Search

In forest modeling to estimate the volume of wood, artificial intelligence has been shown to be quite efficient, especially using artificial neural networks (ANNs). Here we tested whether diameter at breast height (DBH) and the total plant height (Ht) of eucalyptus can be predicted at the stand level using spectral bands measured by an unmanned aerial vehicle (UAV) multispectral sensor and vegetation indices. To do so, using the data obtained by the UAV as input variables, we tested different configurations (number of hidden layers and number of neurons in each layer) of ANNs for predicting DBH and Ht at stand level for different Eucalyptus species. The experimental design was randomized blocks with four replicates, with 20 trees in each experimental plot. The treatments comprised five Eucalyptus species (E. camaldulensis, E. uroplylla, E. saligna, E. grandis, and E. urograndis) and Corymbria citriodora. DBH and Ht for each plot at the stand level were measured seven times in separate overflights by the UAV, so that the multispectral sensor could obtain spectral bands to calculate vegetation indices (VIs). ANNs were then constructed using spectral bands and VIs as input layers, in addition to the categorical variable (species), to predict DBH and Ht at the stand level simultaneously. This report represents one of the first applications of high-throughput phenotyping for plant size traits in Eucalyptus species. In general, ANNs containing three hidden layers gave better statistical performance (higher estimated r, lower estimated root mean squared error–RMSE) due to their greater capacity for self-learning. Among these ANNs, the best contained eight neurons in the first layer, seven in the second, and five in the third (8 − 7 − 5). The results reported here reveal the potential of using the generated models to perform accurate forest inventories based on spectral bands and VIs obtained with a UAV multispectral sensor and ANNs, reducing labor and time.

Made available in DSpace on 2020-12-12T01:38:31Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-09-01 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) Universidade Federal do Rio Grande do Sul The stem volume of commercial trees is an important variable that assists in decision making and economic analysis in forest management. Wood from forest plantations can be used for several purposes, which makes estimating multi-volumes for the same tree a necessary task. Defining its exploitation and use potential, such as the total and merchantable volumes (up to a minimum diameter of interest), with or without bark, is a possible work. The goal of this study was to use different strategies to model multi-volumes of the stem of eucalyptus trees. The data came from rigorous scaling of 460 felled trees stems from four eucalyptus clones in high forest and coppice regimes. The diameters were measured at different heights, with the volume of the sections obtained by the Smalian method. Data were randomly separated into fit and validation data. The single multi-volume model, volume-specific models, and the training of artificial neural networks (ANNs) were fitted. The evaluation criteria of the models were: coefficient of determination, root mean square error, mean absolute error, mean bias error, as well as graphical analysis of observed and estimated values and distribution of residuals. Additionally, the t-test (α = 0.05) was performed between the volume obtained in the rigorous scaling and estimated by each strategy with the validation data. Results showed that the strategies used to model different tree stem volumes are efficient. The actual and estimated volumes showed no differences. The multi-volume model had the most considerable advantage in volume estimation practicality, while the volume-specific models were more efficient in the accuracy of estimates. Given the conditions of this study, the ANNs are more suitable than the regression models in the estimation of multi-volumes of eucalyptus trees, revealing greater accuracy and practicality. Federal University of Mato Grosso do Sul (UFMS) College of Agricultural Sciences (FCA) Sao Paulo State University (UNESP) College of Agricultural Sciences (FCA) Sao Paulo State University (UNESP)

Machine learning techniques (ML) have gained attention in precision agriculture practices since they efficiently address multiple applications, like estimating the growth and yield of trees in forest plantations. The combination between ML algorithms and spectral vegetation indices (VIs) from high-spatial-resolution line measurement, segment: 0.079024 m multispectral imagery, could optimize the prediction of these biometric variables. In this paper, we investigate the performance of ML techniques and VIs acquired with an unnamed aerial vehicle (UAV) to predict the diameter at breast height (DBH) and total height (Ht) of eucalyptus trees. An experimental site with six eucalyptus species was selected, and the Parrot Sequoia sensor was used. Several ML techniques were evaluated, like random forest (RF), REPTree (DT), alternating model tree (AT,) k-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), linear regression (LR), and radial basis function (RBF). Each algorithm performance was verified using the correlation coefficient (r) and the mean absolute error (MAE). We used, as input, 34 VIs as numeric variables to predict DHB and Ht. We also added to the model a categorical variable as input identifying the different eucalyptus trees species. The RF technique obtained an overall superior estimation for all the tested configurations. Still, the RBF also showed a higher performance for predicting DHB, numerically surpassing the RF both in r and MAE, in some cases. For Ht variable, the technique that obtained the smallest MAE was SVM, though in a particular test. In this regard, we conclude that a combination of ML and VIs extracted from UAV-based imagery is suitable to estimate DBH and Ht in eucalyptus species. The approach presented constitutes an interesting contribution to the inventory and management of planted forests.

