baa90c30fe765f
record_format	dspace
spelling	oai:doaj.org-article:bb2a6d182d34425684baa90c30fe765f2021-11-17T19:10:45ZEstimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms1971-745810.3832/ifor3936-014https://doaj.org/article/bb2a6d182d34425684baa90c30fe765f2021-12-01T00:00:00Zhttps://iforest.sisef.org/contents/?id=ifor3936-014https://doaj.org/toc/1971-7458Surveying canopy attributes while conducting fieldwork in the rain forest is time-consuming. Low-cost imagery such as digital cover photography is a potential source of information to speed up the process of vegetation assessments and reduce costs during expeditions. This study presents an image-based non-destructive method to estimate canopy attributes of wild cacao trees in two regions of the rain forest in Colombia, using digital cover photography and machine learning algorithms. Upward-looking photography at the base of each cacao tree and machine learning algorithms were used to estimate gap fraction (GF), foliage cover (FC), crown cover (CC), crown porosity (CP), clumping index (Ω), and leaf area index (LAI) of the canopy cover. Here we used the cacao wild trees found on forestry plots as a case study to test the application of low-cost imagery on the extraction and analysis of canopy attributes. Canopy attributes were successfully extracted from the canopy cover imagery and provided 92% of classification accuracy for the structural attributes of the canopy. Canopy cover attributes allowed us to differentiate between canopy structures of the Amazon and Pacific rainforests sites suggesting that wild cacao trees are associated with different vegetation types. We also compare classification results for the computer extraction of canopy attributes with a digital canopy cover benchmark. We conclude that our approach was effective to quickly survey canopy features of vegetation associated with and of crop wild relatives of cacao. This study allows highly reproducible estimates of canopy attributes using cover photography and state-of-the-art machine learning algorithms such as deep learning Convolutional Neural Networks.Duarte-Carvajalino JMParamo-Alvarez MRamos-Calderón PFGonzález-Orozco CEItalian Society of Silviculture and Forest Ecology (SISEF)articleCanopy AttributesCover PhotographyColombiaMachine LearningDeep LearningForestrySD1-669.5ENiForest - Biogeosciences and Forestry, Vol 14, Iss 1, Pp 517-521 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Canopy Attributes Cover Photography Colombia Machine Learning Deep Learning Forestry SD1-669.5
spellingShingle	Canopy Attributes Cover Photography Colombia Machine Learning Deep Learning Forestry SD1-669.5 Duarte-Carvajalino JM Paramo-Alvarez M Ramos-Calderón PF González-Orozco CE Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
description	Surveying canopy attributes while conducting fieldwork in the rain forest is time-consuming. Low-cost imagery such as digital cover photography is a potential source of information to speed up the process of vegetation assessments and reduce costs during expeditions. This study presents an image-based non-destructive method to estimate canopy attributes of wild cacao trees in two regions of the rain forest in Colombia, using digital cover photography and machine learning algorithms. Upward-looking photography at the base of each cacao tree and machine learning algorithms were used to estimate gap fraction (GF), foliage cover (FC), crown cover (CC), crown porosity (CP), clumping index (Ω), and leaf area index (LAI) of the canopy cover. Here we used the cacao wild trees found on forestry plots as a case study to test the application of low-cost imagery on the extraction and analysis of canopy attributes. Canopy attributes were successfully extracted from the canopy cover imagery and provided 92% of classification accuracy for the structural attributes of the canopy. Canopy cover attributes allowed us to differentiate between canopy structures of the Amazon and Pacific rainforests sites suggesting that wild cacao trees are associated with different vegetation types. We also compare classification results for the computer extraction of canopy attributes with a digital canopy cover benchmark. We conclude that our approach was effective to quickly survey canopy features of vegetation associated with and of crop wild relatives of cacao. This study allows highly reproducible estimates of canopy attributes using cover photography and state-of-the-art machine learning algorithms such as deep learning Convolutional Neural Networks.
format	article
author	Duarte-Carvajalino JM Paramo-Alvarez M Ramos-Calderón PF González-Orozco CE
author_facet	Duarte-Carvajalino JM Paramo-Alvarez M Ramos-Calderón PF González-Orozco CE
author_sort	Duarte-Carvajalino JM
title	Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
title_short	Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
title_full	Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
title_fullStr	Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
title_full_unstemmed	Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
title_sort	estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms
publisher	Italian Society of Silviculture and Forest Ecology (SISEF)
publishDate	2021
url	https://doaj.org/article/bb2a6d182d34425684baa90c30fe765f
work_keys_str_mv	AT duartecarvajalinojm estimationofcanopyattributesofwildcacaotreesusingdigitalcoverphotographyandmachinelearningalgorithms AT paramoalvarezm estimationofcanopyattributesofwildcacaotreesusingdigitalcoverphotographyandmachinelearningalgorithms AT ramoscalderonpf estimationofcanopyattributesofwildcacaotreesusingdigitalcoverphotographyandmachinelearningalgorithms AT gonzalezorozcoce estimationofcanopyattributesofwildcacaotreesusingdigitalcoverphotographyandmachinelearningalgorithms
_version_	1718425377881194496

Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms

Ejemplares similares