*
 

iForest - Biogeosciences and Forestry

*

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

Julio Martin Duarte-Carvajalino (1)   , Mónica Paramo-Alvarez (2), Pablo Fernando Ramos-Calderón (3), Carlos Eduardo González-Orozco (4)

iForest - Biogeosciences and Forestry, Volume 14, Issue 6, Pages 517-521 (2021)
doi: https://doi.org/10.3832/ifor3936-014
Published: Nov 17, 2021 - Copyright © 2021 SISEF

Short Communications


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.

  Keywords


Canopy Attributes, Cover Photography, Colombia, Machine Learning, Deep Learning

Authors’ address

(1)
Julio Martin Duarte-Carvajalino 0000-0001-7117-2051
Corporación Colombiana de Investigación Agropecuaria - AGROSAVIA, Centro de Investigación Tibaitatá, Km 14 vía Mosquera, Bogotá, Cundinamarca (Colombia)
(2)
Mónica Paramo-Alvarez 0000-0001-8682-2651
Corporación Colombiana de Investigación Agropecuaria - AGROSAVIA, Sede Central, Km 14 vía Mosquera, Bogotá (Colombia)
(3)
Pablo Fernando Ramos-Calderón 0000-0002-0748-8534
Corporación Colombiana de Investigación Agropecuaria - AGROSAVIA, Centro de Investigación Nataima, Km 9 vía Espinal-Chicoral, Tolima, Sede Florencia, Caquetá (Colombia)
(4)
Carlos Eduardo González-Orozco 0000-0002-4593-9113
Corporación Colombiana de Investigación Agropecuaria - AGROSAVIA, Centro de Investigación La Libertad, Km 14 vía Villavicencio, Puerto López, Meta (Colombia)

Corresponding author

 
Julio Martin Duarte-Carvajalino
jmduarte@agrosavia.co

Citation

Duarte-Carvajalino JM, Paramo-Alvarez M, Ramos-Calderón PF, González-Orozco CE (2021). Estimation of canopy attributes of wild cacao trees using digital cover photography and machine learning algorithms. iForest 14: 517-521. - doi: 10.3832/ifor3936-014

Academic Editor

Nicola Puletti

Paper history

Received: Jul 23, 2021
Accepted: Sep 08, 2021

First online: Nov 17, 2021
Publication Date: Dec 31, 2021
Publication Time: 2.33 months

Breakdown by View Type

(Waiting for server response...)

Article Usage

Total Article Views: 742
(from publication date up to now)

Breakdown by View Type
HTML Page Views: 0
Abstract Page Views: 0
PDF Downloads: 662
Citation/Reference Downloads: 1
XML Downloads: 79

Web Metrics
Days since publication: 266
Overall contacts: 742
Avg. contacts per week: 19.53

Article Citations

Article citations are based on data periodically collected from the Clarivate Web of Science web site
(last update: Nov 2020)

(No citations were found up to date. Please come back later)


 

Publication Metrics

by Dimensions ©

Articles citing this article

List of the papers citing this article based on CrossRef Cited-by.

