Artificial neural networks (ANN) was evaluated and compared with Response Surface Model (RSM) results using growth response data for E.coli O157:H7 as affected by 5 variables: pH, sodium chloride, and nitrite concentrations, temperature, and aerobic/anaerobic conditions. The best ANN obtained, where the 2 kinetic parameters, growth rate and lag-time, were estimated jointly, contained 17 parameters and displayed a slightly lower Standard Error of Prediction (% SEP) than those obtained with RSM. Mathematical lag-time validation with additional data gave a lower %SEP for ANN (18%) than for RSM (27%), although growth-rate values were the same (22%). ANN thus should provide the innovative possibility of obtaining a single predictive model for the estimation of several kinetic parameters.

This article presents a new approach to the Artificial Neural Networks (ANN) modeling of bacterial growth; using Neural Network models based on Product Units (PUNN) instead of on sigmoidal units (multilayer perceptron type [MLP]) of kinetic parameters (lag‐time, growth rate, and maximum population density) of Leuconostoc mesenteroides and those factors affecting their growth such as storage temperature, pH, NaCl, and NaNO2 concentrations under anaerobic conditions. To enable the best degree of interpretability, a series of simple rules to simplify the expression of the model were set up. The new model PUNN was compared with Response Surface (RS) and MLP estimations developed previously. Standard Estimation Error of generalization (SEPG’) values obtained by PUNN were lower for lag‐time and growth rate but higher for maximum population density than MLP when validated against a new data set. In all cases, bias factors (Bf) and accuracy factors (Af) were close to unity, which indicates a good fit between the observations and predictions for the 3 models. In our study, PUNN and MLP models were more complex than the RS models, especially in the case of the growth rate parameter, but they described lower SEPG’. With this work we have attempted to propose a new approach to neural networks estimations for its application on predictive microbiology, searching for models with easier interpretation and with a great ability to fit the data on the boundaries of variables range. We consider that still there is a lot left to do but PUNN could be a very valuable instrument for mathematical modeling.