Predicting ionic liquid melting points using machine learning

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

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.

Planting the Seeds of a Decision Tree for Ionic Liquids: Steric and Electronic Impacts on Melting Points of Triarylphosponium Ionic Liquids

While machine learning and artificial intelligence offer promising avenues in the computer-aided design of materials, the complexity of these computational techniques remains a barrier for scientists outside of the specific fields of study. Leveraging decision tree models, inspired by empirical methodologies, offers a pragmatic solution to the knowledge barrier presented by artificial intelligence (AI). Herein, we present a model allowing for the qualitative prediction of melting points of ionic liquids derived from the crystallographic analysis of a series of phosphonium-based ionic liquids. By carefully tailoring the steric and electronic properties of the cations within these salts, trends in the melting points are observed, pointing toward the critical importance of π interactions to forming the solid state. Quantification of the percentage of these π interactions using modern quantum crystallographic approaches reveals a linear trend in the relationship of C-Hπ and π-π stacking interactions with melting points. These structure-property relationships are further examined by using computational studies, helping to demonstrate the inverse relationship of dipole moments and melting points for ionic liquids. The results provide valuable insights into the features and relationships that are consistent with achieving low Tm values in phosphonium salts, which were not apparent in earlier studies. The data gathered are presented in a simple decision tree format, allowing for visualization of the data and providing guidance toward developing yet unreported compounds.

Prediction and Interpretability of Melting Points of Ionic Liquids Using Graph Neural Networks

Ionic liquids (ILs) have wide and promising applications in fields such as chemical engineering, energy, and the environment. However, the melting points (MPs) of ILs are one of the most crucial properties affecting their applications. The MPs of ILs are affected by various factors, and tuning these in a laboratory is time-consuming and costly. Therefore, an accurate and efficient method is required to predict the desired MPs in the design of novel targeted ILs. In this study, three descriptor-based machine learning (DBML) models and eight graph neural network (GNN) models were proposed to predict the MPs of ILs. Fingerprints and molecular graphs were used to represent molecules for the DBML and GNNs, respectively. The GNN models demonstrated performance superior to that of the DBML models. Among all of the examined models, the graph convolutional model exhibited the best performance with high accuracy (root-mean-squared error = 37.06, mean absolute error = 28.79, and correlation coefficient = 0.76). Benefiting from molecular graph representation, we built a GNN-based interpretable model to reveal the atomistic contribution to the MPs of ILs using a data-driven procedure. According to our interpretable model, amino groups, S+, N+, and P+ would increase the MPs of ILs, while the negatively charged halogen atoms, S-, and N- would decrease the MPs of ILs. The results of this study provide new insight into the rapid screening and synthesis of targeted ILs with appropriate MPs.

Microwave Encounters Ionic Liquid: Synergistic Mechanism, Synthesis and Emerging Applications

Progress in microwave (MW) energy application technology has stimulated remarkable advances in manufacturing and high-quality applications of ionic liquids (ILs) that are generally used as novel media in chemical engineering. This Review focuses on an emerging technology via the combination of MW energy and the usage of ILs, termed microwave-assisted ionic liquid (MAIL) technology. In comparison to conventional routes that rely on heat transfer through media, the contactless and unique MW heating exploits the electromagnetic wave-ions interactions to deliver energy to IL molecules, accelerating the process of material synthesis, catalytic reactions, and so on. In addition to the inherent advantages of ILs, including outstanding solubility, and well-tuned thermophysical properties, MAIL technology has exhibited great potential in process intensification to meet the requirement of efficient, economic chemical production. Here we start with an introduction to principles of MW heating, highlighting fundamental mechanisms of MW induced process intensification based on ILs. Next, the synergies of MW energy and ILs employed in materials synthesis, as well as their merits, are documented. The emerging applications of MAIL technologies are summarized in the next sections, involving tumor therapy, organic catalysis, separations, and bioconversions. Finally, the current challenges and future opportunities of this emerging technology are discussed.

Computer-Aided Molecular Design of Ionic Liquids as Advanced Process Media: A Review from Fundamentals to Applications

The unique physicochemical properties, flexible structural tunability, and giant chemical space of ionic liquids (ILs) provide them a great opportunity to match different target properties to work as advanced process media. The crux of the matter is how to efficiently and reliably tailor suitable ILs toward a specific application. In this regard, the computer-aided molecular design (CAMD) approach has been widely adapted to cover this family of high-profile chemicals, that is, to perform computer-aided IL design (CAILD). This review discusses the past developments that have contributed to the state-of-the-art of CAILD and provides a perspective about how future works could pursue the acceleration of the practical application of ILs. In a broad context of CAILD, key aspects related to the forward structure-property modeling and reverse molecular design of ILs are overviewed. For the former forward task, diverse IL molecular representations, modeling algorithms, as well as representative models on physical properties, thermodynamic properties, among others of ILs are introduced. For the latter reverse task, representative works formulating different molecular design scenarios are summarized. Beyond the substantial progress made, some future perspectives to move CAILD a step forward are finally provided.

