Radial basis function neural networks for modeling growth rates of the basidiomycetes Physisporinus vitreus and Neolentinus lepideus

Abstract

A radial basis function (RBF) neural network was developed and compared against a quadratic response surface (RS) model for predicting the specific growth rates of the biotechnologically important basidiomycetous fungi, Physisporinus vitreus and Neolentinus lepideus, under three environmental conditions: temperature (10-30 degrees C), water activity (0.950-9.998), and pH (4-6). Both the RBF network and polynomial RS model were mathematically evaluated against experimental data using graphical plots and several statistical indices. The evaluation showed that both models gave reasonably good predictions, but the performance of the RBF neural network was superior to that of the classical statistical method for all three data sets used (training, testing, full). Sensitivity analysis revealed that of the three experimental factors the most influential on the growth rate of P. vitreus was water activity, followed by temperature and pH to a lesser extent. In contrast, temperature in particular and then water activity were the key determinants of the development of N. lepideus. RBF neural networks could be a powerful technique for modeling fungal growth behavior under certain parameters and an alternative to time-consuming, traditional microbiological techniques.

Effect of Physisporinus vitreus on wood properties of Norway spruce. Part 2: Aspects of microtensile strength and chemical changes

“…To this purpose, a detailed knowledge of the degradation pattern of P. vitreus and of the resulting chemical alterations is crucial. Factors during incubation such as temperature, water activity, nutrient and oxygen supply have an influence on the homogeneity, the speed of substrate colonization and finally on the selectivity of fungal activity towards different cell wall components (Schubert et al , 2010. Especially, the carbon/ nitrogen-ratio (C/N-ratio) has recently been discussed to affect the degradation characteristics of P. vitreus during incubation (Lehringer et al 2010).…”

Physisporinus vitreus: a versatile white rot fungus for engineering value-added wood products

“…Highly efficient modification of wood by P. vitreus is based on optimal development of the mycelium, including the lag phase, hyphal elongation, and branching (Schubert et al 2010a). Mycelial growth is greatly influenced by environmental conditions (Rayner and Boddy 1988), and the effect of the fungus is inextricably linked to the underlying substrate, wood, which is a complex anisotropic material with several hierarchical levels of organization from the macroscopic (e.g., growth rings), the mesoscopic (e.g., the set of wood cells) down to the microscopic, and nanoscopic scales (e.g., wood cells and fibrils).…”

“…This strategy is time consuming, requires a large number of experiments, and does not include interactive effects among the parameters on the process. To overcome these problems, we developed a radial basis function neural network and a response surface model for describing and predicting the lag phase and the specific growth rate of P. vitreus under combined effects of a range of parameters [i.e., temperature, water activity (a w ), and pH] (Schubert et al 2009a(Schubert et al , 2010a. Our results show that temperature and a w , in particular, are key determinants of the development of P. vitreus, and pH plays a secondary role (Schubert et al 2009a).…”

Penetration capacity of the wood-decay fungus Physisporinus vitreus

“…This biotechnological process, which is termed bioincising, can be used to improve the uptake of wood preservatives and wood modification substances Schwarze & Schubert 2011). In this context several studies concerning P. vitreus addressed the anatomy of treated Norway spruce wood (Fuhr et al 2011a;Lehringer et al 2010;Stührk et al 2010;Fuhr et al 2012), the influence of environmental factors to its radial growth rate (Fuhr et al 2011b;Schubert et al 2010) and the alteration of wood properties Schwarze et al 2008;Lehringer et al 2011a;Lehringer et al 2011b). Despite their potential, the methods mentioned are unable to illustrate the influence of microscopic effects such as the pit degradation rate on the macroscopic behavior of the fungus, because wood is an opaque material and the in vivo observation of processes inside a wood sample has not been possible until now.…”