 
(1)
Alivernini A, Fares S, Ferrara C, Chianucci F (2018)
An objective image analysis method for estimation of canopy attributes from digital cover photography. Trees - Structure and Function 32: 713-723.
CrossRef | Gscholar
(2)
Altman NS (1992)
An introduction to kernel and nearest-neighbor nonparametric regression. American Statistician 46: 175-185.
CrossRef | Gscholar
(3)
Brown PL, Doley D, Keenan RJ (2000)
Estimating tree crown dimensions using digital analysis of vertical photographs. Agricultural and Forest Meteorology 100: 199-212.
CrossRef | Gscholar
(4)
Chen HF (2009)
In silico log p prediction for a large data set with support vector machines, radial basis neural networks and multiple linear regression. Chemical Biology and Drug Design 74: 142-147.
CrossRef | Gscholar
(5)
Cheng T, Guestrin C (2016)
XGBoost: a scalable tree boosting system. In: “The Association for Computing Machinery’s Special Interest Group on Knowledge Discovery and Data Mining”. ACM, San Francisco, CA, USA, pp. 785-794.
CrossRef | Gscholar
(6)
Chianucci F, Cutini A (2012)
Digital hemispherical photography for estimating forest canopy properties: Current controversies and opportunities. iForest - Biogeosciences and Forestry 5: 290-295.
CrossRef | Gscholar
(7)
Chianucci F, Chiavetta U, Cutini A (2014a)
The estimation of canopy attributes from digital cover photography by two different image analysis methods. iForest - Biogeosciences and Forestry 7: 255-259.
CrossRef | Gscholar
(8)
Chianucci F, Cutini A, Corona P, Puletti N (2014b)
Estimation of leaf area index in understory deciduous trees using digital photography. Agricultural and Forest Meteorology 198: 259-264.
CrossRef | Gscholar
(9)
Chianucci F, Disperati L, Guzzi D, Bianchini D, Nardino V, Lastri C, Rindinella A, Corona P (2016)
Estimation of canopy attributes in beech forests using true colour digital images from a small fixed-wing UAV. International Journal of Applied Earth Observation and Geoinformation 47: 60-68.
CrossRef | Gscholar
(10)
Chianucci F (2020)
An overview of in situ digital canopy photography in forestry. Canadian Journal of Forest Research 50: 227-242.
CrossRef | Gscholar
(11)
Cuatrecasas J (1964)
Cacao and its allies: a taxonomic revision of the genus Theobroma. In: “Systematic Plant Studies”. Smithsonian Institution Press, Washington, DC, USA, pp. 379-614.
Online | Gscholar
(12)
Díaz GM, Negri PA, Lencinas JD (2021)
Toward making canopy hemispherical photography independent of illumination conditions: a deep-learning-based approach. Agricultural and Forest Meteorology 296: 108234.
CrossRef | Gscholar
(13)
Glorot X, Bordes A, Bengio Y (2011)
Deep sparse rectifier neural networks. In: Proceedings of the “14th International Conference on Artificial Intelligence and Statistics” (AISTATS). Fort Lauderdale (FL, USA) 11-13 Apr 2011. Proceedings of Machine Learning Research 15: 315-323.
Online | Gscholar
(14)
González-Orozco CE, Galán AAS, Ramos PE, Yockteng R (2020)
Exploring the diversity and distribution of crop wild relatives of cacao (Theobroma cacao L.) in Colombia. Genetic Resources and Crop Evolution 67: 2071-2085.
CrossRef | Gscholar
(15)
Grotti M, Calders K, Origo N, Puletti N, Alivernini A, Ferrara C, Chianucci F (2020)
An intensity, image-based method to estimate gap fraction, canopy openness and effective leaf area index from phase-shift terrestrial laser scanning. Agricultural and Forest Meteorology. 280: 107766.
CrossRef | Gscholar
(16)
Ho TK (1995)
Random decision forests. In: Proceedings of the “ICDAR - 3rd International Conference on Document Analysis and Recognition”. Montreal (QC, Canada) 14-16 Aug 1995. IEEExplore 1: 278-282.
CrossRef | Gscholar
(17)
Ioffe S, Szegedy C (2015)
Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the “ICML 2015 - 32nd International Conference on Machine Learning”. Proceedings of Machine Learning Research 37: 448-456.
Online | Gscholar
(18)
Krizhevsky A, Sutskever I, Hinton G (2017)
ImageNet classification with deep convolutional neural networks. Communications of the ACM 60 (6): 84-90.
CrossRef | Gscholar
(19)
Li K, Huang X, Zhang J, Sun Z, Huang J, Sun C, Xie Q, Song W (2020)
A new method for forest canopy hemispherical photography segmentation based on deep learning. Forests 11: 1-16.
CrossRef | Gscholar
(20)
Maxted N, Scholten M, Codd R, Ford-Lloyd B (2007)
Creation and use of a national inventory of crop wild relatives. Biological Conservation 140: 142-159.
CrossRef | Gscholar
(21)
Noorian N, Shataee-Jouibary S, Mohammadi J (2016)
Assessment of different remote sensing data for forest structural attributes estimation in the Hyrcanian forests. Forest Systems 25 (3): 1-11.
CrossRef | Gscholar
(22)
Patterson MF, Wiseman PE, Winn MF, Lee SM, Araman PA (2011)
Effects of photographic distance on tree crown attributes calculated using urbancrowns image analysis software. Arboriculture and Urban Forestry 37: 173-179.
CrossRef | Gscholar
(23)
Rumelhart DE, Hinton GE, Williams RJ (1986)
Learning internal representations by error propagation. In: “Parallel Distributed Processing: Explorations in the Microstructure of Cognition” (Rumelhart DE, McClelland JL, Williams RJ eds). MIT Press, Cambridge, MA, USA, vol. 1, pp. 318-362.
Gscholar
(24)
Shataee S, Kalbi S, Fallah A, Pelz D (2012)
Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest regression algorithms. International Journal of Remote Sensing 33: 6254-6280.
CrossRef | Gscholar
(25)
Smith M-L, Anderson J, Fladeland M (2008)
Forest canopy structural properties. In: “Field Measurements for Forest Carbon Monitoring” (Hoover CM ed). Springer, Dordrecht, Netherlands, pp. 179-176.
CrossRef | Gscholar
(26)
Srivastava M, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014)
Dropout: a simple way to prevent neural networks from overfitting. Machine Learning Research 15: 1929-1958.
Online | Gscholar
 

This website uses cookies to ensure you get the best experience on our website. More info