Individual Growth Model for<i>Eucalyptus</i>Stands in Brazil Using Artificial Neural Network

Castro, Renato Vinícius Oliveira; Soares, Carlos Pedro Boëchat; Leite, Hélio Garcia; Souza, Agostinho Lopes de; Nogueira, Gilciano Saraiva; Martins, Fabrina Bolzan

doi:10.1155/2013/196832

Cited by 23 publications

(9 citation statements)

References 39 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The efficiency of artificial neural networks in the processes of simulation was also observed by Soares et al (2014) in the estimation of bean yield. Castro et al (2013) proposed the use of artificial neural networks in the modeling of growth and stand of eucalyptus located in northern Brazil.…”

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in seeding density optimization and yield simulation for oat

Dornelles

Kraisig

Silva

et al. 2018

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

A B S T R A C TArtificial intelligence may represent an efficient strategy for simulation and optimization of important processes in agriculture. The main goal of the study is to propose the use of artificial intelligence, namely artificial neural networks and genetic algorithms, respectively, in the simulation of oat grain yield and optimization of seeding density, considering the main succession systems of southern Brazil. The study was conducted in a randomized complete block design with four replicates, following a 4 x 2 factorial scheme, for seeding densities (100, 300, 600 and 900 seeds m -2 ) and oat cultivars (Brisasul and URS Taura), in succession systems of corn/oats and soybean/oats. A multi-layered artificial neural network and a genetic algorithm were implemented in Java programming language, and the results obtained from this implementation were compared with traditional polynomial regression. The use of artificial intelligence through neural networks and genetic algorithms allows the efficient simulation of oat grain yield and better optimization of seeding density in comparison to polynomial regression, considering the main succession systems in southern Brazil.Inteligência artificial na otimização da densidade de semeadura e simulação da produtividade da aveia R E S U M O O uso de inteligência artificial pode representar uma estratégia eficiente de simulação e otimização de processos importantes na agricultura. O objetivo deste estudo é propor o uso de inteligência artificial via redes neurais artificiais e algoritmos genéticos, respectivamente, na simulação da produtividade de grãos de aveia (Avena sativa) e na otimização da densidade de semeadura, nos principais sistemas de sucessão do sul do Brasil. O estudo foi conduzido em blocos ao acaso com quatro repetições em esquema fatorial 4 x 2, para as densidades de semeadura (100, 300, 600 e 900 sementes m -2 ) e cultivares de aveia (Brisasul e URS Taura), nos sistemas de sucessão milho/aveia e soja/aveia. Implementou-se uma rede neural artificial de múltiplas camadas e um algoritmo genético, em linguagem de programação Java, e comparou-se os resultados obtidos desta implementação com análises tradicionais de regressão polinomial. O uso de inteligência artificial via redes neurais artificiais e algoritmos genéticos permite simular com eficiência a produtividade de grãos de aveia e melhor otimização da densidade de semeadura na comparação com regressão polinomial, considerando os principais sistemas de sucessão no sul do Brasil.

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial intelligence in seeding density optimization and yield simulation for oat

Dornelles

Kraisig

Silva

et al. 2018

Rev. bras. eng. agríc. ambient.

View full text Add to dashboard Cite

show abstract

“…In forest management, ANNs have also been applied to estimate tree volume (Gorgens et al 2009, Silva et al 2009, Diamantopoulou & Milios 2010, Özçelik et al 2010, Yu & Jia-Yin 2012, growth modeling (Castro et al 2013), tree height (Binoti et al 2013a), and to describe diameter distribution (Leite et al 2011, Binoti et al 2013b). However, none of these applications include forest management as an input variable, at least in the estimation of transpiration.…”

Section: Introductionmentioning

confidence: 99%

Coupling daily transpiration modelling with forest management in a semiarid pine plantation