Machine learning modeling for the prediction of plastic properties in metallic glasses

Metallic glasses are one of the most interesting mechanical materials studied in the last years, but as amorphous solids, they differ strongly from their crystalline counterparts. This matter can be addressed with the development and application of predictive techniques capable to describe the plastic regime. Here, machine learning models were employed for the prediction of plastic properties in CuZr metallic glasses. To this aim, 100 different samples were subjected to tensile tests by means of molecular dynamics simulations. A total of 17 materials properties were calculated and explored using statistical analysis. Strong correlations were found for stoichiometry, temperature, structural, and elastic properties with plastic properties. Three regression models were employed for the prediction of six plastic properties. Linear and Ridge regressions delivered the better prediction capability, with coefficients of determination above [Formula: see text]80% for three plastic properties, whereas Lasso regression rendered lower performance, with coefficients of determination above [Formula: see text]60% for two plastic properties. Overall, our work shows that molecular dynamics simulations together with machine learning models can provide a framework for the prediction of plastic behavior of complex materials.

Size-dependent melting of onion-like fullerenic carbons: a molecular dynamics and machine learning study

The melting thermodynamic characteristics of 2- to 20-layered onion-like fullerenes (OLF_n) (C₆₀@C₂₄₀to C₆₀@···@C₆₀₀₀···@C₂₄₀₀₀) are comprehensively explored using first-principles-based ReaxFF atomistic simulations and random forest machine learning (RF ML). It is revealed that OLF_nshows lower thermal stability than the counterparts of single-walled fullerenes (SWF_n). The melting point of SWF_nincreases monotonically with increasing size, whereas for OLF_n, an unusual size-dependent melting point is observed; OLF_nwith intermediate size shows the highest melting point. For small OLF_n, the melting occurs from the inner to the outer, whereas for large OLF_n, it nucleates from the inner to the outer and to intermediate fullerenes. The melting and erosion behaviors of both SWF_nand OLF_nare mainly characterized by the nucleation of non-hexagons, nanovoids, carbon chains and emission of C₂. RF ML model is developed to predict the melting points of both SWF_nand OLF_n. Moreover, the analysis of the feature importance reveals that the Stone-Wales transformation is a critical pathway in the melting of SWF_nand OLF_n. This study provides new insights and perspectives into the thermodynamics and pyrolysis chemistry of fullerenic carbons, and also may shed some lights onto the understanding of thermally-induced erosion of carbon-based resources and spacecraft materials.

Ab initio machine learning of phase space averages

Equilibrium structures determine material properties and biochemical functions. We here propose to machine learn phase space averages, conventionally obtained by ab initio or force-field-based molecular dynamics (MD) or Monte Carlo (MC) simulations. In analogy to ab initio MD, our ab initio machine learning (AIML) model does not require bond topologies and, therefore, enables a general machine learning pathway to obtain ensemble properties throughout the chemical compound space. We demonstrate AIML for predicting Boltzmann averaged structures after training on hundreds of MD trajectories. The AIML output is subsequently used to train machine learning models of free energies of solvation using experimental data and to reach competitive prediction errors (mean absolute error ∼ 0.8 kcal/mol) for out-of-sample molecules-within milliseconds. As such, AIML effectively bypasses the need for MD or MC-based phase space sampling, enabling exploration campaigns of Boltzmann averages throughout the chemical compound space at a much accelerated pace. We contextualize our findings by comparison to state-of-the-art methods resulting in a Pareto plot for the free energy of solvation predictions in terms of accuracy and time.

Machine Learning Prediction of Critical Temperature of Organic Refrigerants by Molecular Topology

In this work, molecular structures, combined with machine learning algorithms, were applied to predict the critical temperatures (Tc) of a group of organic refrigerants. Aiming at solving the problem that previous models cannot distinguish isomers, a topological index was introduced. The results indicate that the novel molecular descriptor ‘molecular fingerprint + topological index’ can effectively differentiate isomers. The average absolute average deviation between the predicted and experimental values is 3.99%, which proves a reasonable prediction ability of the present method. In addition, the performance of the proposed model was compared with that of other previously reported methods. The results show that the present model is superior to other approaches with respect to accuracy.

A review on machine learning algorithms for the ionic liquid chemical space

There are thousands of papers published every year investigating the properties and possible applications of ionic liquids. Industrial use of these exceptional fluids requires adequate understanding of their physical properties, in order to create the ionic liquid that will optimally suit the application. Computational property prediction arose from the urgent need to minimise the time and cost that would be required to experimentally test different combinations of ions. This review discusses the use of machine learning algorithms as property prediction tools for ionic liquids (either as standalone methods or in conjunction with molecular dynamics simulations), presents common problems of training datasets and proposes ways that could lead to more accurate and efficient models.

