Advancing Ionic Liquid Research with pSCNN: A Novel Approach for Accurate Normal Melting Temperature Predictions

Abstract

Ionic liquids (ILs), known for their distinct and tunable properties, offer a broad spectrum of potential applications across various fields, including chemistry, materials science, and energy storage. However, practical applications of ILs are often limited by their unfavorable physicochemical properties. Experimental screening becomes impractical due to the vast number of potential IL combinations. Therefore, the development of a robust and efficient model for predicting the IL properties is imperative. As the defining feature, it is of practice significance to establish an accurate yet efficient model to predict the normal melting point of IL (T _m), which may facilitate the discovery and design of novel ILs for specific applications. In this study, we presented a pseudo-Siamese convolution neural network (pSCNN) inspired by SCNN and focused on the T _m. Utilizing a data set of 3098 ILs, we systematically assess various deep learning models (ANN, pSCNN, and Transformer-CNF), along with molecular descriptors (ECFP fingerprint and Mordred properties), for their performance in predicting the T _m of ILs. Remarkably, among the investigated modeling schemes, the pSCNN, coupled with filtered Mordred descriptors, demonstrates superior performance, yielding mean absolute error (MAE) and root-mean-square error (RMSE) values of 24.36 and 31.56 °C, respectively. Feature analysis further highlights the effectiveness of the pSCNN model. Moreover, the pSCNN method, with a pair of inputs, can be extended beyond ionic liquid melting point prediction.

Figure 1

Various machine learning models for predicting the T_m of ionic liquids.

Figure 2

Distribution of the ionic liquid melting temperature in the whole data set (red line) and the standard normal distribution curve (green line).

Figure 3

Schematic diagram of the proposed pSCNN model. pSCNN consists of two networks. The first one is a pseudo-Siamese convolution network for learning and extracting features of anions and cations. The extracted features are concatenated and fed into the MLP with two dense layers for prediction.

Figure 4

Parity plot comparing the predicted melting point values (T_m,pred) with the corresponding experimental values (T_m,exp).

Figure 5

Boundaries of the applicability domain for the pSCNN model. Compounds positioned to the left of the gray dashed line fall within the 95% confidence interval, while those positioned to the left of the green dashed line are within the 99% confidence interval.

Figure 6

Top 10 most important molecular descriptors that have a significant impact on the T_m of ILs.

Figure 7

Predicted melting points of all potential ILs generated by the pSCNN model.