Ground-truth information of mesostructure formation and local molecular arrangements in imidazolium-based ionic liquids for training deep neural network algorithm

Training data sets were generated from X-ray scattering data of ionic liquid (IL)/water mixtures as the basis for a deep neural network (DNN) computation architecture that can predict non-equilibrium, dynamical phenomena such as chemical reactions, self-assembly, and ionization. Specialized DNN-based architectures are computationally efficient and highly accurate alternatives to the quantum mechanical simulations, which are computationally expensive. However, despite their broad applicability in chemical and materials discovery, DNNs cannot describe non-equilibrium processes such as long-range charge transfer of electrons or finite effects of electron temperature. ILs are known to form various mesoscale ordered hierarchical structures on mixing with water, comparable to the phase behavior of lyotropic liquid crystals. The hierarchical self-assembly of ionic liquids is a complex phenomenon not easily predictable by computation. Thus, IL/water mixtures are an excellent platform to produce large data set for training a DNN algorithm. Model IL systems were formed by pairing a simple anion (chloride, nitrate, or thiocyanate) with a cationic linear hydrocarbon and mixing with varied fractions of water to form mesoscale ordered structures which were measured by X-ray scattering. Quantitative analysis was performed through crystallographic methods and calculation of the radial distribution functions, which will be discussed alongside potential implementation of the data to DNN training.

 

Research presented in this presentation was supported by the Laboratory Directed Research & Development (LDRD) Program of Los Alamos National Laboratory under project number 20210087DR. Part of this work was performed at the Center for Integrated Nanotechnologies, an Office of Science User Facility operated for the U.S. Department of Energy (DOE) Office of Science. Los Alamos National Laboratory, an affirmative action equal opportunity employer, is managed by the Triad National Security, LLC for the U.S. DOE’s NNSA, under contract 89233218CNA000001.