Artificial neural networks in predicting energy density of Bambusa vulgaris in Brazil

Abstract

In this study, the physical and chemical characteristics of Bambusa vulgaris ex J.C. Wendl. var.vulgaris (Bambusa vulgaris) aged 1, 2 and 3 years were evaluated. The objective was to train, validate and evaluate the efficiency of artificial neural networks (ANNs) as predictive tools to estimate bamboo stem energy density grown commercially in northeastern Brazil. For that, samples were collected in a commercial plantation and managed for energy production, determining the energy properties. Among all the characteristics analyzed, basic apparent density was the one with major correlation with bamboo stem energy density. This factor has a great advantage because it is easy to estimate, determined both by dry mass at 0% moisture, and at saturated mass. Also, the precision of ANNs was verified when associated with basic density, as a predictor of bamboo stem energy density, showing low standard error (Syx%, 1.52) and high coefficient of determination (R² = 0.98). ANN-estimated values had no statistical difference (t cal 0.58 ≤ t tab 2.08) with energy density estimated in the laboratory. Therefore, this tool was efficient, being recommended to predict the energetic density of the species under study, with basic density as the only predictive variable.

Artificial intelligence associated with satellite data in predicting energy potential in the Brazilian savanna woodland area

“…Neural networks have also been shown to efficiently predict wood intrinsic characteristics such as moisture content (Ozsahin & Murat 2018), basic wood density , higher heating value (Estiati et al 2016), and energy density (Vale et al 2017), for which the aforementioned authors obtained better results than those reported in this study (RMSE% = 1.45%, R = 0.98, AD% = 0.14). However, those authors used basic wood density as a predictive variable.…”

“…Finally, the ANN that showed the best results was submitted to the validation process using the t-test and, subsequently, an aggregate difference in percentage (AD%), a statistical value used as indicator of under-or overestimation (Miguel et al 2015, Vale et al 2017. These analyses were conducted using the software Microsoft Excel 2013 ® (Microsoft Corp., Redmond, CA, USA).…”

“…The top five networks were retained at the end of processing. This tool allows for the optimization of the ANN architecture by defining the best number of neurons in the hidden layer and the best activation functions of the hidden and output layers (Vale et al 2017). We used the quasi-Newton algorithm developed by Broyden-Fletcher-Goldfarb-Shanno for processing the neural networks in the IPS (BFGS), which has great resolution power for optimization problems and predictions and is the most popular quasi-Newton method (Guerrout et al 2018).…”

Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks

“…The ANNs training was performed using the Intelligent Problem Solver tool from the Statistica 7.0 software [44]. This tool allows optimizing the ANN architecture by automatically setting the best number of neurons in the hidden layer and the best activation functions of the hidden and output layers, choosing the one with the least possible error, and is widely used by the scientific community [45][46][47]. https://doi.org/10.1371/journal.pone.0238703.g002…”