Fernandes¹,

Campo²,

García-Bartual³

et al. 2016

iForest

View full text Add to dashboard Cite

Estimating forest transpiration is of great importance for Adaptive Forest Management (AFM) in the scope of climate change prediction. AFM in the Mediterranean region usually generates a mosaic of different canopy covers within the same forest. Several models and methods are available to estimate forest transpiration, but most require a homogeneous forest cover, or an individual calibration/validation process for each cover stand. Hence, a model capable of reproducing accurately the transpiration of the whole canopy-cover mosaic is necessary. In this paper, the use of Artificial Neural Network (ANN) is proposed as a flexible tool for estimating forest transpiration using the forest cover as an input variable. To that end, sap flow, soil water content and other environmental variables were experimentally collected under five Aleppo pine stands of different canopy covers for two years. These sets of inputs were then used for the ANN training. Stand transpiration was accurately estimated using climate data, soil water content and forest cover through the ANN approach (correlation coefficient R = 0.95; Nash-Sutcliffe coefficient E = 0.90; root-meansquare error RMSE = 0.078 mm day -1 ). Finally, the input value for soil water content (when not available) was computed using the process-based model Gotilwa+. Then, this computed soil water content was used as input in the proposed ANN. This combination predicted the forest transpiration with values of R = 0.90, E = 0.63, and RMSE = 0.068 mm day -1 . Artificial Neural Network proved to be a useful and flexible tool to predict the transpiration dynamics of an Aleppo pine stand regardless of the heterogeneity of the forest cover produced by adaptive forest management.

show abstract

“…The ABA with ANN was the best overall method. ANNs are currently used in forestry in many applications, for instance, developing growth and yield models [83], predicting height [84] and stem volume [85]. As a nonparametric method, it benefits from its capacity to account for data variability and non-linear relationships.…”

Section: Area-and Individual Tree-based Approach For Estimating Stem mentioning

confidence: 99%

Estimating Stem Volume in Eucalyptus Plantations Using Airborne LiDAR: A Comparison of Area- and Individual Tree-Based Approaches

et al. 2020

View full text Add to dashboard Cite

Forest plantations are globally important for the economy and are significant for carbon sequestration. Properly managing plantations requires accurate information about stand timber stocks. In this study, we used the area (ABA) and individual tree (ITD) based approaches for estimating stem volume in fast-growing Eucalyptus spp forest plantations. Herein, we propose a new method to improve individual tree detection (ITD) in dense canopy homogeneous forests and assess the effects of stand age, slope and scan angle on ITD accuracy. Field and Light Detection and Ranging (LiDAR) data were collected in Eucalyptus urophylla x Eucalyptus grandis even-aged forest stands located in the mountainous region of the Rio Doce Valley, southeastern Brazil. We tested five methods to estimate volume from LiDAR-derived metrics using ABA: Artificial Neural Network (ANN), Random Forest (RF), Support Vector Machine (SVM), and linear and Gompertz models. LiDAR-derived canopy metrics were selected using the Recursive Feature Elimination algorithm and Spearman’s correlation, for nonparametric and parametric methods, respectively. For the ITD, we tested three ITD methods: two local maxima filters and the watershed method. All methods were tested adding our proposed procedure of Tree Buffer Exclusion (TBE), resulting in 35 possibilities for treetop detection. Stem volume for this approach was estimated using the Schumacher and Hall model. Estimated volumes in both ABA and ITD approaches were compared to the field observed values using the F-test. Overall, the ABA with ANN was found to be better for stand volume estimation ( r y y ^ = 0.95 and RMSE = 14.4%). Although the ITD results showed similar precision ( r y y ^ = 0.94 and RMSE = 16.4%) to the ABA, the results underestimated stem volume in younger stands and in gently sloping terrain (<25%). Stem volume maps also differed between the approaches; ITD represented the stand variability better. In addition, we discuss the importance of LiDAR metrics as input variables for stem volume estimation methods and the possible issues related to the ABA and ITD performance.

show abstract

Individual Growth Model forEucalyptusStands in Brazil Using Artificial Neural Network

Cited by 23 publications

References 39 publications

Artificial intelligence in seeding density optimization and yield simulation for oat

Artificial intelligence in seeding density optimization and yield simulation for oat

Coupling daily transpiration modelling with forest management in a semiarid pine plantation

Estimating Stem Volume in Eucalyptus Plantations Using Airborne LiDAR: A Comparison of Area- and Individual Tree-Based Approaches

Contact Info

Product

Resources

About