The current success of rubber cultivation is related to the use of clones adapted to different edaphoclimatic regions. Hence, it is important to evaluate variables that are correlated with yield. However, a common problem is choosing the plot dimensions where these variables will be measured. In view of the above, the objective of this work was to evaluate the initial development of two rubber tree clones and to determine the ideal sample unit size to characterize trunk circumference, tree height and bark thickness. The variables circumference at breast height (CBH), total height (Ht) and bark thickness (BT) were measured in seven plots of 680.4 m², in addition to determining the plot size to satisfactorily sample each of the variables measured in each clone, 52 months after planting. At 52 months, clone RRIM 937 showed better development than RRIM600 in relation to the analyzed variables. The ideal sample unit size is different for the variables in the following order: trunk circumference> total height> bark thickness. The measurement of plots with 15 trees is adequate to represent the variability of the analyzed variables, considering the acceptable error of 10%. O sucesso atual do cultivo de seringueira está relacionado ao uso de clones adaptados a diferentes regiões edafoclimáticas. Portanto, é importante avaliar as variáveis que estão correlacionadas com o rendimento. Noentanto, um problema comum é escolher as dimensões da área onde essas variáveis serão medidas. Este trabalho foi conduzido com objetivo de avaliar o desenvolvimento inicial de dois clones de seringueira e determinar o tamanho da amostra ideal para caracterizar a circunferência do tronco, altura da árvore e espessura da casca. As variáveis circunferência na altura do peito (CBH), altura total (Ht) e espessura da casca (BT) foram medidas em sete parcelas de 680,4 m² e foi estabelecido o tamanho da parcela para amostrar satisfatoriamente cada uma das variáveis medidas em cada clone, 52 meses após o plantio. Aos 52 meses, o clone RRIM 937 apresentou melhor desenvolvimento do que RRIM600 em relação às variáveis analisadas. O tamanho ideal da unidade de amostra é diferente para as variáveis na seguinte ordem: circunferência do tronco > altura total > espessura da casca. A medida de parcelas com 15 árvores é adequada para representar a variabilidade das variáveis analisadas, considerando o erro aceitável de 10%.

The objective of this study was to perform a temporal and spatial analysis of the changes in the past global solar radiation based on climate models and remote sensing data in the State of Rio de Janeiro, Brazil for the baseline period (1961-1990). Data from two climate models - the Canadian Centre for Climate Modelling and Analysis and Geophysical Fluid Dynamic Laboratory, were used for the A1B intermediate scenario, data from Conventional Weather Stations and orbital sensor Moderate Resolution Imaging Spectroradiometer (MODIS) MODIS Land Cover Type (MCD12Q1). The results of the Spatial Dependence Degree indicate that the best model to represent the global solar radiation is CCCMA-Exponential dry 70.01 and rainy 0.21 respectively. It was possible to verify that in places where the areas are occupied by forests there was reduction of global solar radiation for both dry and rainy periods of approximately 13 MJ m-2d-1. These results indicate that these forest areas can function as islands of freshness, while maintaining the thermal comfort balanced. It was concluded that the dry period had the highest values of solar radiation compared to the rainy (57%), which can be justified by the occurrence of fires in Rio de Janeiro. O objetivo deste estudo foi realizar uma análise temporal e espacial das mudanças ocorridas da radiação solar global passada baseado em modelo climáticos e sensoriamento remoto no Estado do Rio de Janeiro, Brasil para o período baseline (1961-1990). Utilizaram-se dados de dois modelos climáticos o Canadian Centre for Climate Modelling and Analysis) e Geophysical Fluid Dynamic Laboratory para o cenário intermediário A1B, dados de Estações Meteorológicas Convencionais e do sensor orbital Moderate Resolution Imaging Spectroradiometer (MODIS) MODIS Land Cover Type (MCD12Q1). Os resultados do Grau de Dependência Espacial indicam que o melhor modelo que representa a radiação solar global é o CCCMA-Exponencial seco 70.01 e chuvoso de 0.21 respectivamente. Foi possível verificar que em locais onde as áreas são ocupadas por florestas houve redução da radiação solar global para os dois períodos seco e chuvoso de aproximadamente 13 MJ.m-2.dia-1. Estes resultados indicam que estas áreas de florestas podem funcionar como ilhas de frescor, mantendo o conforto térmico equilibrado. Conclui-se que o período seco apresentoumaiores valores de radiação solar em comparação ao chuvoso (57%), que pode ser justificado pela ocorrência de queimadas no Rio de Janeiro.