Machine Learning for Ionic Liquid Toxicity Prediction

In addition to proper physicochemical properties, low toxicity is also desirable when seeking suitable ionic liquids (ILs) for specific applications. In this context, machine learning (ML) models were developed to predict the IL toxicity in leukemia rat cell line (IPC-81) based on an extended experimental dataset. Following a systematic procedure including framework construction, hyper-parameter optimization, model training, and evaluation, the feedforward neural network (FNN) and support vector machine (SVM) algorithms were adopted to predict the toxicity of ILs directly from their molecular structures. Based on the ML structures optimized by the five-fold cross validation, two ML models were established and evaluated using IL structural descriptors as inputs. It was observed that both models exhibited high predictive accuracy, with the SVM model observed to be slightly better than the FNN model. For the SVM model, the determination coefficients were 0.9289 and 0.9202 for the training and test sets, respectively. The satisfactory predictive performance and generalization ability make our models useful for the computer-aided molecular design (CAMD) of environmentally friendly ILs.

Cellulose Nanocrystal and Water-Soluble Cellulose Derivative Based Electromechanical Bending Actuators

This study reports a versatile method for the development of cellulose nanocrystals (CNCs) and water-soluble cellulose derivatives (methyl cellulose (MC), hydroxypropyl cellulose (HPC), and sodium carboxymethyl cellulose (NaCMC)) films comprising the ionic liquid (IL) 2-hydroxy-ethyl-trimethylammonium dihydrogen phosphate ([Ch][DHP]) for actuator fabrication. The influence of the IL content on the morphology and physico–chemical properties of free-standing composite films was evaluated. Independently of the cellulose derivative, the ductility of the films increases upon [Ch][DHP] incorporation to yield elongation at break values of nearly 15%. An increase on the electrical conductivity as a result of the IL incorporation into cellulosic matrices is found. The actuator performance of composites was evaluated, NaCMC/[Ch][DHP] showing the maximum displacement along the x-axis of 9 mm at 8 Vpp. Based on the obtained high electromechanical actuation performance, together with their simple processability and renewable nature, the materials fabricated here represent a step forward in the development of sustainable soft actuators of high practical relevance.

Predicting Melting Points of Biofriendly Choline-Based Ionic Liquids with Molecular Dynamics

In this work, we introduce a simulation-based method for predicting the melting point of ionic liquids without prior knowledge of their crystal structure. We run molecular dynamics simulations of biofriendly, choline cation-based ionic liquids and apply the method to predict their melting point. The root-mean-square error of the predicted values is below 24 K. We advocate that such precision is sufficient for designing ionic liquids with relatively low melting points. The workflow for simulations is available for everyone and can be adopted for any species from the wide chemical space of ionic liquids.

Hydroxyl Functionalized Pyridinium Ionic Liquids: Experimental and Theoretical Study on Physicochemical and Electrochemical Properties

Structurally modified hydroxyl functionalized pyridinium ionic liquids (ILs), liquid at room temperature, were synthesized and characterized. Alkylated N-(2-hydroxyethyl)-pyridinium ILs were prepared from alkylpyridines via corresponding bromide salts by N-alkylation (65–93%) and final anion exchange (75–96%). Pyridinium-alkylation strongly influenced the IL physicochemical and electrochemical properties. Experimental values for the ILs physicochemical properties (density, viscosity, conductivity, and thermal decomposition temperature), were in good agreement with corresponding predicted values obtained by theoretical calculations. The pyridinium ILs have electrochemical window of 3.0–5.4 V and were thermally stable up to 405°C. The IL viscosity and density were measured over a wide temperature range (25–80°C). Pyridine alkyl-substitution strongly affected the partial positive charge on the nitrogen atom of the pyridinium cations, as shown by charge distribution calculations. On-going studies on Mg complexes of the new ILs demonstrate promising properties for high current density electrodeposition of magnesium.

The Ionic Liquid Property Explorer: An Extensive Library of Task-Specific Solvents

Ionic liquids have a broad spectrum of applications ranging from gas separation to sensors and pharmaceuticals. Rational selection of the constituent ions is key to achieving tailor-made materials with functional properties. To facilitate the discovery of new ionic liquids for sustainable applications, we have created a virtual library of over 8 million synthetically feasible ionic liquids. Each structure has been evaluated for their-task suitability using data-driven statistical models calculated for 12 highly relevant properties: melting point, thermal decomposition, glass transition, heat capacity, viscosity, density, cytotoxicity, CO 2 solubility, surface tension, and electrical and thermal conductivity. For comparison, values of six properties computed using quantum chemistry based equilibrium thermodynamics COSMO-RS methods are also provided. We believe the data set will be useful for future efforts directed towards targeted synthesis and optimization.