Optimising an artificial neural network for predicting the melting point of ionic liquids

Abstract

We present an optimised artificial neural network (ANN) model for predicting the melting point of a group of 97 imidazolium salts with varied anions. Each cation and anion in the model is described using molecular descriptors. Our model has a mean prediction error of 1.30%, a regression coefficient of 0.99 and a mean P-value of 0.92. The ANN's prediction performance depends mainly on the anion size. In particular, the prediction error decreases as the anion size increases. The high statistical relevance makes this model a useful tool for predicting the melting points of imidazolium-based ionic liquids.

Spectroscopic determination of the photodegradation of monovarietal extra virgin olive oils and their binary mixtures through intelligent systems

“…Even though there are different kinds of ANNs, the supervised multilayer perceptron (MLP) is one of the most successfully employed ANNs in scientific research [20,21], and it was the one selected to assist in the case proposed. As it is a supervised-learning ANN, there must be both input and target data so the MLP can be correctly trained and optimized [22]. Since the estimation mechanism of ANNs is based on non-linear interpolation, they strongly depend on the range of data covered by the database, because if the model were forced to extrapolate, the error attained in this case would increase [16,23].…”

Prediction of the binary surface tension of mixtures containing ionic liquids using Support Vector Machine algorithms

“…Lazzús [27] reported the successful application of artificial neural networks to correlate a total of 2410 data points of density at several temperatures and pressures (ρ-T-P), corresponding to 250 ionic liquids. Torrecilla et al [28] presented an optimized ANN model for predicting the melting point of a group of 97 imidazolium salts with various anions. Bini et al [29] reported that a recursive neural network (RNN) was an applicable tool for predicting the melting points of several pyridinium based ionic liquids (ILs).…”

Prediction of activity coefficients at infinite dilution for organic solutes in ionic liquids by artificial neural network

“…Palomar et al [20,21] developed an ANN model to estimate a set of ILs properties such as IL density, solubility of ILs in nheptane, solubility of heptane in ILs, and partition coefficients of toluene between ILs and heptane phases for 45 imidazolium-based ILs based on a priori quantum-chemical parameter. An ANN model was also developed by Torrecilla et al [22] for predicting the melting point of ionic liquids.…”